Add Quantization Function. (#256)

* 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
2025-12-24 13:28:13 +08:00 · 2022-10-08 15:45:28 +08:00
parent 8d47637541
commit 1efc0fa6b0
13 changed files with 736 additions and 0 deletions
--- a/tools/quantization/configs/classification/mobilenetv1_ssld_quant.yaml
+++ b/tools/quantization/configs/classification/mobilenetv1_ssld_quant.yaml
@@ -0,0 +1,49 @@
+Global:
+  model_dir: ./MobileNetV1_ssld_infer/
+  format: 'paddle'
+  model_filename: inference.pdmodel
+  params_filename: inference.pdiparams
+  image_path: ./ImageNet_val_640
+  arch: MobileNetV1
+  input_list: ['input']
+  preprocess: cls_image_preprocess
+
+
+Distillation:
+  alpha: 1.0
+  loss: l2
+  node:
+  - softmax_0.tmp_0
+
+
+Quantization:
+  use_pact: true
+  activation_bits: 8
+  is_full_quantize: false
+  onnx_format: True
+  activation_quantize_type: moving_average_abs_max
+  weight_quantize_type: channel_wise_abs_max
+  not_quant_pattern:
+  - skip_quant
+  quantize_op_types:
+  - conv2d
+  - depthwise_conv2d
+  weight_bits: 8
+
+
+TrainConfig:
+  train_iter: 5000
+  learning_rate:
+    type: CosineAnnealingDecay
+    learning_rate: 0.015
+    T_max: 8000
+  optimizer_builder:
+    optimizer:
+      type: Momentum
+    weight_decay: 0.00002
+  origin_metric: 0.70898
+
+
+PTQ:
+  calibration_method: 'avg'   # option: avg, abs_max, hist, KL, mse
+  skip_tensor_list: None
--- a/tools/quantization/configs/classification/resnet50_vd_quant.yaml
+++ b/tools/quantization/configs/classification/resnet50_vd_quant.yaml
@@ -0,0 +1,47 @@
+Global:
+  model_dir: ./ResNet50_vd_infer/
+  format: 'paddle'
+  model_filename: inference.pdmodel
+  params_filename: inference.pdiparams
+  image_path: ./ImageNet_val_640
+  arch: ResNet50
+  input_list: ['input']
+  preprocess: cls_image_preprocess
+
+
+Distillation:
+  alpha: 1.0
+  loss: l2
+  node:
+  - softmax_0.tmp_0
+
+Quantization:
+  use_pact: true
+  activation_bits: 8
+  is_full_quantize: false
+  onnx_format: True
+  activation_quantize_type: moving_average_abs_max
+  weight_quantize_type: channel_wise_abs_max
+  not_quant_pattern:
+  - skip_quant
+  quantize_op_types:
+  - conv2d
+  - depthwise_conv2d
+  weight_bits: 8
+
+TrainConfig:
+  train_iter: 5000
+  learning_rate:
+    type: CosineAnnealingDecay
+    learning_rate: 0.015
+    T_max: 8000
+  optimizer_builder:
+    optimizer:
+      type: Momentum
+    weight_decay: 0.00002
+  origin_metric: 0.7912
+
+
+PTQ:
+  calibration_method: 'avg'   # option: avg, abs_max, hist, KL, mse
+  skip_tensor_list: None