2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								# Windows端基础训练预测功能测试
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								Windows端基础训练预测功能测试的主程序为`test_train_inference_python.sh` , , 
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								## 1. 测试结论汇总
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  训练相关: 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								| 算法名称 | 模型名称 | 单机单卡 | 单机多卡 | 多机多卡 | 模型压缩(单机多卡) |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								|  :----  |   :----  |    :----  |  :----   |  :----   |  :----   |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								|  DB  | ch_ppocr_mobile_v2.0_det| 正常训练 < br >  混合精度 | - | - | 正常训练: < br >  离线量化(无需训练) |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  预测相关:基于训练是否使用量化,可以将训练产出的模型可以分为`正常模型` 和`量化模型` ,这两类模型对应的预测功能汇总如下: 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								| 模型类型 |device | batchsize | tensorrt | mkldnn | cpu多线程 |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								|  ----   |  ---- |   ----   |  :----:  |   :----:   |  :----:  |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								| 正常模型 | GPU | 1/6 | fp32/fp16 | - | - |
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:16:13 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								| 正常模型 | CPU | 1/6 | - | fp32/fp16 | 支持 |
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								| 量化模型 | GPU | 1/6 | int8 | - | - |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								| 量化模型 | CPU | 1/6 | - | int8 | 支持 |
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								## 2. 测试流程
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
									
										
										
										
											2021-11-08 09:06:34 +00:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								运行环境配置请参考[文档 ](./install.md )的内容配置TIPC的运行环境。
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								另外, , , , 下载链接 ](https://git-scm.com/download/win )。
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								### 2.1 安装依赖
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  安装PaddlePaddle >= 2.0 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  安装PaddleOCR依赖 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    ```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    pip install  -r ../requirements.txt
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    ```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  安装autolog( )  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    ```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    git clone https://github.com/LDOUBLEV/AutoLog
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    cd AutoLog
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    pip  install -r requirements.txt
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    python setup.py bdist_wheel
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    pip  install ./dist/auto_log-1.0.0-py3-none-any.whl
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    cd ../
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    ```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  安装PaddleSlim (可选) 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								   ```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								   # 如果要测试量化、裁剪等功能, 
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								   pip install paddleslim
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								   ```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								### 2.2 功能测试
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								先运行`prepare.sh` 准备数据和模型,然后运行`test_train_inference_python.sh` 进行测试,最终在```test_tipc/output` ``目录下生成` python_infer_*.log`格式的日志文件。
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								`test_train_inference_python.sh` 包含5种运行模式, , , :  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  模式1: , , , ;  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```shell
							 
						 
					
						
							
								
									
										
										
										
											2021-11-18 19:23:02 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'lite_train_lite_infer'
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'lite_train_lite_infer'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  模式2: , , , , ;  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```shell
							 
						 
					
						
							
								
									
										
										
										
											2021-11-18 19:23:02 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'lite_train_whole_infer'
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'lite_train_whole_infer'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  模式3: , , , ,  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```shell
							 
						 
					
						
							
								
									
										
										
										
											2021-11-18 19:23:02 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'whole_infer'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								# 用法1:
  
						 
					
						
							
								
									
										
										
										
											2021-11-18 19:23:02 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'whole_infer'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								# 用法2: 指定GPU卡预测,   
						 
					
						
							
								
									
										
										
										
											2021-11-18 19:23:02 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'whole_infer' '1'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  模式4: , :  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```shell
							 
						 
					
						
							
								
									
										
										
										
											2021-11-18 19:23:02 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'whole_train_whole_infer'
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt  'whole_train_whole_infer'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  模式5: , ;  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```shell
							 
						 
					
						
							
								
									
										
										
