05221632

app/logs/2025-05-22/south-forecast.2025-05-22.0.log

@@ -0,0 +1,1322 @@
+2025-05-22 11:00:08,282 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:00:08,613 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 11:00:11,212 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:00:14,107 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:00:14,110 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:00:14,392 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 11:00:14,401 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 11:00:14,415 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 11:00:14,419 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 11:00:14,423 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 11:00:14,427 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 11:00:14,463 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 11:00:14,463 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 11:00:14,463 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 11:00:14,463 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 11:00:14,464 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 11:00:14,464 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 11:00:15,484 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 11:00:15,484 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 11:00:15,485 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 11:00:15,485 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 11:00:28,458 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 11:00:28,458 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 11:00:28,458 - tf_lstm.py - INFO - 训练集损失函数为：[9.0069e-01 3.1528e-01 9.7720e-02 2.6780e-02 6.4900e-03 1.4300e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 11:00:28,458 - tf_lstm.py - INFO - 训练集损失函数为：[9.0124e-01 3.1763e-01 9.9520e-02 2.7860e-02 7.1800e-03 1.9800e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 11:00:28,459 - tf_lstm.py - INFO - 验证集损失函数为：[5.0957e-01 1.6535e-01 4.7580e-02 1.2060e-02 2.7500e-03 6.1000e-04
+ 1.7000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 11:00:28,459 - tf_lstm.py - INFO - 验证集损失函数为：[0.51216 0.16791 0.0493  0.01325 0.00369 0.00147 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 11:00:28,518 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682e934cf784a6b4a7b99c0b - insert_trained_model_into_mongo
+2025-05-22 11:00:28,528 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682e934c6e3c6f67919b8a61 - insert_trained_model_into_mongo
+2025-05-22 11:00:28,553 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682e934c6e3c6f67919b8a63 - insert_scaler_model_into_mongo
+2025-05-22 11:00:28,559 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682e934cf784a6b4a7b99c0d - insert_scaler_model_into_mongo
+2025-05-22 11:00:29,840 - task_worker.py - ERROR - Area -99 failed: 'NoneType' object has no attribute 'area_id' - region_task
+2025-05-22 11:07:40,679 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:07:44,165 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 11:08:09,067 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:13:00,030 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:13:00,144 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 11:13:02,718 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:13:05,631 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:13:05,632 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 11:13:05,855 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 11:13:05,855 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 11:13:05,873 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 11:13:05,873 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 11:13:05,881 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 11:13:05,881 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 11:13:05,909 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 11:13:05,909 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 11:13:05,909 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 11:13:05,909 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 11:13:05,909 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 11:13:05,910 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 11:13:06,849 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 11:13:06,850 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 11:13:06,872 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 11:13:06,872 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 11:13:19,649 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 11:13:19,649 - tf_lstm.py - INFO - 训练集损失函数为：[9.0405e-01 3.1641e-01 9.7950e-02 2.6820e-02 6.5000e-03 1.4300e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 11:13:19,649 - tf_lstm.py - INFO - 验证集损失函数为：[5.1157e-01 1.6582e-01 4.7650e-02 1.2070e-02 2.7500e-03 6.1000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 11:13:19,659 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 11:13:19,660 - tf_lstm.py - INFO - 训练集损失函数为：[9.0396e-01 3.1831e-01 9.9550e-02 2.7800e-02 7.1400e-03 1.9600e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 11:13:19,660 - tf_lstm.py - INFO - 验证集损失函数为：[0.51355 0.16811 0.04924 0.01319 0.00367 0.00146 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00088 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 11:13:19,705 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682e964ff0d6786d32a727ec - insert_trained_model_into_mongo
+2025-05-22 11:13:19,709 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682e964f3e4b222ab549997c - insert_trained_model_into_mongo
+2025-05-22 11:13:19,728 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682e964ff0d6786d32a727ee - insert_scaler_model_into_mongo
+2025-05-22 11:13:19,733 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682e964f3e4b222ab549997e - insert_scaler_model_into_mongo
+2025-05-22 11:13:21,022 - task_worker.py - ERROR - Area -99 failed: 'NoneType' object has no attribute 'area_id' - region_task
+2025-05-22 13:06:09,682 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:06:09,939 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 13:06:12,715 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:06:15,661 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:06:15,662 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:06:15,932 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 13:06:15,932 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 13:06:15,959 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:06:15,959 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:06:15,967 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:06:15,968 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:06:16,004 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:06:16,004 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:06:16,005 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:06:16,005 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:06:16,005 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:06:16,005 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:06:17,007 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:06:17,007 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:06:17,007 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:06:17,007 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:06:29,989 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:06:29,990 - tf_lstm.py - INFO - 训练集损失函数为：[9.0225e-01 3.1749e-01 9.9030e-02 2.7310e-02 6.6500e-03 1.4700e-03
+ 3.3000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 13:06:29,990 - tf_lstm.py - INFO - 验证集损失函数为：[0.50924 0.16612 0.04859 0.013   0.00362 0.00146 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 13:06:29,990 - tf_lstm.py - INFO - 验证集损失函数为：[5.1195e-01 1.6715e-01 4.8400e-02 1.2340e-02 2.8200e-03 6.2000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 13:06:30,043 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb0d6741733b69380e30e - insert_trained_model_into_mongo
+2025-05-22 13:06:30,044 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb0d63e5e1c931e47042e - insert_trained_model_into_mongo
+2025-05-22 13:06:30,052 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb0d6741733b69380e310 - insert_scaler_model_into_mongo
