Add Examples to deploy quantized models (#342)

* Add PaddleOCR Support * Add PaddleOCR Support * Add PaddleOCRv3 Support * Add PaddleOCRv3 Support * Update README.md * Update README.md * Update README.md * Update README.md * Add PaddleOCRv3 Support * Add PaddleOCRv3 Supports * Add PaddleOCRv3 Suport * Fix Rec diff * Remove useless functions * Remove useless comments * Add PaddleOCRv2 Support * Add PaddleOCRv3 & PaddleOCRv2 Support * remove useless parameters * Add utils of sorting det boxes * Fix code naming convention * Fix code naming convention * Fix code naming convention * Fix bug in the Classify process * Imporve OCR Readme * Fix diff in Cls model * Update Model Download Link in Readme * Fix diff in PPOCRv2 * Improve OCR readme * Imporve OCR readme * Improve OCR readme * Improve OCR readme * Imporve OCR readme * Improve OCR readme * Fix conflict * Add readme for OCRResult * Improve OCR readme * Add OCRResult readme * Improve OCR readme * Improve OCR readme * Add Model Quantization Demo * Fix Model Quantization Readme * Fix Model Quantization Readme * Add the function to do PTQ quantization * Improve quant tools readme * Improve quant tool readme * Improve quant tool readme * Add PaddleInference-GPU for OCR Rec model * Add QAT method to fastdeploy-quantization tool * Remove examples/slim for now * Move configs folder * Add Quantization Support for Classification Model * Imporve ways of importing preprocess * Upload YOLO Benchmark on readme * Upload YOLO Benchmark on readme * Upload YOLO Benchmark on readme * Improve Quantization configs and readme * Add support for multi-inputs model * Add backends and params file for YOLOv7 * Add quantized model deployment support for YOLO series * Fix YOLOv5 quantize readme * Fix YOLO quantize readme * Fix YOLO quantize readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Fix bug, change Fronted to ModelFormat * Change Fronted to ModelFormat * Add examples to deploy quantized paddleclas models * Fix readme * Add quantize Readme * Add quantize Readme * Add quantize Readme * Modify readme of quantization tools * Modify readme of quantization tools * Improve quantization tools readme * Improve quantization readme * Improve PaddleClas quantized model deployment readme * Add PPYOLOE-l quantized deployment examples * Improve quantization tools readme
2025-12-24 13:28:13 +08:00 · 2022-10-14 13:35:45 +08:00
parent aac879bf2d
commit b0663209f6
36 changed files with 1465 additions and 87 deletions
--- a/tools/quantization/configs/README.md
+++ b/tools/quantization/configs/README.md
@@ -0,0 +1,51 @@
+# FastDeploy 量化配置文件说明
+FastDeploy 量化配置文件中，包含了全局配置，量化蒸馏训练配置，离线量化配置和训练配置.
+用户除了直接使用FastDeploy提供在本目录的配置文件外，可以按需求自行修改相关配置文件
+
+## 实例解读
+
+```
+# 全局配置
+Global:
+  model_dir: ./yolov5s.onnx                   #输入模型的路径
+  format: 'onnx'                              #输入模型的格式, paddle模型请选择'paddle'
+  model_filename: model.pdmodel               #量化后转为paddle格式模型的模型名字
+  params_filename: model.pdiparams            #量化后转为paddle格式模型的参数名字
+  image_path: ./COCO_val_320                  #离线量化或者量化蒸馏训练使用的数据集路径
+  arch: YOLOv5                                #模型结构
+  input_list: ['x2paddle_images']             #待量化的模型的输入名字
+  preprocess: yolo_image_preprocess           #模型量化时,对数据做的预处理函数, 用户可以在 ../fdquant/dataset.py 中修改或自行编写新的预处理函数
+
+#量化蒸馏训练配置
+Distillation:
+  alpha: 1.0                                  #蒸馏loss所占权重
+  loss: soft_label                            #蒸馏loss算法
+
+Quantization:
+  onnx_format: true                           #是否采用ONNX量化标准格式, 要在FastDeploy上部署, 必须选true
+  use_pact: true                              #量化训练是否使用PACT方法
+  activation_quantize_type: 'moving_average_abs_max'     #激活量化方式
+  quantize_op_types:                          #需要进行量化的OP
+  - conv2d
+  - depthwise_conv2d
+
+#离线量化配置
+PTQ:
+  calibration_method: 'avg'                   #离线量化的激活校准算法, 可选: avg, abs_max, hist, KL, mse, emd
+  skip_tensor_list: None                      #用户可指定跳过某些conv层,不进行量化
+
+#训练参数配置
+TrainConfig:
+  train_iter: 3000
+  learning_rate: 0.00001
+  optimizer_builder:
+    optimizer:
+      type: SGD
+    weight_decay: 4.0e-05
+  target_metric: 0.365
+
+```
+## 更多详细配置方法
+
+FastDeploy一键量化功能由PaddeSlim助力, 更详细的量化配置方法请参考:
+[自动化压缩超参详细教程](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/hyperparameter_tutorial.md)