										
											2021-11-19 11:13:50 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_windows_gpu_cpu.txt  'klquant_whole_infer'
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_windows_gpu_cpu.txt  'klquant_whole_infer'
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								运行相应指令后,在`test_tipc/output` 文件夹下自动会保存运行日志。如'lite_train_lite_infer'模式下,会运行训练+inference的链条, , `test_tipc/output` 文件夹有以下文件:
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								test_tipc/output/
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								|- results_python.log    # 运行指令状态的日志
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								|- norm_train_gpus_0_autocast_null/  # GPU 0号卡上正常训练的训练日志和模型保存文件夹
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								|- pact_train_gpus_0_autocast_null/  # GPU 0号卡上量化训练的训练日志和模型保存文件夹
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								......
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								|- python_infer_cpu_usemkldnn_True_threads_1_batchsize_1.log  # CPU上开启Mkldnn线程数设置为1, 
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								|- python_infer_gpu_usetrt_True_precision_fp16_batchsize_1.log # GPU上开启TensorRT, 
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								......
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								其中`results_python.log` 中包含了每条指令的运行状态,如果运行成功会输出:
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								Run successfully with command - python3.7 tools/train.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained Global.use_gpu=True  Global.save_model_dir=./tests/output/norm_train_gpus_0_autocast_null Global.epoch_num=1     Train.loader.batch_size_per_card=2   !
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								Run successfully with command - python3.7 tools/export_model.py -c tests/configs/det_mv3_db.yml -o  Global.pretrained_model=./tests/output/norm_train_gpus_0_autocast_null/latest Global.save_inference_dir=./tests/output/norm_train_gpus_0_autocast_null!
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								......
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								如果运行失败,会输出:
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								Run failed with command - python3.7 tools/train.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained Global.use_gpu=True  Global.save_model_dir=./tests/output/norm_train_gpus_0_autocast_null Global.epoch_num=1     Train.loader.batch_size_per_card=2   !
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								Run failed with command - python3.7 tools/export_model.py -c tests/configs/det_mv3_db.yml -o  Global.pretrained_model=./tests/output/norm_train_gpus_0_autocast_null/latest Global.save_inference_dir=./tests/output/norm_train_gpus_0_autocast_null!
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								......
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								可以很方便的根据`results_python.log` 中的内容判定哪一个指令运行错误。
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								### 2.3 精度测试
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								使用compare_results.py脚本比较模型预测的结果是否符合预期, : 
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  提取日志中的预测坐标; 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  从本地文件中提取保存好的坐标结果; 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  比较上述两个结果是否符合精度预期,误差大于设置阈值时会报错。 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								#### 使用方式
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								运行命令:
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```shell
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								python test_tipc/compare_results.py --gt_file=./test_tipc/results/python_*.txt  --log_file=./test_tipc/output/python_*.log --atol=1e-3 --rtol=1e-3
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								参数介绍:  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  gt_file: ,  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
										 
							
							
								-  log_file: 指向运行test_tipc/test_train_inference_python.sh 脚本的infer模式保存的预测日志, , : , , ,  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  atol: 设置的绝对误差 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								-  rtol: 设置的相对误差 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								#### 运行结果
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
									
										
										
										
											2021-11-12 17:58:07 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								正常运行效果如下:
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								Assert allclose passed! The results of python_infer_cpu_usemkldnn_False_threads_1_batchsize_1.log and ./test_tipc/results/python_ppocr_det_mobile_results_fp32.txt are consistent!
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								出现不一致结果时的运行输出:
							 
						 
					
						
							
								
									
										
										
										
											2021-11-12 17:58:07 +08:00 
										
									 
								 
							 
							
								
									
										 
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								......
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								Traceback (most recent call last):
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								  File "test_tipc/compare_results.py", line 140, in < module > 
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								    format(filename, gt_filename))
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								ValueError: The results of python_infer_cpu_usemkldnn_False_threads_1_batchsize_1.log and the results of ./test_tipc/results/python_ppocr_det_mobile_results_fp32.txt are inconsistent!
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								```
							 
						 
					
						
							
								
									
										
										
										
											2021-11-01 20:01:55 +08:00 
										
									 
								 
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								## 3. 更多教程
  
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								本文档为功能测试用,更丰富的训练预测使用教程请参考:  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								[模型训练 ](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/training.md )  
							 
						 
					
						
							
								
							 
							
								
							 
							
								 
							
								
									
								 
							
							
								[基于Python预测引擎推理 ](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference.md )