diff --git a/configs/picodet/README.md b/configs/picodet/README.md
index 4ec08a7a412b0bf34d47725977f18badf8f8be8a..7f4e6a539aaeee1b4f21739280566e2109022bfb 100644
--- a/configs/picodet/README.md
+++ b/configs/picodet/README.md
@@ -220,9 +220,10 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
### 部署
-- PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp)
+- OpenVINO demo [Python](../../deploy/third_engine/demo/openvino/python)
- [PaddleLite C++ demo](../../deploy/lite)
- [Android demo(Paddle Lite)](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo)
+- PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp)
Android demo可视化：
@@ -237,43 +238,35 @@ Android demo可视化：
依赖包:
- PaddlePaddle >= 2.2.2
-- PaddleSlim >= 2.2.1
+- PaddleSlim >= 2.2.2
**安装:**
```shell
-pip install paddleslim==2.2.1
+pip install paddleslim==2.2.2
```
-
-量化训练 (点击展开)
+
+量化训练
开始量化训练:
```shell
-python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
- --slim_config configs/slim/quant/picodet_s_quant.yml --eval
+python tools/train.py -c configs/picodet/picodet_s_416_coco_lcnet.yml \
+ --slim_config configs/slim/quant/picodet_s_416_lcnet_quant.yml --eval
```
- 更多细节请参考[slim文档](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim)
-
-离线量化 (点击展开)
-
-校准及导出量化模型:
+- 量化训练Model ZOO：
-```shell
-python tools/post_quant.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
- --slim_config configs/slim/post_quant/picodet_s_ptq.yml
-```
-
-- 注意: 离线量化模型精度问题正在解决中.
-
-
+| 量化模型 | 输入尺寸 | mAPval
0.5:0.95 | Configs | Weight | Inference Model | Paddle Lite(INT8) |
+| :-------- | :--------: | :--------------------: | :-------: | :----------------: | :----------------: | :----------------: |
+| PicoDet-S | 416*416 | 31.5 | [config](./picodet_s_416_coco_lcnet.yml) | [slim config](../slim/quant/picodet_s_416_lcnet_quant.yml) | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet_quant.pdparams) | [w/ 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant.tar) | [w/o 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant_non_postprocess.tar) | [w/ 后处理](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant.nb) | [w/o 后处理](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant_non_postprocess.nb) |
## 非结构化剪枝
diff --git a/configs/picodet/README_en.md b/configs/picodet/README_en.md
index eb8d12b576d2142e481a6d06e340d6562a703551..c1a9483fa4d47661435d1dd8e3364353e4ad30a6 100644
--- a/configs/picodet/README_en.md
+++ b/configs/picodet/README_en.md
@@ -216,9 +216,10 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
### Deploy
-- PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp)
+- OpenVINO demo [Python](../../deploy/third_engine/demo/openvino/python)
- [PaddleLite C++ demo](../../deploy/lite)
- [Android demo(Paddle Lite)](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo)
+- PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp)
Android demo visualization:
@@ -233,43 +234,35 @@ Android demo visualization:
Requirements:
- PaddlePaddle >= 2.2.2
-- PaddleSlim >= 2.2.1
+- PaddleSlim >= 2.2.2
**Install:**
```shell
-pip install paddleslim==2.2.1
+pip install paddleslim==2.2.2
```
-
-Quant aware (click to expand)
+
+Quant aware
Configure the quant config and start training:
```shell
-python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
- --slim_config configs/slim/quant/picodet_s_quant.yml --eval
+python tools/train.py -c configs/picodet/picodet_s_416_coco_lcnet.yml \
+ --slim_config configs/slim/quant/picodet_s_416_lcnet_quant.yml --eval
```
- More detail can refer to [slim document](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim)
-
-Post quant (click to expand)
-
-Configure the post quant config and start calibrate model:
+- Quant Aware Model ZOO：
-```shell
-python tools/post_quant.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
- --slim_config configs/slim/post_quant/picodet_s_ptq.yml
-```
-
-- Notes: Now the accuracy of post quant is abnormal and this problem is being solved.
-
-
+| Quant Model | Input size | mAPval
0.5:0.95 | Configs | Weight | Inference Model | Paddle Lite(INT8) |
+| :-------- | :--------: | :--------------------: | :-------: | :----------------: | :----------------: | :----------------: |
+| PicoDet-S | 416*416 | 31.5 | [config](./picodet_s_416_coco_lcnet.yml) | [slim config](../slim/quant/picodet_s_416_lcnet_quant.yml) | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet_quant.pdparams) | [w/ postprocess](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant.tar) | [w/o postprocess](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant_non_postprocess.tar) | [w/ postprocess](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant.nb) | [w/o postprocess](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant_non_postprocess.nb) |
## Unstructured Pruning
diff --git a/configs/slim/quant/picodet_s_416_lcnet_quant.yml b/configs/slim/quant/picodet_s_416_lcnet_quant.yml
new file mode 100644
index 0000000000000000000000000000000000000000..000807ab6b138ca8f28440f97b44809e75a9ac3d
--- /dev/null
+++ b/configs/slim/quant/picodet_s_416_lcnet_quant.yml
@@ -0,0 +1,22 @@
+pretrain_weights: https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet.pdparams
+slim: QAT
+
+QAT:
+ quant_config: {
+ 'activation_preprocess_type': 'PACT',
+ 'weight_quantize_type': 'channel_wise_abs_max', 'activation_quantize_type': 'moving_average_abs_max',
+ 'weight_bits': 8, 'activation_bits': 8, 'dtype': 'int8', 'window_size': 10000, 'moving_rate': 0.9,
+ 'quantizable_layer_type': ['Conv2D', 'Linear']}
+ print_model: False
+
+TrainReader:
+ batch_size: 48
+
+LearningRate:
+ base_lr: 0.024
+ schedulers:
+ - !CosineDecay
+ max_epochs: 300
+ - !LinearWarmup
+ start_factor: 0.1
+ steps: 300