diff --git a/PTDN/configs/ppocr_det_mobile_params.txt b/PTDN/configs/ppocr_det_mobile_params.txt index 63a78fb39f05552651fe02832e6e2622f5cba155..3d2117d7ca9b444f55b9c9f343647026af7e97c6 100644 --- a/PTDN/configs/ppocr_det_mobile_params.txt +++ b/PTDN/configs/ppocr_det_mobile_params.txt @@ -1,9 +1,9 @@ ===========================train_params=========================== model_name:ocr_det python:python3.7 -gpu_list:0|0,1 -Global.use_gpu:True|True -Global.auto_cast:null +gpu_list:0|0,1|10.21.226.181,10.21.226.133;0,1 +Global.use_gpu:True|True|True +Global.auto_cast:fp32|amp Global.epoch_num:lite_train_infer=1|whole_train_infer=300 Global.save_model_dir:./output/ Train.loader.batch_size_per_card:lite_train_infer=2|whole_train_infer=4 diff --git a/PTDN/docs/test_inference_cpp.md b/PTDN/docs/test_inference_cpp.md index 140860cb506513cbaa0fdc621848568d90e8ef5c..25db1b5b6b1aa101a8f8969cfae3efc02e542971 100644 --- a/PTDN/docs/test_inference_cpp.md +++ b/PTDN/docs/test_inference_cpp.md @@ -6,7 +6,7 @@ C++预测功能测试的主程序为`test_inference_cpp.sh`，可以测试基于 基于训练是否使用量化，进行本测试的模型可以分为`正常模型`和`量化模型`，这两类模型对应的C++预测功能汇总如下： -| 模型类型 |device | batchsize | tensorrt | mkldnn | cpu多线程 | +| 模型类型 |device | batchsize | tensorrt | mkldnn | cpu多线程 | | ---- | ---- | ---- | :----: | :----: | :----: | | 正常模型 | GPU | 1/6 | fp32/fp16 | - | - | | 正常模型 | CPU | 1/6 | - | fp32 | 支持 | @@ -15,17 +15,17 @@ C++预测功能测试的主程序为`test_inference_cpp.sh`，可以测试基于 ## 2. 测试流程 ### 2.1 功能测试 -先运行`prepare.sh`准备数据和模型，然后运行`test_inference_cpp.sh`进行测试，最终在```tests/output```目录下生成`cpp_infer_*.log`后缀的日志文件。 +先运行`prepare.sh`准备数据和模型，然后运行`test_inference_cpp.sh`进行测试，最终在```PTDN/output```目录下生成`cpp_infer_*.log`后缀的日志文件。 ```shell -bash tests/prepare.sh ./tests/configs/ppocr_det_mobile_params.txt "cpp_infer" +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt "cpp_infer" # 用法1: -bash tests/test_inference_cpp.sh ./tests/configs/ppocr_det_mobile_params.txt +bash PTDN/test_inference_cpp.sh ./PTDN/configs/ppocr_det_mobile_params.txt # 用法2: 指定GPU卡预测，第三个传入参数为GPU卡号 -bash tests/test_inference_cpp.sh ./tests/configs/ppocr_det_mobile_params.txt '1' +bash PTDN/test_inference_cpp.sh ./PTDN/configs/ppocr_det_mobile_params.txt '1' ``` - + ### 2.2 精度测试 @@ -37,12 +37,12 @@ bash tests/test_inference_cpp.sh ./tests/configs/ppocr_det_mobile_params.txt '1' #### 使用方式 运行命令： ```shell -python3.7 tests/compare_results.py --gt_file=./tests/results/cpp_*.txt --log_file=./tests/output/cpp_*.log --atol=1e-3 --rtol=1e-3 +python3.7 PTDN/compare_results.py --gt_file=./PTDN/results/cpp_*.txt --log_file=./PTDN/output/cpp_*.log --atol=1e-3 --rtol=1e-3 ``` 参数介绍： -- gt_file： 指向事先保存好的预测结果路径，支持*.txt 结尾，会自动索引*.txt格式的文件，文件默认保存在tests/result/ 文件夹下 -- log_file: 指向运行tests/test.sh 脚本的infer模式保存的预测日志，预测日志中打印的有预测结果，比如：文本框，预测文本，类别等等，同样支持infer_*.log格式传入 +- gt_file： 指向事先保存好的预测结果路径，支持*.txt 结尾，会自动索引*.txt格式的文件，文件默认保存在PTDN/result/ 文件夹下 +- log_file: 指向运行PTDN/test_inference_cpp.sh 脚本的infer模式保存的预测日志，预测日志中打印的有预测结果，比如：文本框，预测文本，类别等等，同样支持cpp_infer_*.log格式传入 - atol: 设置的绝对误差 - rtol: 设置的相对误差 diff --git a/PTDN/docs/test_serving.md b/PTDN/docs/test_serving.md new file mode 100644 index 0000000000000000000000000000000000000000..c6b35630392249ea969585c69a9e4c3d35f1cf52 --- /dev/null +++ b/PTDN/docs/test_serving.md @@ -0,0 +1,78 @@ +# PaddleServing预测功能测试 + +PaddleServing预测功能测试的主程序为`test_serving.sh`，可以测试基于PaddleServing的部署功能。 + +## 1. 测试结论汇总 + +基于训练是否使用量化，进行本测试的模型可以分为`正常模型`和`量化模型`，这两类模型对应的C++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 | - | - | +| 正常模型 | CPU | 1/6 | - | fp32 | 支持 | +| 量化模型 | GPU | 1/6 | int8 | - | - | +| 量化模型 | CPU | 1/6 | - | int8 | 支持 | + +## 2. 测试流程 +### 2.1 功能测试 +先运行`prepare.sh`准备数据和模型，然后运行`test_serving.sh`进行测试，最终在```PTDN/output```目录下生成`serving_infer_*.log`后缀的日志文件。 + +```shell +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt "serving_infer" + +# 用法: +bash PTND/test_serving.sh ./PTDN/configs/ppocr_det_mobile_params.txt +``` + +#### 运行结果 + +各测试的运行情况会打印在 `PTDN/output/results_serving.log` 中： +运行成功时会输出： + +``` +Run successfully with command - python3.7 pipeline_http_client.py --image_dir=../../doc/imgs > ../../tests/output/server_infer_cpu_usemkldnn_True_threads_1_batchsize_1.log 2>&1 ! +Run successfully with command - xxxxx +... +``` + +运行失败时会输出： + +``` +Run failed with command - python3.7 pipeline_http_client.py --image_dir=../../doc/imgs > ../../tests/output/server_infer_cpu_usemkldnn_True_threads_1_batchsize_1.log 2>&1 ! +Run failed with command - python3.7 pipeline_http_client.py --image_dir=../../doc/imgs > ../../tests/output/server_infer_cpu_usemkldnn_True_threads_6_batchsize_1.log 2>&1 ! +Run failed with command - xxxxx +... +``` + +详细的预测结果会存在 PTDN/output/ 文件夹下，例如`server_infer_gpu_usetrt_True_precision_fp16_batchsize_1.log`中会返回检测框的坐标: + +``` +{'err_no': 0, 'err_msg': '', 'key': ['dt_boxes'], 'value': ['[[[ 78. 642.]\n [409. 640.]\n [409. 657.]\n +[ 78. 659.]]\n\n [[ 75. 614.]\n [211. 614.]\n [211. 635.]\n [ 75. 635.]]\n\n +[[103. 554.]\n [135. 554.]\n [135. 575.]\n [103. 575.]]\n\n [[ 75. 531.]\n +[347. 531.]\n [347. 549.]\n [ 75. 549.] ]\n\n [[ 76. 503.]\n [309. 498.]\n +[309. 521.]\n [ 76. 526.]]\n\n [[163. 462.]\n [317. 462.]\n [317. 493.]\n +[163. 493.]]\n\n [[324. 431.]\n [414. 431.]\n [414. 452.]\n [324. 452.]]\n\n +[[ 76. 412.]\n [208. 408.]\n [209. 424.]\n [ 76. 428.]]\n\n [[307. 409.]\n +[428. 409.]\n [428. 426.]\n [307 . 426.]]\n\n [[ 74. 385.]\n [217. 382.]\n +[217. 400.]\n [ 74. 403.]]\n\n [[308. 381.]\n [427. 380.]\n [427. 400.]\n +[308. 401.]]\n\n [[ 74. 363.]\n [195. 362.]\n [195. 378.]\n [ 74. 379.]]\n\n +[[303. 359.]\n [423. 357.]\n [423. 375.]\n [303. 377.]]\n\n [[ 70. 336.]\n +[239. 334.]\n [239. 354.]\ n [ 70. 356.]]\n\n [[ 70. 312.]\n [204. 310.]\n +[204. 327.]\n [ 70. 330.]]\n\n [[303. 308.]\n [419. 306.]\n [419. 326.]\n +[303. 328.]]\n\n [[113. 2 72.]\n [246. 270.]\n [247. 299.]\n [113. 301.]]\n\n + [[361. 269.]\n [384. 269.]\n [384. 296.]\n [361. 296.]]\n\n [[ 70. 250.]\n + [243. 246.]\n [243. 265.]\n [ 70. 269.]]\n\n [[ 65. 221.]\n [187. 220.]\n +[187. 240.]\n [ 65. 241.]]\n\n [[337. 216.]\n [382. 216.]\n [382. 240.]\n +[337. 240.]]\n\n [ [ 65. 196.]\n [247. 193.]\n [247. 213.]\n [ 65. 216.]]\n\n +[[296. 197.]\n [423. 191.]\n [424. 209.]\n [296. 215.]]\n\n [[ 65. 167.]\n [244. 167.]\n +[244. 186.]\n [ 65. 186.]]\n\n [[ 67. 139.]\n [290. 139.]\n [290. 159.]