From 4b0dd292e3defcabd50d6146a8bc8176843d0846 Mon Sep 17 00:00:00 2001 From: HydrogenSulfate <490868991@qq.com> Date: Tue, 28 Jun 2022 06:54:50 +0000 Subject: [PATCH] debug --- .../ImageNet/PPHGNet/PPHGNet_small_pact.yaml | 157 ---------------- .../docs/test_train_ptq_inference_python.md | 105 +++++++++++ test_tipc/test_ptq_inference_python.sh | 173 ++++++++++++++++++ 3 files changed, 278 insertions(+), 157 deletions(-) delete mode 100644 ppcls/configs/ImageNet/PPHGNet/PPHGNet_small_pact.yaml create mode 100644 test_tipc/docs/test_train_ptq_inference_python.md create mode 100644 test_tipc/test_ptq_inference_python.sh diff --git a/ppcls/configs/ImageNet/PPHGNet/PPHGNet_small_pact.yaml b/ppcls/configs/ImageNet/PPHGNet/PPHGNet_small_pact.yaml deleted file mode 100644 index 9f9e9c06..00000000 --- a/ppcls/configs/ImageNet/PPHGNet/PPHGNet_small_pact.yaml +++ /dev/null @@ -1,157 +0,0 @@ -# global configs -Global: - checkpoints: null - pretrained_model: null - output_dir: ./output/ - device: gpu - save_interval: 1 - eval_during_train: True - eval_interval: 1 - epochs: 600 - print_batch_step: 10 - use_visualdl: False - # used for static mode and model export - image_shape: [3, 224, 224] - save_inference_dir: ./inference - # training model under @to_static - to_static: False - use_dali: False - -# model architecture -Arch: - name: PPHGNet_small - class_num: 1000 - -# loss function config for traing/eval process -Loss: - Train: - - CELoss: - weight: 1.0 - epsilon: 0.1 - Eval: - - CELoss: - weight: 1.0 - - -Optimizer: - name: Momentum - momentum: 0.9 - lr: - name: Cosine - learning_rate: 0.5 - warmup_epoch: 5 - regularizer: - name: 'L2' - coeff: 0.00004 - - -# data loader for train and eval -DataLoader: - Train: - dataset: - name: ImageNetDataset - image_root: ./dataset/ILSVRC2012/ - cls_label_path: ./dataset/ILSVRC2012/train_list.txt - transform_ops: - - DecodeImage: - to_rgb: True - channel_first: False - - RandCropImage: - size: 224 - interpolation: bicubic - backend: pil - - RandFlipImage: - flip_code: 1 - - TimmAutoAugment: - config_str: rand-m7-mstd0.5-inc1 - interpolation: bicubic - img_size: 224 - - NormalizeImage: - scale: 1.0/255.0 - mean: [0.485, 0.456, 0.406] - std: [0.229, 0.224, 0.225] - order: '' - - RandomErasing: - EPSILON: 0.25 - sl: 0.02 - sh: 1.0/3.0 - r1: 0.3 - attempt: 10 - use_log_aspect: True - mode: pixel - batch_transform_ops: - - OpSampler: - MixupOperator: - alpha: 0.2 - prob: 0.5 - CutmixOperator: - alpha: 1.0 - prob: 0.5 - - sampler: - name: DistributedBatchSampler - batch_size: 128 - drop_last: False - shuffle: True - loader: - num_workers: 16 - use_shared_memory: True - - Eval: - dataset: - name: ImageNetDataset - image_root: ./dataset/ILSVRC2012/ - cls_label_path: ./dataset/ILSVRC2012/val_list.txt - transform_ops: - - DecodeImage: - to_rgb: True - channel_first: False - - ResizeImage: - resize_short: 236 - interpolation: bicubic - backend: pil - - CropImage: - size: 224 - - NormalizeImage: - scale: 1.0/255.0 - mean: [0.485, 0.456, 0.406] - std: [0.229, 0.224, 0.225] - order: '' - sampler: - name: DistributedBatchSampler - batch_size: 128 - drop_last: False - shuffle: False - loader: - num_workers: 16 - use_shared_memory: True - -Infer: - infer_imgs: docs/images/inference_deployment/whl_demo.jpg - batch_size: 10 - transforms: - - DecodeImage: - to_rgb: True - channel_first: False - - ResizeImage: - resize_short: 236 - - CropImage: - size: 224 - - NormalizeImage: - scale: 1.0/255.0 - mean: [0.485, 0.456, 0.406] - std: [0.229, 0.224, 0.225] - order: '' - - ToCHWImage: - PostProcess: - name: Topk - topk: 5 - class_id_map_file: ppcls/utils/imagenet1k_label_list.txt - -Metric: - Train: - - TopkAcc: - topk: [1, 5] - Eval: - - TopkAcc: - topk: [1, 5] diff --git a/test_tipc/docs/test_train_ptq_inference_python.md b/test_tipc/docs/test_train_ptq_inference_python.md new file mode 100644 index 00000000..22a0ff91 --- /dev/null +++ b/test_tipc/docs/test_train_ptq_inference_python.md @@ -0,0 +1,105 @@ +# Linux GPU/CPU KL离线量化推理测试 + +Linux GPU/CPU KL离线量化推理测试的主程序为`test_ptq_inference_python.sh`，可以测试基于Python的模型KL离线量化推理等基本功能。 + +## 1. 测试结论汇总 + +- KL离线量化： + +| 算法名称 | 模型名称 | CPU | +| :-------------: | :-------------------------------------: | :----------: | +| MobileNetV3 | MobileNetV3_large_x1_0 | KL离线量化 | +| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | KL离线量化 | +| PPHGNet | PPHGNet_small | KL离线量化 | +| PPHGNet | PPHGNet_tiny | KL离线量化 | +| PPLCNet | PPLCNet_x0_25 | KL离线量化 | +| PPLCNet | PPLCNet_x0_35 | KL离线量化 | +| PPLCNet | PPLCNet_x0_5 | KL离线量化 | +| PPLCNet | PPLCNet_x0_75 | KL离线量化 | +| PPLCNet | PPLCNet_x1_0 | KL离线量化 | +| PPLCNet | PPLCNet_x1_5 | KL离线量化 | +| PPLCNet | PPLCNet_x2_0 | KL离线量化 | +| PPLCNet | PPLCNet_x2_5 | KL离线量化 | +| PPLCNetV2 | PPLCNetV2_base | KL离线量化 | +| ResNet | ResNet50 | KL离线量化 | +| ResNet | ResNet50_vd | KL离线量化 | +| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | KL离线量化 | + +- 推理相关： + +| 算法名称 | 模型名称 | CPU | +| :-------------: | :-------------------------------------: | :----------: | +| MobileNetV3 | MobileNetV3_large_x1_0 | KL离线量化 | +| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | KL离线量化 | +| PPHGNet | PPHGNet_small | KL离线量化 | +| PPHGNet | PPHGNet_tiny | KL离线量化 | +| PPLCNet | PPLCNet_x0_25 | KL离线量化 | +| PPLCNet | PPLCNet_x0_35 | KL离线量化 | +| PPLCNet | PPLCNet_x0_5 | KL离线量化 | +| PPLCNet | PPLCNet_x0_75 | KL离线量化 | +| PPLCNet | PPLCNet_x1_0 | KL离线量化 | +| PPLCNet | PPLCNet_x1_5 | KL离线量化 | +| PPLCNet | PPLCNet_x2_0 | KL离线量化 | +| PPLCNet | PPLCNet_x2_5 | KL离线量化 | +| PPLCNetV2 | PPLCNetV2_base | KL离线量化 | +| ResNet | ResNet50 | KL离线量化 | +| ResNet | ResNet50_vd | KL离线量化 | +| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | KL离线量化 | + + +## 2. 测试流程 + +一下测试流程以 MobileNetV3_large_x1_0 模型为例。 + +### 2.1 准备环境 + +- 安装PaddlePaddle：如果您已经安装了2.2或者以上版本的paddlepaddle，那么无需运行下面的命令安装paddlepaddle。 + ```bash + # 需要安装2.2及以上版本的Paddle + # 安装GPU版本的Paddle + python3.7 -m pip install paddlepaddle-gpu==2.2.0 + # 安装CPU版本的Paddle + python3.7 -m pip install paddlepaddle==2.2.0 + ``` + +- 安装PaddleSlim + ```bash + python3.7 -m pip install paddleslim==2.2.0 + ``` + +- 安装依赖 + ```bash + python3.7 -m pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple + ``` + +- 安装AutoLog（规范化日志输出工具） + ```bash + python3.7 -m pip install https://paddleocr.bj.bcebos.com/libs/auto_log-1.2.0-py3-none-any.whl + ``` + +### 2.2 准备数据和模型 + +```bash +bash test_tipc/prepare.sh test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_ptq_infer_python.txt whole_infer +``` + +离线量化的操作流程，可参考[文档](../../deploy/slim/README.md)。 + +### 2.3 功能测试 + +以`MobileNetV3_large_x1_0`的`Linux GPU/CPU KL离线量化训练推理测试`为例，命令如下所示。 + +```bash +bash test_tipc/test_ptq_inference_python.sh test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_ptq_infer_python.txt whole_infer +``` + +输出结果如下，表示命令运行成功。 + +```log +Run successfully with command - MobileNetV3_large_x1_0 - python3.7 deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.save_inference_dir=./MobileNetV3_large_x1_0_infer! +Run successfully with command - MobileNetV3_large_x1_0 - python3.7 python/predict_cls.py -c configs/inference_cls.yaml -o Global.use_gpu=True -o Global.use_tensorrt=False -o Global.use_fp16=False -o Global.inference_model_dir=.././MobileNetV3_large_x1_0_infer//quant_post_static_model -o Global.batch_size=1 -o Global.infer_imgs=../deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg -o Global.benchmark=False > .././test_tipc/output/MobileNetV3_large_x1_0/whole_infer/infer_gpu_usetrt_False_precision_False_batchsize_1.log 2>&1 ! +Run successfully with