+2025-05-22 13:06:30,052 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb0d63e5e1c931e470430 - insert_scaler_model_into_mongo
+2025-05-22 13:06:31,384 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 13:21:28,302 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:21:32,961 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 13:21:55,981 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:22:19,846 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:22:19,965 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:22:32,298 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 13:22:32,299 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 13:22:49,121 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:22:49,123 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:22:59,511 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:22:59,519 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:22:59,558 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:22:59,558 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:22:59,560 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:22:59,565 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:22:59,565 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:22:59,567 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:23:14,175 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:23:14,175 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:23:14,176 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:23:14,177 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:23:52,897 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:23:52,897 - tf_lstm.py - INFO - 训练集损失函数为：[9.0598e-01 3.1883e-01 9.9640e-02 2.7810e-02 7.1500e-03 1.9700e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 13:23:52,898 - tf_lstm.py - INFO - 验证集损失函数为：[0.51461 0.16825 0.04928 0.0132  0.00367 0.00147 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 13:23:52,944 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:23:52,945 - tf_lstm.py - INFO - 训练集损失函数为：[9.0190e-01 3.1699e-01 9.8690e-02 2.7170e-02 6.6100e-03 1.4600e-03
+ 3.3000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 13:23:52,945 - tf_lstm.py - INFO - 验证集损失函数为：[5.1143e-01 1.6671e-01 4.8180e-02 1.2270e-02 2.8100e-03 6.3000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 13:23:58,957 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb4ee215b380c4e277f3d - insert_trained_model_into_mongo
+2025-05-22 13:23:58,962 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb4eef0381e0011af450d - insert_trained_model_into_mongo
+2025-05-22 13:23:58,970 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb4ee215b380c4e277f3f - insert_scaler_model_into_mongo
+2025-05-22 13:23:58,987 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb4eef0381e0011af450f - insert_scaler_model_into_mongo
+2025-05-22 13:25:06,867 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:25:10,017 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 13:25:33,151 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:25:56,908 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:25:56,915 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:31:51,198 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:31:51,314 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 13:31:53,876 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:31:56,769 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:31:56,769 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:31:56,973 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 13:31:56,974 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 13:31:56,992 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:31:56,993 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:31:57,000 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:31:57,001 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:31:57,027 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:31:57,027 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:31:57,028 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:31:57,028 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:31:57,029 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:31:57,029 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:31:57,948 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:31:57,949 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:31:57,957 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:31:57,958 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:32:10,777 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:32:10,778 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:32:10,778 - tf_lstm.py - INFO - 训练集损失函数为：[8.9570e-01 3.1407e-01 9.7760e-02 2.7200e-02 6.9900e-03 1.9300e-03
+ 8.1000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 13:32:10,778 - tf_lstm.py - INFO - 训练集损失函数为：[9.0424e-01 3.1647e-01 9.8080e-02 2.6880e-02 6.5100e-03 1.4300e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 13:32:10,778 - tf_lstm.py - INFO - 验证集损失函数为：[0.5076  0.16537 0.04823 0.01291 0.0036  0.00145 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00088 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 13:32:10,778 - tf_lstm.py - INFO - 验证集损失函数为：[5.1157e-01 1.6595e-01 4.7750e-02 1.2100e-02 2.7500e-03 6.1000e-04
+ 1.7000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 13:32:10,816 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb6daed827ab3f0037eb2 - insert_trained_model_into_mongo
+2025-05-22 13:32:10,816 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb6dad7c91141fbffba57 - insert_trained_model_into_mongo
+2025-05-22 13:32:10,848 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb6dad7c91141fbffba59 - insert_scaler_model_into_mongo
+2025-05-22 13:32:10,863 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb6daed827ab3f0037eb4 - insert_scaler_model_into_mongo
+2025-05-22 13:32:12,164 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 13:36:17,718 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:36:17,835 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 13:36:20,536 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:36:23,520 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:36:23,524 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:36:23,730 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 13:36:23,730 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 13:36:23,748 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:36:23,748 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:36:23,757 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:36:23,757 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:36:23,784 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:36:23,784 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:36:23,785 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:36:23,786 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:36:23,786 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:36:23,787 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:36:24,750 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:36:24,751 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:36:24,755 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:36:24,755 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:36:37,674 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:36:37,674 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:36:37,675 - tf_lstm.py - INFO - 训练集损失函数为：[9.0215e-01 3.1682e-01 9.8480e-02 2.7050e-02 6.5600e-03 1.4400e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 13:36:37,675 - tf_lstm.py - INFO - 验证集损失函数为：[0.51142 0.16709 0.04888 0.01311 0.00366 0.00147 0.00102 0.00093 0.00091
+ 0.0009  0.0009  0.00089 0.00089 0.00088 0.00088 0.00088 0.00088 0.00087
+ 0.00087 0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 13:36:37,675 - tf_lstm.py - INFO - 验证集损失函数为：[5.1143e-01 1.6646e-01 4.8020e-02 1.2190e-02 2.7800e-03 6.2000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 13:36:37,713 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb7e5627b101c684d84af - insert_trained_model_into_mongo
+2025-05-22 13:36:37,720 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb7e5627b101c684d84b1 - insert_scaler_model_into_mongo
+2025-05-22 13:36:37,736 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eb7e5c78eb332b44d57b5 - insert_trained_model_into_mongo
