From 5c72d5a12b295d9242faaf37421e1b1257a00bc0 Mon Sep 17 00:00:00 2001
From: shangliang Xu <ghostxsl@users.noreply.github.com>
Date: Tue, 7 Jun 2022 14:44:29 +0800
Subject: [PATCH] [TIPC] add dist train infer (#6141)

---
 test_tipc/README.md                           |  1 +
 ...n_s_300e_coco_train_fleet_infer_python.txt | 53 +++++++++++++
 .../docs/test_train_fleet_inference_python.md | 76 +++++++++++++++++++
 test_tipc/prepare.sh                          | 22 +++---
 test_tipc/test_train_inference_python.sh      | 10 ++-
 5 files changed, 149 insertions(+), 13 deletions(-)
 create mode 100644 test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt
 create mode 100644 test_tipc/docs/test_train_fleet_inference_python.md

diff --git a/test_tipc/README.md b/test_tipc/README.md
index 097b61cd3..8df5e2230 100644
--- a/test_tipc/README.md
+++ b/test_tipc/README.md
@@ -105,6 +105,7 @@ bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/yolov3/yolov3_
 ## 4. 开始测试
 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) ：测试基于Python的模型训练、评估、推理等基本功能，包括裁剪、量化、蒸馏。
+- [test_train_fleet_inference_python 使用](./docs/test_train_fleet_inference_python.md)：测试基于Python的多机多卡训练与推理等基本功能。
 - [test_inference_cpp 使用](docs/test_inference_cpp.md)：测试基于C++的模型推理。
 - [test_serving 使用](./)：测试基于Paddle Serving的服务化部署功能。
 - [test_lite_arm_cpu_cpp 使用](./)：测试基于Paddle-Lite的ARM CPU端c++预测部署功能。
diff --git a/test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt b/test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt
new file mode 100644
index 000000000..775a96fb1
--- /dev/null
+++ b/test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ppyoloe_crn_s_300e_coco
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+use_gpu:True
+auto_cast:null
+epoch:lite_train_lite_infer=1|lite_train_whole_infer=1|whole_train_whole_infer=300
+save_dir:null
+TrainReader.batch_size:lite_train_lite_infer=2|lite_train_whole_infer=2|whole_train_whole_infer=2
+pretrain_weights:https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
+trained_model_name:model_final.pdparams
+train_infer_img_dir:./dataset/coco/test2017/
+filename:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml -o
+pact_train:tools/train.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml --slim_config _template_pact -o
+fpgm_train:tools/train.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml --slim_config _template_fpgm -o
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml -o
+null:null
+##
+===========================infer_params===========================
+--output_dir:./output_inference
+weights:https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
+norm_export:tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml -o
+pact_export:tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml --slim_config _template_pact -o
+fpgm_export:tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml --slim_config _template_fpgm -o
+distill_export:null
+export1:null
+export2:null
+kl_quant_export:tools/post_quant.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml --slim_config _template_kl_quant -o
+##
+infer_mode:norm
+infer_quant:False
+inference:./deploy/python/infer.py
