Add more rtdetr ACT demo (#1747)

example/auto_compression/detection/README.md

@@ -44,6 +44,29 @@
 | :-------- |:-------- | :---------------------: | :----------------: | :---------------: | :----------------------: | :---------------------: |
 | SSD-MobileNetv1 |  73.8  |   73.52    |   4.0ms  |  1.7ms  |  [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/ssd_mbv1_voc_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/ssd_mobilenet_v1_quant.tar) |
 - 测速环境：Tesla T4，TensorRT 8.4.1，CUDA 11.2，batch_size=1，包含NMS.
+
+### RT-DETR
+
+| 模型              | Base mAP | 离线量化mAP | ACT量化mAP | TRT-FP32 | TRT-FP16 |  TRT-INT8  |                           配置文件                           |                           量化模型                           |
+| :---------------- | :------- | :---------: | :--------: | :------: | :------: | :--------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
+| RT-DETR-R50       | 53.1     |    52.9     |    53.0    | 32.05ms  |  9.12ms  | **6.96ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_r50vd_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_r50vd_6x_coco_quant.tar) |
+| RT-DETR-R101      | 54.3     |      -      |    54.1    | 54.13ms  | 12.68ms  | **9.20ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_r101vd_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_r101vd_6x_coco_quant.tar) |
+| RT-DETR-HGNetv2-L | 53.0     |      -      |    52.9    | 26.16ms  |  8.54ms  | **6.65ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_hgnetv2_l_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_hgnetv2_l_6x_coco_quant.tar) |
+| RT-DETR-HGNetv2-X | 54.8     |      -      |    54.6    | 49.22ms  | 12.50ms  | **9.24ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_hgnetv2_x_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_hgnetv2_x_6x_coco_quant.tar) |
+
+- 上表测试环境：Tesla T4，TensorRT 8.6.0，CUDA 11.7，batch_size=1。
+
+| 模型              | Base mAP | 离线量化mAP | ACT量化mAP | TRT-FP32 | TRT-FP16 |  TRT-INT8  |                           配置文件                           |                           量化模型                           |
+| :---------------- | :------- | :---------: | :--------: | :------: | :------: | :--------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
+| RT-DETR-R50       | 53.1     |    52.9     |    53.0    |  9.64ms  |  5.00ms  | **3.99ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_r50vd_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_r50vd_6x_coco_quant.tar) |
+| RT-DETR-R101      | 54.3     |      -      |    54.1    | 14.93ms  |  7.15ms  | **5.12ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_r101vd_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_r101vd_6x_coco_quant.tar) |
+| RT-DETR-HGNetv2-L | 53.0     |      -      |    52.9    |  8.17ms  |  4.77ms  | **4.00ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_hgnetv2_l_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_hgnetv2_l_6x_coco_quant.tar) |
+| RT-DETR-HGNetv2-X | 54.8     |      -      |    54.6    | 12.81ms  |  6.97ms  | **5.32ms** | [config](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/detection/configs/rtdetr_hgnetv2_x_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/rtdetr_hgnetv2_x_6x_coco_quant.tar) |
+
+- 上表测试环境：A10，TensorRT 8.6.0，CUDA 11.6，batch_size=1。
+- mAP的指标均在COCO val2017数据集中评测得到，IoU=0.5:0.95。
+- 两个表中的离线量化只量化模型中的conv2d，ACT量化模型中的conv2d和matmul。
+
 ## 3. 自动压缩流程
 
 #### 3.1 准备环境

example/auto_compression/detection/configs/rtdetr_hgnetv2_l_qat_dis.yaml

+
+Global:
+  reader_config: configs/rtdetr_reader.yml
+  include_nms: True
+  Evaluation: True
+  model_dir: ./rtdetr_hgnetv2_l_6x_coco/
+  model_filename: model.pdmodel
+  params_filename: model.pdiparams
+
+Distillation:
+  alpha: 1.0
+  loss: soft_label
+
+QuantAware:
+  onnx_format: true
+  activation_quantize_type: 'moving_average_abs_max'
+  quantize_op_types:
+  - conv2d
+  - depthwise_conv2d
+  - matmul_v2
+
+TrainConfig:
+  train_iter: 200
+  eval_iter: 50
+  learning_rate:  
+    type: CosineAnnealingDecay
+    learning_rate: 0.00003
+    T_max: 10000
+  optimizer_builder:
+    optimizer: 
+      type: SGD
+    weight_decay: 4.0e-05

example/auto_compression/detection/configs/rtdetr_hgnetv2_x_qat_dis.yaml

+
+Global:
+  reader_config: configs/rtdetr_reader.yml
+  include_nms: True
+  Evaluation: True
+  model_dir: ./rtdetr_r50vd_6x_coco/ 
+  model_filename: model.pdmodel
+  params_filename: model.pdiparams
+
+Distillation:
+  alpha: 1.0
+  loss: soft_label
+
+QuantAware:
+  onnx_format: true
+  activation_quantize_type: 'moving_average_abs_max'
+  quantize_op_types:
+  - conv2d
+  - depthwise_conv2d
+  - matmul_v2
+
+TrainConfig:
+  train_iter: 500
+  eval_iter: 100
+  learning_rate:  
+    type: CosineAnnealingDecay
+    learning_rate: 0.00003
+    T_max: 10000
+  optimizer_builder:
+    optimizer: 
+      type: SGD
+    weight_decay: 4.0e-05

example/auto_compression/detection/configs/rtdetr_r101vd_qat_dis.yaml

+
+Global:
+  reader_config: configs/rtdetr_reader.yml
+  include_nms: True
+  Evaluation: True
+  model_dir: ./rtdetr_hgnetv2_x_6x_coco/
+  model_filename: model.pdmodel
+  params_filename: model.pdiparams
+
+Distillation:
+  alpha: 1.0
+  loss: soft_label
+
+QuantAware:
+  onnx_format: true
+  activation_quantize_type: 'moving_average_abs_max'
+  quantize_op_types:
+  - conv2d
+  - depthwise_conv2d
+  - matmul_v2
+
+TrainConfig:
+  train_iter: 200
+  eval_iter: 50
+  learning_rate:  
+    type: CosineAnnealingDecay
+    learning_rate: 0.00003
+    T_max: 10000
+  optimizer_builder:
+    optimizer: 
+      type: SGD
+    weight_decay: 4.0e-05

example/auto_compression/detection/configs/rtdetr_r50vd_qat_dis.yaml

@@ -17,10 +17,11 @@ QuantAware:
   quantize_op_types:
   - conv2d
   - depthwise_conv2d
+  - matmul_v2
 
 TrainConfig:
-  train_iter: 10
-  eval_iter: 10
+  train_iter: 500
+  eval_iter: 100
   learning_rate:  
     type: CosineAnnealingDecay
     learning_rate: 0.00003