+2025-05-22 13:36:37,757 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eb7e5c78eb332b44d57b7 - insert_scaler_model_into_mongo
+2025-05-22 13:36:39,035 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 13:43:10,995 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:43:14,416 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 13:43:37,750 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:44:04,231 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:44:04,235 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 13:45:28,979 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 13:45:28,979 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 13:45:29,000 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:45:29,001 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 13:45:29,028 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:45:29,029 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 13:45:29,071 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:45:29,072 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:45:29,073 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 13:45:29,073 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 13:45:29,074 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:45:29,075 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 13:45:31,139 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:45:31,140 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:45:31,142 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 13:45:31,143 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 13:46:07,442 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:46:07,442 - tf_lstm.py - INFO - 训练集损失函数为：[8.9715e-01 3.1446e-01 9.7490e-02 2.6710e-02 6.4700e-03 1.4300e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 13:46:07,443 - tf_lstm.py - INFO - 验证集损失函数为：[5.0805e-01 1.6497e-01 4.7450e-02 1.2030e-02 2.7400e-03 6.1000e-04
+ 1.7000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 13:46:07,584 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 13:46:07,584 - tf_lstm.py - INFO - 训练集损失函数为：[8.9563e-01 3.1477e-01 9.8380e-02 2.7490e-02 7.0800e-03 1.9500e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 13:46:07,584 - tf_lstm.py - INFO - 验证集损失函数为：[0.50812 0.16611 0.04868 0.01307 0.00365 0.00146 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00088 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 13:46:14,116 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eba26770d6ffe7e22a033 - insert_trained_model_into_mongo
+2025-05-22 13:46:14,120 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eba26d439ed5d688f8e53 - insert_trained_model_into_mongo
+2025-05-22 13:46:14,129 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eba26770d6ffe7e22a035 - insert_scaler_model_into_mongo
+2025-05-22 13:46:14,166 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eba26d439ed5d688f8e55 - insert_scaler_model_into_mongo
+2025-05-22 14:22:14,267 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:22:14,388 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 14:22:17,074 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:22:19,916 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:22:22,871 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:22:22,872 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:22:23,608 - task_worker.py - ERROR - Area -99 failed: 'NoneType' object has no attribute 'area_id' - region_task
+2025-05-22 14:26:54,980 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:26:55,106 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 14:26:57,683 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:00,530 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:03,427 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:03,432 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:04,177 - task_worker.py - ERROR - Area -99 failed: 'NoneType' object has no attribute 'area_id' - region_task
+2025-05-22 14:27:41,884 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:42,000 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 14:27:44,598 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:47,308 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:50,203 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:50,204 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 14:27:50,954 - task_worker.py - ERROR - Area 1002 failed: Can only merge Series or DataFrame objects, a <class 'multiprocessing.managers.DictProxy'> was passed - region_task
+2025-05-22 15:56:08,387 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:56:08,656 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 15:56:11,294 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:56:14,276 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:56:14,282 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:56:14,515 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 15:56:14,534 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 15:56:14,537 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 15:56:14,546 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 15:56:14,553 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 15:56:14,561 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 15:56:14,583 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 15:56:14,583 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 15:56:14,584 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 15:56:14,588 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 15:56:14,588 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 15:56:14,589 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 15:56:15,565 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 15:56:15,566 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 15:56:15,566 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 15:56:15,566 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 15:56:28,464 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 15:56:28,464 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 15:56:28,465 - tf_lstm.py - INFO - 训练集损失函数为：[8.9989e-01 3.1527e-01 9.8050e-02 2.7280e-02 7.0200e-03 1.9400e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 15:56:28,465 - tf_lstm.py - INFO - 训练集损失函数为：[9.0568e-01 3.1746e-01 9.8530e-02 2.7070e-02 6.5900e-03 1.4600e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 15:56:28,465 - tf_lstm.py - INFO - 验证集损失函数为：[0.50977 0.16589 0.04836 0.01296 0.00362 0.00146 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 15:56:28,465 - tf_lstm.py - INFO - 验证集损失函数为：[5.1289e-01 1.6660e-01 4.8030e-02 1.2220e-02 2.8000e-03 6.2000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 15:56:28,507 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682ed8acd5726df85922d205 - insert_trained_model_into_mongo
+2025-05-22 15:56:28,522 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682ed8ac2e1adc5f49fe0f09 - insert_trained_model_into_mongo
+2025-05-22 15:56:28,529 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682ed8acd5726df85922d207 - insert_scaler_model_into_mongo
+2025-05-22 15:56:28,543 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682ed8ac2e1adc5f49fe0f0b - insert_scaler_model_into_mongo
+2025-05-22 15:56:29,862 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 15:57:07,940 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:57:08,055 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 15:57:10,632 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:57:13,508 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:57:13,518 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 15:57:13,711 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 15:57:13,718 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 15:57:13,729 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 15:57:13,736 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 15:57:13,737 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 15:57:13,744 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 15:57:13,770 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 15:57:13,770 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 15:57:13,770 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 15:57:13,776 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 15:57:13,776 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 15:57:13,777 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 15:57:14,694 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 15:57:14,694 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 15:57:14,712 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 15:57:14,713 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 15:57:27,628 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 15:57:27,628 - tf_lstm.py - INFO - 训练集损失函数为：[9.1627e-01 3.2273e-01 1.0049e-01 2.7670e-02 6.7300e-03 1.4900e-03