command - MobileNetV3_large_x1_0 - python3.7 python/predict_cls.py -c configs/inference_cls.yaml -o Global.use_gpu=False -o Global.enable_mkldnn=False -o Global.cpu_num_threads=1 -o Global.inference_model_dir=.././MobileNetV3_large_x1_0_infer//quant_post_static_model -o Global.batch_size=1 -o Global.infer_imgs=../deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg -o Global.benchmark=False > .././test_tipc/output/MobileNetV3_large_x1_0/whole_infer/infer_cpu_usemkldnn_False_threads_1_batchsize_1.log 2>&1 ! +``` +同时，测试过程中的日志保存在`PaddleClas/test_tipc/output/MobileNetV3_large_x1_0/whole_infer`下。 + +如果运行失败，也会在终端中输出运行失败的日志信息以及对应的运行命令。可以基于该命令，分析运行失败的原因。 diff --git a/test_tipc/test_ptq_inference_python.sh b/test_tipc/test_ptq_inference_python.sh new file mode 100644 index 00000000..82c98164 --- /dev/null +++ b/test_tipc/test_ptq_inference_python.sh @@ -0,0 +1,173 @@ +#!/bin/bash +FILENAME=$1 +source test_tipc/common_func.sh + +# MODE be one of ['whole_infer'] +MODE=$2 + +dataline=$(cat ${FILENAME}) + +# parser params +IFS=$'\n' +lines=(${dataline}) + +# The training params +model_name=$(func_parser_value "${lines[1]}") +python=$(func_parser_value "${lines[2]}") +gpu_list=$(func_parser_value "${lines[3]}") +train_use_gpu_key=$(func_parser_key "${lines[4]}") +train_use_gpu_value=$(func_parser_value "${lines[4]}") +autocast_list=$(func_parser_value "${lines[5]}") +autocast_key=$(func_parser_key "${lines[5]}") +epoch_key=$(func_parser_key "${lines[6]}") +epoch_num=$(func_parser_params "${lines[6]}") +save_model_key=$(func_parser_key "${lines[7]}") +train_batch_key=$(func_parser_key "${lines[8]}") +train_batch_value=$(func_parser_value "${lines[8]}") +pretrain_model_key=$(func_parser_key "${lines[9]}") +pretrain_model_value=$(func_parser_value "${lines[9]}") +train_model_name=$(func_parser_value "${lines[10]}") +train_infer_img_dir=$(func_parser_value "${lines[11]}") +train_param_key1=$(func_parser_key "${lines[12]}") +train_param_value1=$(func_parser_value "${lines[12]}") + +trainer_list=$(func_parser_value "${lines[14]}") +trainer_norm=$(func_parser_key "${lines[15]}") +norm_trainer=$(func_parser_value "${lines[15]}") +pact_key=$(func_parser_key "${lines[16]}") +pact_trainer=$(func_parser_value "${lines[16]}") +fpgm_key=$(func_parser_key "${lines[17]}") +fpgm_trainer=$(func_parser_value "${lines[17]}") +distill_key=$(func_parser_key "${lines[18]}") +distill_trainer=$(func_parser_value "${lines[18]}") +to_static_key=$(func_parser_key "${lines[19]}") +to_static_trainer=$(func_parser_value "${lines[19]}") +trainer_key2=$(func_parser_key "${lines[20]}") +trainer_value2=$(func_parser_value "${lines[20]}") + +eval_py=$(func_parser_value "${lines[23]}") +eval_key1=$(func_parser_key "${lines[24]}") +eval_value1=$(func_parser_value "${lines[24]}") + +save_infer_key=$(func_parser_key "${lines[27]}") +export_weight=$(func_parser_key "${lines[28]}") +norm_export=$(func_parser_value "${lines[29]}") +pact_export=$(func_parser_value "${lines[30]}") +fpgm_export=$(func_parser_value "${lines[31]}") +distill_export=$(func_parser_value "${lines[32]}") +kl_quant_cmd_key=$(func_parser_key "${lines[33]}") +kl_quant_cmd_value=$(func_parser_value "${lines[33]}") +export_key2=$(func_parser_key "${lines[34]}") +export_value2=$(func_parser_value "${lines[34]}") + +# parser inference model +infer_model_dir_list=$(func_parser_value "${lines[36]}") +infer_export_flag=$(func_parser_value "${lines[37]}") +infer_is_quant=$(func_parser_value "${lines[38]}") + +# parser inference +inference_py=$(func_parser_value "${lines[39]}") +use_gpu_key=$(func_parser_key "${lines[40]}") +use_gpu_list=$(func_parser_value "${lines[40]}") +use_mkldnn_key=$(func_parser_key "${lines[41]}") +use_mkldnn_list=$(func_parser_value "${lines[41]}") +cpu_threads_key=$(func_parser_key "${lines[42]}") +cpu_threads_list=$(func_parser_value "${lines[42]}") +batch_size_key=$(func_parser_key "${lines[43]}") +batch_size_list=$(func_parser_value "${lines[43]}") +use_trt_key=$(func_parser_key "${lines[44]}") +use_trt_list=$(func_parser_value "${lines[44]}") +precision_key=$(func_parser_key "${lines[45]}") +precision_list=$(func_parser_value "${lines[45]}") +infer_model_key=$(func_parser_key "${lines[46]}") +image_dir_key=$(func_parser_key "${lines[47]}") +infer_img_dir=$(func_parser_value "${lines[47]}") +save_log_key=$(func_parser_key "${lines[48]}") +benchmark_key=$(func_parser_key "${lines[49]}") +benchmark_value=$(func_parser_value "${lines[49]}") +infer_key1=$(func_parser_key "${lines[50]}") +infer_value1=$(func_parser_value "${lines[50]}") +if [ ! $epoch_num ]; then + epoch_num=2 +fi +if [[ $MODE = 'benchmark_train' ]]; then + epoch_num=1 +fi + +LOG_PATH="./test_tipc/output/${model_name}/${MODE}" +mkdir -p ${LOG_PATH} +status_log="${LOG_PATH}/results_python.log" + +function func_inference() { + IFS='|' + _python=$1 + _script=$2 + _model_dir=$3 + _log_path=$4 + _img_dir=$5 + _flag_quant=$6 + # inference + for use_gpu in ${use_gpu_list[*]}; do + if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then + for use_mkldnn in ${use_mkldnn_list[*]}; do + for threads in ${cpu_threads_list[*]}; do + for batch_size in ${batch_size_list[*]}; do + _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log" + set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}") + set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}") + set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}") + set_cpu_threads=$(func_set_params "${cpu_threads_key}" "${threads}") + set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}") + set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}") + command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} ${set_infer_params1} > ${_save_log_path} 2>&1 " + eval $command + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${command}" "../${status_log}" "${model_name}" + done + done + done + elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then + for use_trt in ${use_trt_list[*]}; do + for precision in ${precision_list[*]}; do + if [ ${precision} = "True" ] && [ ${use_trt} = "False" ]; then + continue + fi + for batch_size in ${batch_size_list[*]}; do + _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log" + set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}") + set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}") + set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}") + set_tensorrt=$(func_set_params "${use_trt_key}" "${use_trt}") + set_precision=$(func_set_params "${precision_key}" "${precision}") + set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}") + command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} > ${_save_log_path} 2>&1 " + eval $command + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${command}" "../${status_log}" "${model_name}" + done + done + done + else + echo "Does not support hardware other than CPU and GPU Currently!" + fi + done +} + +# for kl_quant +if [ ${kl_quant_cmd_value} != "null" ] && [ ${kl_quant_cmd_value} != "False" ]; then + echo "kl_quant" + command="${python} ${kl_quant_cmd_value}" + echo ${command} + eval $command + last_status=${PIPESTATUS[0]} + status_check $last_status "${command}" "${status_log}" "${model_name}" + cd ${infer_model_dir_list}/quant_post_static_model + ln -s __model__ inference.pdmodel + ln -s __params__ inference.pdiparams + cd ../../deploy + is_quant=True + func_inference "${python}" "${inference_py}" "../${infer_model_dir_list}/quant_post_static_model" "../${LOG_PATH}" "${infer_img_dir}" ${is_quant} + cd .. +fi -- GitLab