+--device:gpu|cpu
+--enable_mkldnn:False
+--cpu_threads:4
+--batch_size:1|2
+--use_tensorrt:null
+--run_mode:paddle
+--model_dir:
+--image_dir:./dataset/coco/test2017/
+--save_log_path:null
+--run_benchmark:False
+--trt_max_shape:1600
+===========================infer_benchmark_params===========================
+numpy_infer_input:3x640x640.npy
\ No newline at end of file
diff --git a/test_tipc/docs/test_train_fleet_inference_python.md b/test_tipc/docs/test_train_fleet_inference_python.md
new file mode 100644
index 000000000..0b9bb6580
--- /dev/null
+++ b/test_tipc/docs/test_train_fleet_inference_python.md
@@ -0,0 +1,76 @@
+# Linux GPU/CPU 多机多卡训练推理测试
+
+Linux GPU/CPU 多机多卡训练推理测试的主程序为`test_train_fleet_inference_python.sh`，可以测试基于Python的模型训练、评估、推理等基本功能。
+
+## 1. 测试结论汇总
+
+- 训练相关：
+
+|   算法名称   | 模型名称 | 多机多卡 |
+|:--------:|   :----:  |    :----:  |
+| PP-YOLOE | ppyoloe_crn_s_300e_coco     | 分布式训练 |
+
+
+- 推理相关：
+
+|   算法名称   |           模型名称           | device_CPU | device_GPU | batchsize |
+|:--------:|:------------------------:|   :----:   |  :----:  |:---------:|
+| PP-YOLOE | ppyoloe_crn_s_300e_coco  |  支持 | 支持 |   1, 2    |
+
+
+## 2. 测试流程
+
+运行环境配置请参考[文档](./install.md)的内容配置TIPC的运行环境。
+
+### 2.1 功能测试
+
+#### 2.1.1 修改配置文件
+
+首先，修改配置文件中的`ip`设置:  假设两台机器的`ip`地址分别为`192.168.0.1`和`192.168.0.2`，则对应的配置文件`gpu_list`字段需要修改为`gpu_list:192.168.0.1,192.168.0.2;0,1`； `ip`地址查看命令为`ifconfig`。
+
+
+#### 2.1.2 准备数据
+
+运行`prepare.sh`准备数据和模型，以配置文件`test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt`为例，数据准备命令如下所示。
+
+```shell
+bash test_tipc/prepare.sh test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt lite_train_lite_infer
+```
+
+**注意：** 由于是多机训练，这里需要在所有的节点上均运行启动上述命令，准备数据。
+
+#### 2.1.3 修改起始端口并开始测试
+
+在多机的节点上使用下面的命令设置分布式的起始端口（否则后面运行的时候会由于无法找到运行端口而hang住），一般建议设置在`10000~20000`之间。
+
+```shell
+export FLAGS_START_PORT=17000
+```
+
+以配置文件`test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt`为例，测试方法如下所示。
+
+```shell
+bash test_tipc/test_train_inference_python.sh  test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_train_fleet_infer_python.txt lite_train_lite_infer
+```
+
+**注意：** 由于是多机训练，这里需要在所有的节点上均运行启动上述命令进行测试。
+
+
+#### 2.1.4 输出结果
+
+输出结果如下，表示命令运行成功。
+
+```bash
+ Run successfully with command - python3.7 -m paddle.distributed.launch --ips=192.168.0.1,192.168.0.2 --gpus=0,1
+ tools/train.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml -o log_iter=1 use_gpu=True save_dir=./test_tipc/outpu
+t/ppyoloe_crn_s_300e_coco/norm_train_gpus_0,1_autocast_null_nodes_2 epoch=1 pretrain_weights=https://paddledet.bj.bc
+ebos.com/models/ppyoloe_crn_s_300e_coco.pdparams TrainReader.batch_size=2 filename=ppyoloe_crn_s_300e_coco    !
+ 
+ ......
+ Run successfully with command - python3.7 ./deploy/python/infer.py --device=cpu --enable_mkldnn=False --cpu_threads
+=4 --model_dir=./test_tipc/output/ppyoloe_crn_s_300e_coco/norm_train_gpus_0,1_autocast_null_nodes_2/ppyoloe_crn_s_30
+0e_coco --batch_size=2 --image_dir=./dataset/coco/test2017/ --run_benchmark=False --trt_max_shape=1600 > ./test_tipc
+/output/ppyoloe_crn_s_300e_coco/python_infer_cpu_usemkldnn_False_threads_4_precision_fluid_batchsize_2.log 2>&1 !