+ 3.3000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 15:57:27,628 - tf_lstm.py - INFO - 验证集损失函数为：[5.2048e-01 1.6975e-01 4.9060e-02 1.2500e-02 2.8600e-03 6.3000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 15:57:27,654 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 15:57:27,655 - tf_lstm.py - INFO - 训练集损失函数为：[9.1329e-01 3.2208e-01 1.0066e-01 2.8050e-02 7.1900e-03 1.9700e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 15:57:27,655 - tf_lstm.py - INFO - 验证集损失函数为：[0.51954 0.17006 0.04973 0.01329 0.00368 0.00147 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 15:57:27,670 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682ed8e7d0ad45b5ef1ff99f - insert_trained_model_into_mongo
+2025-05-22 15:57:27,693 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682ed8e7952fc3d26b39b369 - insert_trained_model_into_mongo
+2025-05-22 15:57:27,698 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682ed8e7d0ad45b5ef1ff9a1 - insert_scaler_model_into_mongo
+2025-05-22 15:57:27,700 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682ed8e7952fc3d26b39b36b - insert_scaler_model_into_mongo
+2025-05-22 15:57:28,989 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 16:00:26,751 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:02:27,969 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 16:02:51,521 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:03:20,174 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:03:20,244 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:03:43,812 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 16:03:43,818 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 16:03:43,837 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:03:43,843 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:03:43,869 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:03:43,874 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:03:43,915 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:03:43,916 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:03:43,918 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:03:43,920 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:03:43,920 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:03:43,922 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:03:45,818 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:03:45,820 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:03:45,842 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:03:45,842 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:04:23,192 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:04:23,193 - tf_lstm.py - INFO - 训练集损失函数为：[9.0817e-01 3.2013e-01 1.0016e-01 2.7980e-02 7.1900e-03 1.9700e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 16:04:23,192 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:04:23,193 - tf_lstm.py - INFO - 验证集损失函数为：[0.51636 0.16911 0.04957 0.01328 0.00369 0.00147 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087 0.00087
+ 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 16:04:23,193 - tf_lstm.py - INFO - 训练集损失函数为：[9.0438e-01 3.1823e-01 9.9190e-02 2.7320e-02 6.6400e-03 1.4700e-03
+ 3.3000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 16:04:23,193 - tf_lstm.py - INFO - 验证集损失函数为：[5.1324e-01 1.6746e-01 4.8450e-02 1.2330e-02 2.8200e-03 6.2000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 16:04:28,183 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eda8ce1472c691263abcd - insert_trained_model_into_mongo
+2025-05-22 16:04:28,184 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eda8ca57967ec2470f538 - insert_trained_model_into_mongo
+2025-05-22 16:04:28,234 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eda8ca57967ec2470f53a - insert_scaler_model_into_mongo
+2025-05-22 16:04:28,235 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eda8ce1472c691263abcf - insert_scaler_model_into_mongo
+2025-05-22 16:15:20,362 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:15:20,482 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 16:15:23,124 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:15:26,082 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:15:26,083 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:15:26,299 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 16:15:26,299 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 16:15:26,318 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:15:26,318 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:15:26,326 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:15:26,326 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:15:26,353 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:15:26,353 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:15:26,353 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:15:26,353 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:15:26,353 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:15:26,353 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:15:27,303 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:15:27,303 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:15:27,303 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:15:27,303 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:15:40,212 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:15:40,212 - tf_lstm.py - INFO - 训练集损失函数为：[9.0386e-01 3.1856e-01 9.9750e-02 2.7890e-02 7.1800e-03 1.9800e-03
+ 8.3000e-04 6.0000e-04 5.5000e-04 5.5000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 16:15:40,212 - tf_lstm.py - INFO - 训练集损失函数为：[8.9587e-01 3.1399e-01 9.7500e-02 2.6790e-02 6.5000e-03 1.4400e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 16:15:40,212 - tf_lstm.py - INFO - 验证集损失函数为：[0.51364 0.16831 0.04936 0.01325 0.0037  0.00148 0.00101 0.00092 0.0009
+ 0.0009  0.00089 0.00089 0.00088 0.00088 0.00088 0.00088 0.00087 0.00087
+ 0.00087 0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 16:15:40,213 - tf_lstm.py - INFO - 验证集损失函数为：[5.0722e-01 1.6484e-01 4.7540e-02 1.2080e-02 2.7600e-03 6.1000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 16:15:40,256 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682edd2c58422a3c9f4e08aa - insert_trained_model_into_mongo
+2025-05-22 16:15:40,266 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682edd2c1c34fc32963f2881 - insert_trained_model_into_mongo
+2025-05-22 16:15:40,287 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682edd2c58422a3c9f4e08ac - insert_scaler_model_into_mongo
+2025-05-22 16:15:40,289 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682edd2c1c34fc32963f2883 - insert_scaler_model_into_mongo
+2025-05-22 16:15:41,578 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 16:18:18,375 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:18:18,503 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 16:18:21,225 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:18:24,210 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:18:24,216 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:18:24,419 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 16:18:24,420 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 16:18:24,439 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:18:24,440 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:18:24,447 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:18:24,448 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:18:24,475 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:18:24,475 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:18:24,476 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:18:24,476 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:18:24,476 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:18:24,477 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:18:25,429 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:18:25,429 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:18:25,431 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:18:25,431 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:18:38,854 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:18:38,854 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:18:38,854 - tf_lstm.py - INFO - 训练集损失函数为：[8.9569e-01 3.1485e-01 9.8280e-02 2.7410e-02 7.0500e-03 1.9500e-03