\n [ 67. 159.]]\n\n +[[ 68. 113.]\n [410. 113.]\n [410. 128.]\n [ 68. 129.] ]\n\n [[277. 87.]\n [416. 87.]\n +[416. 108.]\n [277. 108.]]\n\n [[ 79. 28.]\n [132. 28.]\n [132. 62.]\n [ 79. 62.]]\n\n +[[163. 17.]\n [410. 14.]\n [410. 50.]\n [163. 53.]]]']} +``` + + +## 3. 更多教程 + +本文档为功能测试用，更详细的Serving预测使用教程请参考：[PPOCR 服务化部署](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/deploy/pdserving/README_CN.md) diff --git a/PTDN/docs/test_train_inference_python.md b/PTDN/docs/test_train_inference_python.md index 8c468ffd34fcd7d949331c9097c7993ca7a1e391..89885ddfa3c1f36a120d713e39689767f8fc6342 100644 --- a/PTDN/docs/test_train_inference_python.md +++ b/PTDN/docs/test_train_inference_python.md @@ -19,7 +19,7 @@ - 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 | +| 模型类型 |device | batchsize | tensorrt | mkldnn | cpu多线程 | | ---- | ---- | ---- | :----: | :----: | :----: | | 正常模型 | GPU | 1/6 | fp32/fp16 | - | - | | 正常模型 | CPU | 1/6 | - | fp32 | 支持 | @@ -46,42 +46,42 @@ ### 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```tests/output```目录下生成`python_infer_*.log`格式的日志文件。 +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```PTDN/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，每种模式的运行数据不同，分别用于测试速度和精度，分别是： - 模式1：lite_train_infer，使用少量数据训练，用于快速验证训练到预测的走通流程，不验证精度和速度； ```shell -bash tests/prepare.sh ./tests/configs/ppocr_det_mobile_params.txt 'lite_train_infer' -bash tests/test_train_inference_python.sh ./tests/configs/ppocr_det_mobile_params.txt 'lite_train_infer' +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'lite_train_infer' +bash PTDN/test_train_inference_python.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'lite_train_infer' ``` - 模式2：whole_infer，使用少量数据训练，一定量数据预测，用于验证训练后的模型执行预测，预测速度是否合理； ```shell -bash tests/prepare.sh ./tests/configs/ppocr_det_mobile_params.txt 'whole_infer' -bash tests/test_train_inference_python.sh ./tests/configs/ppocr_det_mobile_params.txt 'whole_infer' +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'whole_infer' +bash PTDN/test_train_inference_python.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'whole_infer' ``` - 模式3：infer，不训练，全量数据预测，走通开源模型评估、动转静，检查inference model预测时间和精度; ```shell -bash tests/prepare.sh ./tests/configs/ppocr_det_mobile_params.txt 'infer' +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'infer' # 用法1: -bash tests/test_train_inference_python.sh ./tests/configs/ppocr_det_mobile_params.txt 'infer' +bash PTDN/test_train_inference_python.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'infer' # 用法2: 指定GPU卡预测，第三个传入参数为GPU卡号 -bash tests/test_train_inference_python.sh ./tests/configs/ppocr_det_mobile_params.txt 'infer' '1' +bash PTDN/test_train_inference_python.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'infer' '1' ``` - 模式4：whole_train_infer，CE： 全量数据训练，全量数据预测，验证模型训练精度，预测精度，预测速度； ```shell -bash tests/prepare.sh ./tests/configs/ppocr_det_mobile_params.txt 'whole_train_infer' -bash tests/test_train_inference_python.sh ./tests/configs/ppocr_det_mobile_params.txt 'whole_train_infer' +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'whole_train_infer' +bash PTDN/test_train_inference_python.