+```
+
+**注意：** 由于分布式训练时，仅在`trainer_id=0`所在的节点中保存模型，因此其他的节点中在运行模型导出与推理时会报错，为正常现象。
diff --git a/test_tipc/prepare.sh b/test_tipc/prepare.sh
index 37efb0306..ca854ed71 100644
--- a/test_tipc/prepare.sh
+++ b/test_tipc/prepare.sh
@@ -22,15 +22,15 @@ if [ ${MODE} = "whole_train_whole_infer" ];then
     eval "${python} ./dataset/coco/download_coco.py"
 elif [ ${MODE} = "cpp_infer" ];then
     # download coco lite data
-    wget -nc -P ./dataset/coco/ https://paddledet.bj.bcebos.com/data/tipc/coco_tipc.tar
+    wget -nc -P ./dataset/coco/ https://paddledet.bj.bcebos.com/data/tipc/coco_tipc.tar --no-check-certificate
     cd ./dataset/coco/ && tar -xvf coco_tipc.tar && mv -n coco_tipc/* .
     rm -rf coco_tipc/ && cd ../../
     # download wider_face lite data
-    wget -nc -P ./dataset/wider_face/ https://paddledet.bj.bcebos.com/data/tipc/wider_tipc.tar
+    wget -nc -P ./dataset/wider_face/ https://paddledet.bj.bcebos.com/data/tipc/wider_tipc.tar --no-check-certificate
     cd ./dataset/wider_face/ && tar -xvf wider_tipc.tar && mv -n wider_tipc/* .
     rm -rf wider_tipc/ && cd ../../
     # download spine lite data
-    wget -nc -P ./dataset/spine_coco/ https://paddledet.bj.bcebos.com/data/tipc/spine_tipc.tar
+    wget -nc -P ./dataset/spine_coco/ https://paddledet.bj.bcebos.com/data/tipc/spine_tipc.tar --no-check-certificate
     cd ./dataset/spine_coco/ && tar -xvf spine_tipc.tar && mv -n spine_tipc/* .
     rm -rf spine_tipc/ && cd ../../
     if [[ ${model_name} =~ "s2anet" ]]; then
@@ -38,7 +38,7 @@ elif [ ${MODE} = "cpp_infer" ];then
         cd ../../
     fi
     # download mot lite data
-    wget -nc -P ./dataset/mot/ https://paddledet.bj.bcebos.com/data/tipc/mot_tipc.tar
+    wget -nc -P ./dataset/mot/ https://paddledet.bj.bcebos.com/data/tipc/mot_tipc.tar --no-check-certificate
     cd ./dataset/mot/ && tar -xvf mot_tipc.tar && mv -n mot_tipc/* .
     rm -rf mot_tipc/ && cd ../../
 
@@ -50,7 +50,7 @@ elif [ ${MODE} = "cpp_infer" ];then
             echo "################### Opencv already exists, skip downloading. ###################"
         else
             mkdir -p $(pwd)/deps && cd $(pwd)/deps
-            wget -c https://paddledet.bj.bcebos.com/data/opencv-3.4.16_gcc8.2_ffmpeg.tar.gz
+            wget -c https://paddledet.bj.bcebos.com/data/opencv-3.4.16_gcc8.2_ffmpeg.tar.gz --no-check-certificate
             tar -xvf opencv-3.4.16_gcc8.2_ffmpeg.tar.gz && cd ../
             echo "################### Finish downloading opencv. ###################"
         fi
@@ -60,13 +60,13 @@ elif [ ${MODE} = "benchmark_train" ];then
     pip install -U pip Cython
     pip install -r requirements.txt
     # prepare lite benchmark coco data
-    wget -nc -P ./dataset/coco/ https://paddledet.bj.bcebos.com/data/coco_benchmark.tar
+    wget -nc -P ./dataset/coco/ https://paddledet.bj.bcebos.com/data/coco_benchmark.tar --no-check-certificate
     cd ./dataset/coco/ && tar -xvf coco_benchmark.tar 
     mv -u coco_benchmark/* ./
     ls ./
     cd ../../
     # prepare lite benchmark mot data
-    wget -nc -P ./dataset/mot/ https://paddledet.bj.bcebos.com/data/mot_benchmark.tar
+    wget -nc -P ./dataset/mot/ https://paddledet.bj.bcebos.com/data/mot_benchmark.tar --no-check-certificate
     cd ./dataset/mot/ && tar -xvf mot_benchmark.tar
     mv -u mot_benchmark/* ./
     ls ./
@@ -87,15 +87,15 @@ elif [ ${MODE} = "serving_infer" ];then
     python -m pip install paddlepaddle-gpu==2.2.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html
 else
     # download coco lite data
-    wget -nc -P ./dataset/coco/ https://paddledet.bj.bcebos.com/data/tipc/coco_tipc.tar
+    wget -nc -P ./dataset/coco/ https://paddledet.bj.bcebos.com/data/tipc/coco_tipc.tar --no-check-certificate
     cd ./dataset/coco/ && tar -xvf coco_tipc.tar && mv -n coco_tipc/* .