+ 8.2000e-04 6.0000e-04 5.6000e-04 5.5000e-04 5.5000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 16:18:38,855 - tf_lstm.py - INFO - 训练集损失函数为：[9.1019e-01 3.2047e-01 9.9880e-02 2.7530e-02 6.7100e-03 1.4800e-03
+ 3.3000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 16:18:38,855 - tf_lstm.py - INFO - 验证集损失函数为：[0.50823 0.16598 0.0485  0.01302 0.00365 0.00147 0.00102 0.00093 0.00091
+ 0.0009  0.0009  0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087
+ 0.00087 0.00087 0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086
+ 0.00086 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085
+ 0.00085 0.00085 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 16:18:38,855 - tf_lstm.py - INFO - 验证集损失函数为：[5.1680e-01 1.6865e-01 4.8800e-02 1.2440e-02 2.8500e-03 6.3000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 16:18:38,892 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eddde166c956a98e4cdb6 - insert_trained_model_into_mongo
+2025-05-22 16:18:38,903 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682eddde9239166b91e13257 - insert_trained_model_into_mongo
+2025-05-22 16:18:38,910 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eddde9239166b91e13259 - insert_scaler_model_into_mongo
+2025-05-22 16:18:38,924 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682eddde166c956a98e4cdb8 - insert_scaler_model_into_mongo
+2025-05-22 16:19:36,327 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:19:36,452 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 16:19:39,140 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:19:42,056 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:19:42,056 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:19:42,261 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 16:19:42,261 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 16:19:42,279 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:19:42,279 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:19:42,287 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:19:42,287 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:19:42,316 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:19:42,316 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:19:42,317 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:19:42,317 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:19:42,317 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:19:42,317 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:19:43,248 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:19:43,249 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:19:43,261 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:19:43,261 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:19:56,132 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:19:56,132 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:19:56,133 - tf_lstm.py - INFO - 训练集损失函数为：[9.0371e-01 3.1890e-01 9.9980e-02 2.7980e-02 7.2000e-03 1.9800e-03
+ 8.2000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 16:19:56,133 - tf_lstm.py - INFO - 验证集损失函数为：[0.51401 0.16865 0.04951 0.01329 0.0037  0.00147 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087 0.00087
+ 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085 0.00085 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 16:19:56,133 - tf_lstm.py - INFO - 验证集损失函数为：[5.1199e-01 1.6678e-01 4.8120e-02 1.2220e-02 2.7800e-03 6.2000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 16:19:56,191 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682ede2c6f86cd09523a290d - insert_trained_model_into_mongo
+2025-05-22 16:19:56,191 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682ede2c82774bd11b16d043 - insert_trained_model_into_mongo
+2025-05-22 16:19:56,209 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682ede2c6f86cd09523a290f - insert_scaler_model_into_mongo
+2025-05-22 16:19:56,223 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682ede2c82774bd11b16d045 - insert_scaler_model_into_mongo
+2025-05-22 16:19:57,513 - task_worker.py - ERROR - Area 1002 failed: 'Datetime' - region_task
+2025-05-22 16:23:41,614 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:23:47,120 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
+2025-05-22 16:24:10,592 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:24:39,240 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:24:39,242 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
+ - _tfmw_add_deprecation_warning
+2025-05-22 16:24:39,724 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
+2025-05-22 16:24:39,726 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
+2025-05-22 16:24:39,745 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:24:39,748 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
+2025-05-22 16:24:39,774 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:24:39,776 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
+2025-05-22 16:24:39,816 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:24:39,816 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:24:39,817 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
+2025-05-22 16:24:39,817 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
+2025-05-22 16:24:39,819 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:24:39,819 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
+2025-05-22 16:24:41,717 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:24:41,717 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:24:41,748 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
+2025-05-22 16:24:41,748 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
+2025-05-22 16:25:18,445 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:25:18,445 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
+2025-05-22 16:25:18,445 - tf_lstm.py - INFO - 训练集损失函数为：[9.0181e-01 3.1616e-01 9.7980e-02 2.6830e-02 6.4900e-03 1.4300e-03
+ 3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
+ 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
+ 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
+2025-05-22 16:25:18,445 - tf_lstm.py - INFO - 训练集损失函数为：[8.9533e-01 3.1324e-01 9.7340e-02 2.7070e-02 6.9500e-03 1.9200e-03
+ 8.1000e-04 5.9000e-04 5.5000e-04 5.4000e-04 5.4000e-04 5.4000e-04
+ 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
+ 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
+ 5.2000e-04 5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
+ 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
+2025-05-22 16:25:18,446 - tf_lstm.py - INFO - 验证集损失函数为：[5.1082e-01 1.6583e-01 4.7670e-02 1.2070e-02 2.7500e-03 6.1000e-04
+ 1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
+ 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
+2025-05-22 16:25:18,446 - tf_lstm.py - INFO - 验证集损失函数为：[0.50668 0.16475 0.04801 0.01285 0.00359 0.00145 0.00101 0.00092 0.0009
+ 0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
+ 0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
+ 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
+ 0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
+ 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
+ 0.00082] - training
+2025-05-22 16:25:18,550 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682edf6e4f4d66c1538080fc - insert_trained_model_into_mongo
+2025-05-22 16:25:18,562 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682edf6e4f4d66c1538080fe - insert_scaler_model_into_mongo
+2025-05-22 16:25:18,564 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682edf6ee396be238e929ca2 - insert_trained_model_into_mongo
+2025-05-22 16:25:18,576 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682edf6ee396be238e929ca4 - insert_scaler_model_into_mongo