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'whole_train_infer' ``` - 模式5：klquant_infer，测试离线量化； ```shell -bash tests/prepare.sh ./tests/configs/ppocr_det_mobile_params.txt 'klquant_infer' -bash tests/test_train_inference_python.sh tests/configs/ppocr_det_mobile_params.txt 'klquant_infer' +bash PTDN/prepare.sh ./PTDN/configs/ppocr_det_mobile_params.txt 'klquant_infer' +bash PTDN/test_train_inference_python.sh PTDN/configs/ppocr_det_mobile_params.txt 'klquant_infer' ``` @@ -95,12 +95,12 @@ bash tests/test_train_inference_python.sh tests/configs/ppocr_det_mobile_params. #### 使用方式 运行命令： ```shell -python3.7 tests/compare_results.py --gt_file=./tests/results/python_*.txt --log_file=./tests/output/python_*.log --atol=1e-3 --rtol=1e-3 +python3.7 PTDN/compare_results.py --gt_file=./PTDN/results/python_*.txt --log_file=./PTDN/output/python_*.log --atol=1e-3 --rtol=1e-3 ``` 参数介绍： -- gt_file： 指向事先保存好的预测结果路径，支持*.txt 结尾，会自动索引*.txt格式的文件，文件默认保存在tests/result/ 文件夹下 -- log_file: 指向运行tests/test.sh 脚本的infer模式保存的预测日志，预测日志中打印的有预测结果，比如：文本框，预测文本，类别等等，同样支持infer_*.log格式传入 +- gt_file： 指向事先保存好的预测结果路径，支持*.txt 结尾，会自动索引*.txt格式的文件，文件默认保存在PTDN/result/ 文件夹下 +- log_file: 指向运行PTDN/test_train_inference_python.sh 脚本的infer模式保存的预测日志，预测日志中打印的有预测结果，比如：文本框，预测文本，类别等等，同样支持python_infer_*.log格式传入 - atol: 设置的绝对误差 - rtol: 设置的相对误差 diff --git a/PTDN/readme.md b/PTDN/readme.md index 69977fac00482b11e862a7ee83bf9359ac48ffb8..71e888a2fe05a0a6d700b40250dd80d5f6d041e0 100644 --- a/PTDN/readme.md +++ b/PTDN/readme.md @@ -15,20 +15,23 @@ **字段说明：** - 基础训练预测：包括模型训练、Paddle Inference Python预测。 -- 其他：包括Paddle Inference C++预测、Paddle Serving部署、Paddle-Lite部署等。 +- 更多训练方式：包括多机多卡、混合精度。 +- 模型压缩：包括裁剪、离线/在线量化、蒸馏。 +- 其他预测部署：包括Paddle Inference C++预测、Paddle Serving部署、Paddle-Lite部署等。 +更详细的mkldnn、Tensorrt等预测加速相关功能的支持情况可以查看各测试工具的[更多教程](#more)。 -| 算法论文 | 模型名称 | 模型类型 | 基础训练预测 | 其他 | -| :--- | :--- | :----: | :--------: | :---- | -| DB |ch_ppocr_mobile_v2.0_det | 检测 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | -| DB |ch_ppocr_server_v2.0_det | 检测 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +| 算法论文 | 模型名称 | 模型类型 | 基础
训练预测 | 更多
训练方式 | 模型压缩 | 其他预测部署 | +| :--- | :--- | :----: | :--------: | :---- | :---- | :---- | +| DB |ch_ppocr_mobile_v2.0_det | 检测 | 支持 | 多机多卡
混合精度 | FPGM裁剪
离线量化| Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +| DB |ch_ppocr_server_v2.0_det | 检测 | 支持 | 多机多卡
混合精度 | FPGM裁剪
离线量化| Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | | DB |ch_PP-OCRv2_det | 检测 | -| CRNN |ch_ppocr_mobile_v2.0_rec | 识别 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | -| CRNN |ch_ppocr_server_v2.0_rec | 识别 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +| CRNN |ch_ppocr_mobile_v2.0_rec | 识别 | 支持 | 多机多卡
混合精度 | PACT量化
离线量化| Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +| CRNN |ch_ppocr_server_v2.0_rec | 识别 | 支持 | 多机多卡
混合精度 | PACT量化
离线量化| Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | | CRNN |ch_PP-OCRv2_rec | 识别 | -| PP-OCR |ch_ppocr_mobile_v2.0 | 检测+识别 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | -| PP-OCR |ch_ppocr_server_v2.0 | 检测+识别 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | -|PP-OCRv2|ch_PP-OCRv2 | 检测+识别 | 支持 | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +| PP-OCR |ch_ppocr_mobile_v2.0 | 检测+识别 | 支持 | 多机多卡