     rm -rf coco_tipc/ && cd ../../
     # download wider_face lite data
-    wget -nc -P ./dataset/wider_face/ https://paddledet.bj.bcebos.com/data/tipc/wider_tipc.tar
+    wget -nc -P ./dataset/wider_face/ https://paddledet.bj.bcebos.com/data/tipc/wider_tipc.tar --no-check-certificate
     cd ./dataset/wider_face/ && tar -xvf wider_tipc.tar && mv -n wider_tipc/* .
     rm -rf wider_tipc/ && cd ../../
     # download spine_coco lite data
-    wget -nc -P ./dataset/spine_coco/ https://paddledet.bj.bcebos.com/data/tipc/spine_tipc.tar
+    wget -nc -P ./dataset/spine_coco/ https://paddledet.bj.bcebos.com/data/tipc/spine_tipc.tar --no-check-certificate
     cd ./dataset/spine_coco/ && tar -xvf spine_tipc.tar && mv -n spine_tipc/* .
     rm -rf spine_tipc/ && cd ../../
     if [[ ${model_name} =~ "s2anet" ]]; then
@@ -103,7 +103,7 @@ else
         cd ../../
     fi
     # download mot lite data
-    wget -nc -P ./dataset/mot/ https://paddledet.bj.bcebos.com/data/tipc/mot_tipc.tar
+    wget -nc -P ./dataset/mot/ https://paddledet.bj.bcebos.com/data/tipc/mot_tipc.tar --no-check-certificate
     cd ./dataset/mot/ && tar -xvf mot_tipc.tar && mv -n mot_tipc/* .
     rm -rf mot_tipc/ && cd ../../
 fi
diff --git a/test_tipc/test_train_inference_python.sh b/test_tipc/test_train_inference_python.sh
index d0eb77810..91b32271e 100644
--- a/test_tipc/test_train_inference_python.sh
+++ b/test_tipc/test_train_inference_python.sh
@@ -278,10 +278,16 @@ else
                 set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
                 if [ ${#gpu} -le 2 ];then  # train with cpu or single gpu
                     cmd="${python} ${run_train} LearningRate.base_lr=0.0001 log_iter=1 ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_batchsize} ${set_filename} ${set_train_params1} ${set_autocast}"
-                elif [ ${#ips} -le 26 ];then  # train with multi-gpu
+                elif [ ${#ips} -le 15 ];then  # train with multi-gpu
                     cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} log_iter=1 ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_batchsize} ${set_filename} ${set_train_params1} ${set_autocast}"
                 else     # train with multi-machine
-                    cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${set_use_gpu} ${run_train} log_iter=1 ${set_save_model} ${set_epoch} ${set_pretrain} ${set_batchsize} ${set_filename} ${set_train_params1} ${set_autocast}"
+                    IFS=","
+                    ips_array=(${ips})
+                    nodes=${#ips_array[@]}
+                    save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}_nodes_${nodes}"
+                    IFS="|"
+                    set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
+                    cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} log_iter=1 ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_batchsize} ${set_filename} ${set_train_params1} ${set_autocast}"
                 fi
                 # run train
                 eval $cmd
-- 
GitLab