app/model/main.py

@@ -8,6 +8,10 @@
 """
 模型调参及系统功能配置
 """
+import concurrent.futures
+import types
+
+from pyexpat import features
 from tqdm import tqdm
 import pandas as pd
 from pathlib import Path
@@ -15,7 +19,10 @@ from copy import deepcopy
 from concurrent.futures import ProcessPoolExecutor
 from app.common.config import parser, logger
 from app.model.resource_manager import ResourceController
-from app.model.task_worker import station_task, region_task
+from app.model.task_worker import Task
+from app.model.material import MaterialLoader
+from multiprocessing import Manager, Lock
+
 """"
 调用思路
    xxxx 1. 从入口参数中获取IN OUT文件位置 xxxx
@@ -47,9 +54,9 @@ def main():
     )
 
     # 生成任务列表
-    all_stations = [str(child) for child in Path(opt.input_file).iterdir() if child.is_dir()]
-    # task_func = partial(station_task, config=config)
-
+    all_stations = [str(child.parts[-1]) for child in Path(opt.input_file).iterdir() if child.is_dir()]
+    loader = MaterialLoader(opt.input_file)
+    task = Task(loader)
     # ---------------------------- 监控任务，进度跟踪 ----------------------------
     # 场站级功率预测训练
     completed = 0
@@ -58,27 +65,48 @@ def main():
             futures = []
             for sid in all_stations:
                 # 动态分配GPU
-                gpu_id = rc.get_gpu()
                 task_config = deepcopy(config)
+                gpu_id = rc.get_gpu()
                 task_config['gpu_assignment'] = gpu_id
                 task_config['station_id'] = sid
                 # 提交任务
-                future = executor.submit(station_task, task_config)
+                future = executor.submit(task.station_task, task_config)
                 future.add_done_callback(
                     lambda _: rc.release_gpu(task_config['gpu_assignment']))
                 futures.append(future)
 
+            total_cap = 0
+            weighted_nwp = pd.DataFrame()
+            weighted_nwp_h = pd.DataFrame()
+            weighted_nwp_v = pd.DataFrame()
+            weighted_nwp_v_h = pd.DataFrame()
+
             # 处理完成情况
-            for future in futures:
+            for future in concurrent.futures.as_completed(futures):
                 result = future._result
                 if result == 'success':
+                    # 分治-汇总策略得到加权后的nwp
                     completed += 1
+                    local = result['weights']
+                    total_cap += local['cap']
+                    weighted_nwp = weighted_nwp.add(local['nwp'], fill_value=0)
+                    weighted_nwp_h = weighted_nwp_h.add(local['nwp_h'], fill_value=0)
+                    weighted_nwp_v = weighted_nwp_v.add(local['nwp_v'], fill_value=0)
+                    weighted_nwp_v_h = weighted_nwp_v_h.add(local['nwp_v_h'], fill_value=0)
                 pbar.update(1)
                 pbar.set_postfix_str(f"Completed: {completed}/{len(all_stations)}")
-
+    # 归一化处理
+    weighted_nwp /= total_cap
+    weighted_nwp_h /= total_cap
+    weighted_nwp_v /= total_cap
+    weighted_nwp_v_h /= total_cap
+    data_nwps = types.SimpleNamespace(**{'nwp': weighted_nwp, 'nwp_h': weighted_nwp_h, 'nwp_v': weighted_nwp_v, 'nwp_v_h': weighted_nwp_v_h})
     print(f"Final result: {completed} stations trained successfully")
     # 区域级功率预测训练
-    region_task(config)
+    task_config = deepcopy(config)
+    gpu_id = rc.get_gpu()
+    task_config['gpu_assignment'] = gpu_id
+    task.region_task(task_config, data_nwps)
 
 if __name__ == "__main__":
     main()

app/model/material.py

@@ -19,11 +19,6 @@ class MaterialLoader:
         self.lazy_load = lazy_load
         self._data_cache = {}
         self.opt = parser.parse_args_and_yaml()
-        self.sum_cap = 0
-        self.weighted_nwp = pd.DataFrame()
-        self.weighted_nwp_h = pd.DataFrame()
-        self.weighted_nwp_v = pd.DataFrame()
-        self.weighted_nwp_v_h = pd.DataFrame()
 
     def wrapper_path(self, station_id, spec):
         return f"{self.base_path/station_id/spec}.txt"
@@ -85,7 +80,6 @@ class MaterialLoader:
         if self.lazy_load:
             if station_id not in self._data_cache:
                 self._data_cache[station_id] = self._load_material(station_id)
-                self.add_weights(self._data_cache[station_id])
             return self._data_cache[station_id]
         else:
             return self._load_material(station_id)
@@ -93,20 +87,11 @@ class MaterialLoader:
     def add_weights(self, data_objects):
         """对nwp数据进行cap加权（nwp, nwp_h, nwp_v_, nwp_v_h）"""
 