混合精度 | - | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +| PP-OCR |ch_ppocr_server_v2.0 | 检测+识别 | 支持 | 多机多卡
混合精度 | - | Paddle Inference: C++
Paddle Serving: Python, C++
Paddle-Lite:
(1) ARM CPU(C++) | +|PP-OCRv2|ch_PP-OCRv2 | 检测+识别 | | DB |det_mv3_db_v2.0 | 检测 | | DB |det_r50_vd_db_v2.0 | 检测 | | EAST |det_mv3_east_v2.0 | 检测 | @@ -98,6 +101,8 @@ PTDN/ - `test_serving.sh`：测试基于Paddle Serving的服务化部署功能。 - `test_lite.sh`：测试基于Paddle-Lite的端侧预测部署功能。 + +#### 更多教程 各功能测试中涉及混合精度、裁剪、量化等训练相关，及mkldnn、Tensorrt等多种预测相关参数配置，请点击下方相应链接了解更多细节和使用教程： [test_train_inference_python 使用](docs/test_train_inference_python.md) [test_inference_cpp 使用](docs/test_inference_cpp.md) diff --git a/PTDN/test_serving.sh b/PTDN/test_serving.sh index ec79a46c9bf4b51c16b1c0ddfff41b772b13b0ae..af66d70d7b0a255c33d1114a3951adb92407b8d1 100644 --- a/PTDN/test_serving.sh +++ b/PTDN/test_serving.sh @@ -1,5 +1,5 @@ #!/bin/bash -source tests/common_func.sh +source PTDN/common_func.sh FILENAME=$1 dataline=$(awk 'NR==67, NR==83{print}' $FILENAME) @@ -36,8 +36,8 @@ web_precision_key=$(func_parser_key "${lines[15]}") web_precision_list=$(func_parser_value "${lines[15]}") pipeline_py=$(func_parser_value "${lines[16]}") -LOG_PATH="../../tests/output" -mkdir -p ./tests/output +LOG_PATH="../../PTDN/output" +mkdir -p ./PTDN/output status_log="${LOG_PATH}/results_serving.log" function func_serving(){ diff --git a/PTDN/test_train_inference_python.sh b/PTDN/test_train_inference_python.sh index 28cc037801bb4c1f1bcc10a74855b8c146197f4d..756e1f89d74c1df8de50cf8e23fd3d9c95bd20c5 100644 --- a/PTDN/test_train_inference_python.sh +++ b/PTDN/test_train_inference_python.sh @@ -245,6 +245,7 @@ else for gpu in ${gpu_list[*]}; do use_gpu=${USE_GPU_KEY[Count]} Count=$(($Count + 1)) + ips="" if [ ${gpu} = "-1" ];then env="" elif [ ${#gpu} -le 1 ];then @@ -264,6 +265,11 @@ else env=" " fi for autocast in ${autocast_list[*]}; do + if [ ${autocast} = "amp" ]; then + set_amp_config="Global.use_amp=True Global.scale_loss=1024.0 Global.use_dynamic_loss_scaling=True" + else + set_amp_config=" " + fi for trainer in ${trainer_list[*]}; do flag_quant=False if [ ${trainer} = ${pact_key} ]; then @@ -290,7 +296,6 @@ else if [ ${run_train} = "null" ]; then continue fi - set_autocast=$(func_set_params "${autocast_key}" "${autocast}") set_epoch=$(func_set_params "${epoch_key}" "${epoch_num}") set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}") @@ -306,11 +311,11 @@ else set_save_model=$(func_set_params "${save_model_key}" "${save_log}") if [ ${#gpu} -le 2 ];then # train with cpu or single gpu - cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} " - elif [ ${#gpu} -le 15 ];then # train with multi-gpu - cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1}" + cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} " + elif [ ${#ips} -le 26 ];then # train with multi-gpu + cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}" else # train with multi-machine - cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1}" + cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${set_use_gpu} ${run_train} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}" fi # run train eval "unset CUDA_VISIBLE_DEVICES" diff --git a/configs/rec/rec_mtb_nrtr.yml b/configs/rec/rec_mtb_nrtr.yml index 392afc98d52194fdd144ccee626dbda4ddc547e5..04267500854310dc6d5df9318bb8c056c65cd5b5 100644 --- a/configs/rec/rec_mtb_nrtr.yml +++ b/configs/rec/rec_mtb_nrtr.yml @@ -17,7 +17,7 @@ Global: character_dict_path: ppocr/utils/EN_symbol_dict.txt max_text_length: 25 infer_mode: False - use_space_char: True + use_space_char: False save_res_path: ./output/rec/predicts_nrtr.txt Optimizer: diff --git a/doc/doc_ch/enhanced_ctc_loss.md b/doc/doc_ch/enhanced_ctc_loss.md index 5525c7785f0a8fc642cebc82674400c2487558f9..8c0856a7a7bceedbcc0a48bb1af6658afa720886 100644 --- a/doc/doc_ch/enhanced_ctc_loss.md +++ b/doc/doc_ch/enhanced_ctc_loss.md @@ -64,7 +64,7 @@ C-CTC Loss是CTC Loss + Center Loss的简称。 其中Center Loss出自论文 < 以配置文件`configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml`为例， center提取命令如下所示: ``` -python tools/export_center.py -c configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml -o Global.pretrained_model: "./output/rec_mobile_pp-OCRv2/best_accuracy" +python tools/export_center.py -c configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml -o Global.pretrained_model="./output/rec_mobile_pp-OCRv2/best_accuracy" ``` 运行完后，会在PaddleOCR主目录下生成`train_center.pkl`. diff --git a/doc/joinus.PNG b/doc/joinus.PNG index 974a4bd008d7b103de044cf8b4dbf37f09a0d06b..202ad0a5c6edf2190b71d5a7a544f1df94f866c4 100644 Binary files a/doc/joinus.PNG and b/doc/joinus.PNG differ diff --git a/ppocr/postprocess/__init__.py b/ppocr/postprocess/__init__.py index 3a4ebf52a3bd91ffd509b113103dab900588b0bd..5ca4e6bb96fc6f37ef67a2fb0b8c2496e1a83d77 100644 --- a/ppocr/postprocess/__init__.py +++ b/ppocr/postprocess/__init__.py @@ -29,10 +29,7 @@ from .rec_postprocess import CTCLabelDecode, AttnLabelDecode, SRNLabelDecode, Di TableLabelDecode, NRTRLabelDecode, SARLabelDecode , SEEDLabelDecode from .cls_postprocess import ClsPostProcess from .pg_postprocess import PGPostProcess - -if platform.system() != "Windows": - # pse is not support in Windows - from .pse_postprocess import PSEPostProcess +from .pse_postprocess import PSEPostProcess def build_post_process(config, global_config=None): diff --git a/ppocr/postprocess/pse_postprocess/pse/__init__.py b/ppocr/postprocess/pse_postprocess/pse/__init__.py index 97b8d8aff0cf229a4e3ec1961638273bd201822a..0536a32ea5614a8f1826ac2550b1f12518ac53e5 100644 --- a/ppocr/postprocess/pse_postprocess/pse/__init__.py +++ b/ppocr/postprocess/pse_postprocess/pse/__init__.py @@ -17,7 +17,12 @@ import subprocess python_path = sys.executable -if subprocess.call('cd ppocr/postprocess/pse_postprocess/pse;{} setup.py build_ext --inplace;cd -'.format(python_path), shell=True) != 0: - raise RuntimeError('Cannot compile pse: {}'.format(os.path.dirname(os.path.realpath(__file__)))) +ori_path = os.getcwd() +os.chdir('ppocr/postprocess/pse_postprocess/pse') +if subprocess.call( + '{} setup.py build_ext --inplace'.format(python_path), shell=True) != 0: + raise RuntimeError('Cannot compile pse: {}'.format( + os.path.dirname(os.path.realpath(__file__)))) +os.chdir(ori_path) -from .pse import pse \ No newline at end of file +from .pse import pse diff --git a/tools/program.py b/tools/program.py index 798e6dff297ad1149942488cca1d5540f1924867..f94ad83c532183f5a6ff458cfd8c0bfa814d5784 100755 --- a/tools/program.py +++ b/tools/program.py @@ -159,7 +159,8 @@ def train(config, eval_class, pre_best_model_dict, logger, - vdl_writer=None): + vdl_writer=None, + scaler=None): cal_metric_during_train = config['Global'].get('cal_metric_during_train', False) log_smooth_window = config['Global']['log_smooth_window'] @@ -226,14 +227,29 @@ def train(config, images = batch[0] if use_srn: model_average = True - if model_type == 'table' or extra_input: - preds = model(images, data=batch[1:]) + + # use amp + if scaler: + with paddle.amp.auto_cast(): + if model_type == 'table' or extra_input: + preds = model(images, data=batch[1:]) + else: + preds = model(images) else: - preds = model(images) + if model_type == 'table' or extra_input: + preds = model(images, data=batch[1:]) + else: + preds = model(images) loss = loss_class(preds, batch) avg_loss = loss['loss'] - avg_loss.backward() - optimizer.step() + + if scaler: + scaled_avg_loss = scaler.scale(avg_loss) + scaled_avg_loss.backward() + scaler.minimize(optimizer, scaled_avg_loss) + else: + avg_loss.backward() + optimizer.step() optimizer.clear_grad() train_batch_cost += time.time() - batch_start @@ -480,11 +496,6 @@ def preprocess(is_train=False): 'CLS', 'PGNet', 'Distillation', 'NRTR', 'TableAttn', 'SAR', 'PSE', 'SEED' ] - windows_not_support_list = ['PSE'] - if platform.system() == "Windows" and alg in windows_not_support_list: - logger.warning('{} is not support in Windows now'.format( - windows_not_support_list)) - sys.exit() device = 'gpu:{}'.format(dist.ParallelEnv().dev_id) if use_gpu else 'cpu' device = paddle.set_device(device) diff --git a/tools/train.py b/tools/train.py index 05d295aa99718c25b94a123c23d08c2904fe8c6a..d182af2988cb29511be40a079d2b3e06605ebe28 100755 --- a/tools/train.py +++ b/tools/train.py @@ -102,10 +102,27 @@ def main(config, device, logger, vdl_writer): if valid_dataloader is not None: logger.info('valid dataloader has {} iters'.format( len(valid_dataloader))) + + use_amp = config["Global"].get("use_amp", False) + if use_amp: + AMP_RELATED_FLAGS_SETTING = { + 'FLAGS_cudnn_batchnorm_spatial_persistent': 1, + 'FLAGS_max_inplace_grad_add': 8, + } + paddle.fluid.set_flags(AMP_RELATED_FLAGS_SETTING) + scale_loss = config["Global"].get("scale_loss", 1.0) + use_dynamic_loss_scaling = config["Global"].get( + "use_dynamic_loss_scaling", False) + scaler = paddle.amp.GradScaler( + init_loss_scaling=scale_loss, + use_dynamic_loss_scaling=use_dynamic_loss_scaling) + else: + scaler = None + # start train program.train(config, train_dataloader, valid_dataloader, device, model, loss_class, optimizer, lr_scheduler, post_process_class, - eval_class, pre_best_model_dict, logger, vdl_writer) + eval_class, pre_best_model_dict, logger, vdl_writer, scaler) def test_reader(config, device, logger):