-        def sum_df(df_obj, df, weight):
+        def local_sum(df, weight):
             """内部函数：对DataFrame进行加权求和"""
-            columns_to_scale = [col for col in df.columns if col not in ['PlantID', 'PlantName', 'Datetime']]
-
-            if not df_obj.empty:
-                # 验证列名一致性
-                assert set(df_obj.columns) == set(df.columns), "DataFrame列不匹配"
-                # 向量化操作：仅对数值列进行加权累加
-                df_obj[columns_to_scale] += df[columns_to_scale] * weight
-            else:
-                # 初始化操作：复制结构并加权数值列
-                df_obj = df.copy()
-                df_obj[columns_to_scale] = df[columns_to_scale] * weight
-            return df_obj
+            columns_to_scale = [col for col in df.columns if col not in ['PlantID', 'PlantName', 'PlantType', 'Qbsj', 'Datetime']]
+            weighted_df = df[columns_to_scale] * weight
+            return weighted_df, weight
 
         # 从data_objects解构对象
         nwp, nwp_h, nwp_v, nwp_v_h, power, cap = (
@@ -118,32 +103,32 @@ class MaterialLoader:
             data_objects.cap
         )
 
-        # 累加总容量（用于后续归一化）
-        self.sum_cap += cap
-
         # 对每个NWP数据集进行容量加权
-        self.weighted_nwp = sum_df(self.weighted_nwp, nwp, cap)
-        self.weighted_nwp_h = sum_df(self.weighted_nwp_h, nwp_h, cap)
-        self.weighted_nwp_v = sum_df(self.weighted_nwp_v, nwp_v, cap)
-        self.weighted_nwp_v_h = sum_df(self.weighted_nwp_v_h, nwp_v_h, cap)
+        weighted_nwp, cap = local_sum(nwp, cap)
+        weighted_nwp_h, _ = local_sum(nwp_h, cap)
+        weighted_nwp_v, _ = local_sum(nwp_v, cap)
+        weighted_nwp_v_h, _ = local_sum(nwp_v_h, cap)
+
+        return {
+            'nwp': weighted_nwp,
+            'nwp_h': weighted_nwp_h,
+            'nwp_v': weighted_nwp_v,
+            'nwp_v_h': weighted_nwp_v_h,
+            'cap': cap
+        }
 
     def get_material_region(self):
         try:
-            basic = pd.read_csv(os.path.join(self.base_path, self.opt.doc_area_mapping['basic']), sep=r'\s+', header=0)
-            power = pd.read_csv(os.path.join(self.base_path, self.opt.doc_area_mapping['power']), sep=r'\s+', header=0)
+            basic = pd.read_csv(os.path.join(self.base_path, self.opt.doc_area_mapping['basic']+'.txt'), sep=r'\s+', header=0)
+            power = pd.read_csv(os.path.join(self.base_path, self.opt.doc_area_mapping['power']+'.txt'), sep=r'\s+', header=0)
             plant_type = int(basic.loc[basic['PropertyID'].tolist().index('PlantType'), 'Value'])
             area_id = int(basic.loc[basic['PropertyID'].tolist().index('AreaId'), 'Value'])
             assert plant_type == 0 or plant_type == 1
             area_cap = float(basic.loc[basic['PropertyID'].tolist().index('AreaCap'), 'Value'])
-            columns_to_scale = [col for col in self.weighted_nwp.columns if col not in ['PlantID', 'PlantName', 'Datetime']]
-            self.weighted_nwp[columns_to_scale] /= self.sum_cap
             return types.SimpleNamespace(**{
-                'nwp': self.weighted_nwp,
-                'nwp_h': self.weighted_nwp_h,
                 'power': power,
-                'nwp_v': self.weighted_nwp_v,
-                'nwp_v_h': self.weighted_nwp_v_h,
-                'area_cap': area_cap
+                'area_cap': area_cap,
+                'area_id': area_id
             })
         except Exception as e:
             print(f"Region Error loading: {str(e)}")

app/model/task_worker.py

@@ -12,50 +12,58 @@ from app.model.tf_region_train import RegionTrainer
 from app.model.material import MaterialLoader
 
 
-def station_task(config):
-    """场站级训练任务"""
-    try:
-        print("111")
-        station_id = config['station_id']
-        mate = MaterialLoader(base_path=config['input_file'])
-        # 动态生成场站数据路径
-        print("222")
-        # 加载数据
-        data_objects = mate.get_material(station_id)
-        print("333")
-        # 数据合并
-        train_data = pd.merge(data_objects.nwp_v_h, data_objects.power, on=config['col_time'])
-        print("444")
-        # 模型训练
-        # model = ModelTrainer(station_id, train_data, capacity=data_objects.cap, gpu_id=config.get('gpu_assignment'))
-        model = ModelTrainer(train_data, capacity=data_objects.cap, config=config)
-        model.train()
-        print("555")
-        return {'status': 'success', 'station_id': station_id}
-    except Exception as e:
-        logging.error(f"Station {station_id} failed: {str(e)}")
-        return {'status': 'failed', 'station_id': station_id}
+class Task(object):
+    def __init__(self, loader):
+        self.loader = loader
 
+    def station_task(self, config):
+        """场站级训练任务"""
+        station_id = -99
+        try:
+            print("111")
+            station_id = config['station_id']
+            # 动态生成场站数据路径
+            print("222")
+            # 加载数据
+            data_objects = self.loader.get_material(station_id)
+            local_weights = self.loader.add_weights(data_objects)
+            print("333")
+            # 数据合并
+            train_data = pd.merge(data_objects.nwp_v_h, data_objects.power, on=config['col_time'])
+            print("444")
+            # 模型训练
+            # model = ModelTrainer(station_id, train_data, capacity=data_objects.cap, gpu_id=config.get('gpu_assignment'))
+            model = ModelTrainer(train_data, capacity=data_objects.cap, config=config)
+            model.train()
+            print("555")
+            return {'status': 'success', 'station_id': station_id, 'weights': local_weights}
+        except Exception as e:
+            logging.error(f"Station {station_id} failed: {str(e)}")
+            return {'status': 'failed', 'station_id': station_id}
 
-def region_task(config):
-    """区域级训练任务"""
-    try:
-        print("111")
-        station_id = config['station_id']
-        mate = MaterialLoader(base_path=config['input_file'])
-        # 动态生成场站数据路径
-        print("222")
-        # 加载数据
-        data_objects = mate.get_material_region()
-        print("333")
-        # 数据合并
-        train_data = pd.merge(data_objects.nwp_v_h, data_objects.power, on=config['col_time'])
-        print("444")
-        # 模型训练
-        model = ModelTrainer(train_data, capacity=data_objects.cap, config=config)
-        model.train()
-        print("555")
-        return {'status': 'success', 'station_id': station_id}
-    except Exception as e:
-        logging.error(f"Station {station_id} failed: {str(e)}")
-        return {'status': 'failed', 'station_id': station_id}
+
+    def region_task(self, config, data_nwps):
+        """区域级训练任务"""
+        area_id = -99
+        try:
+            print("111")
+            # 动态生成场站数据路径
+            print("222")
+            # 加载数据
+            data_objects = self.loader.get_material_region()
+            config['area_id'] = data_objects.area_id
+            area_id = data_objects.area_id
+            print("333")
+            # 数据合并
+            print(data_nwps.nwp)
+            print(data_nwps.nwp_v)
+            train_data = pd.merge(data_nwps.nwp_v_h, data_objects.power, on=config['col_time'])
+            print("444")
+            # 模型训练
+            model = ModelTrainer(train_data, capacity=data_objects.cap, config=config)
+            model.train()
+            print("555")
+            return {'status': 'success', 'area_id': area_id}
+        except Exception as e:
+            logging.error(f"Area {area_id} failed: {str(e)}")
+            return {'status': 'failed', 'area_id': area_id}

app/model/tf_model_train.py

@@ -22,7 +22,7 @@ class ModelTrainer:
     def __init__(self,
                  train_data: pd.DataFrame,
                  capacity: float,
-                 config: Dict[str, Any] = None
+                 config: Dict[str, Any] = None,
                  ):
         self.config = config
         self.logger = logger
@@ -45,13 +45,15 @@ class ModelTrainer:
             self.logger.info(f"GPU {self.gpu_id} allocated")
 
 
-    def train(self):
+    def train(self, pre_area=False):
         """执行训练流程"""
         # 获取程序开始时间
         start_time = time.time()
         success = 0
         print("aaa")
-        farm_id = self.input_file.split('/')[-2]
+        # 预测编号：场站级，场站id，区域级，区域id
+        pre_id = self.config['area_id'] if pre_area else self.config['station_id']
+        pre_type = 'a' if pre_area else 's'
         output_file = self.input_file.replace('IN', 'OUT')
         status_file = 'STATUS.TXT'
         try:
@@ -87,10 +89,10 @@ class ModelTrainer:
             self.opt.Model['features'] = ','.join(self.dh.opt.features)
             self.config.update({
                 'params': json.dumps(self.config['Model']),
-                'descr': f'南网竞赛-{farm_id}',
+                'descr': f'南网竞赛-{pre_id}',
                 'gen_time': time.strftime('%Y-%m-%d %H:%M:%S', time.localtime()),
-                'model_table': self.config['model_table'] + farm_id,
-                'scaler_table': self.config['scaler_table'] + farm_id
+                'model_table': self.config['model_table'] + f'_{pre_type}_' + pre_id,
+                'scaler_table': self.config['scaler_table'] + f'_{pre_type}_'+ pre_id
             })
             self.mgUtils.insert_trained_model_into_mongo(trained_model, self.config)
             self.mgUtils.insert_scaler_model_into_mongo(scaled_train_bytes, scaled_target_bytes, self.config)