Skip to content

P
PaddleDetection

s920243400 / PaddleDetection
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleDetection

通知 2
Star 0
Fork 0
P
PaddleDetection
未验证 提交 35a93b11 编写于 作者: G Guanghua Yu 提交者： GitHub
浏览文件
操作

fix quant & ptq export (#4370)

上级 26ae0bac
隐藏空白更改
内联 并排
Showing with 20 addition and 10 deletion
configs/picodet/README.md
浏览文件 @ 35a93b11
...@@ -23,13 +23,13 @@ We developed a series of lightweight models, which named `PicoDet`. Because of i ...@@ -23,13 +23,13 @@ We developed a series of lightweight models, which named `PicoDet`. Because of i
| Model | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<br><sup>(ms) | download | config | | Model | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<br><sup>(ms) | download | config |
| :------------------------ | :-------: | :------: | :---: | :---: | :---: | :------------: | :-------------------------------------------------: | :-----: | | :------------------------ | :-------: | :------: | :---: | :---: | :---: | :------------: | :-------------------------------------------------: | :-----: |
| PicoDet-S | 320*320 | 27.1 | 41.4 | 0.99 | 0.73 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_s_320_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_320_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_320_coco.yml) | | PicoDet-S | 320*320 | 27.1 | 41.4 | 0.99 | 0.73 | 7.78 | [model](https://paddledet.bj.bcebos.com/models/picodet_s_320_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_320_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_320_coco.yml) |
| PicoDet-S | 416*416 | 30.6 | 45.5 | 0.99 | 1.24 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco.yml) | | PicoDet-S | 416*416 | 30.6 | 45.5 | 0.99 | 1.24 | 11.84 | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco.yml) |
| PicoDet-M | 320*320 | 30.9 | 45.7 | 2.15 | 1.48 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_m_320_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_320_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_320_coco.yml) | | PicoDet-M | 320*320 | 30.9 | 45.7 | 2.15 | 1.48 | 10.56 | [model](https://paddledet.bj.bcebos.com/models/picodet_m_320_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_320_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_320_coco.yml) |
| PicoDet-M | 416*416 | 34.3 | 49.8 | 2.15 | 2.50 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_m_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_416_coco.yml) | | PicoDet-M | 416*416 | 34.3 | 49.8 | 2.15 | 2.50 | 15.87 | [model](https://paddledet.bj.bcebos.com/models/picodet_m_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_416_coco.yml) |
| PicoDet-L | 320*320 | 32.6 | 47.9 | 3.24 | 2.18 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_l_320_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_320_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_320_coco.yml) | | PicoDet-L | 320*320 | 32.6 | 47.9 | 3.24 | 2.18 | 12.82 | [model](https://paddledet.bj.bcebos.com/models/picodet_l_320_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_320_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_320_coco.yml) |
| PicoDet-L | 416*416 | 35.9 | 51.7 | 3.24 | 3.69 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_l_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_416_coco.yml) | | PicoDet-L | 416*416 | 35.9 | 51.7 | 3.24 | 3.69 | 19.42 | [model](https://paddledet.bj.bcebos.com/models/picodet_l_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_416_coco.yml) |
| PicoDet-L | 640*640 | 40.3 | 57.1 | 3.24 | 8.74 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco.yml) | | PicoDet-L | 640*640 | 40.3 | 57.1 | 3.24 | 8.74 | 41.52 | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco.yml) |
<details> <details>
...@@ -45,9 +45,9 @@ We developed a series of lightweight models, which named `PicoDet`. Because of i ...@@ -45,9 +45,9 @@ We developed a series of lightweight models, which named `PicoDet`. Because of i
| Model | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<br><sup>(ms) | download | config | | Model | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<br><sup>(ms) | download | config |
| :------------------------ | :-------: | :------: | :---: | :---: | :---: | :------------: | :-------------------------------------------------: | :-----: | | :------------------------ | :-------: | :------: | :---: | :---: | :---: | :------------: | :-------------------------------------------------: | :-----: |
| PicoDet-Shufflenetv2 1x | 416*416 | 30.0 | 44.6 | 1.17 | 1.53 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_shufflenetv2_1x_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_shufflenetv2_1x_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/more_config/picodet_shufflenetv2_1x_416_coco.yml) | | PicoDet-Shufflenetv2 1x | 416*416 | 30.0 | 44.6 | 1.17 | 1.53 | 14.76 | [model](https://paddledet.bj.bcebos.com/models/picodet_shufflenetv2_1x_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_shufflenetv2_1x_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/more_config/picodet_shufflenetv2_1x_416_coco.yml) |
| PicoDet-MobileNetv3-large 1x | 416*416 | 35.6 | 52.0 | 3.55 | 2.80 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_mobilenetv3_large_1x_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_mobilenetv3_large_1x_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/more_config/picodet_mobilenetv3_large_1x_416_coco.yml) | | PicoDet-MobileNetv3-large 1x | 416*416 | 35.6 | 52.0 | 3.55 | 2.80 | 18.87 | [model](https://paddledet.bj.bcebos.com/models/picodet_mobilenetv3_large_1x_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_mobilenetv3_large_1x_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/more_config/picodet_mobilenetv3_large_1x_416_coco.yml) |
| PicoDet-LCNet 1.5x | 416*416 | 36.3 | 52.2 | 3.10 | 3.85 | -- | [model](https://paddledet.bj.bcebos.com/models/picodet_lcnet_1_5x_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_lcnet_1_5x_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/more_config/picodet_lcnet_1_5x_416_coco.yml) | | PicoDet-LCNet 1.5x | 416*416 | 36.3 | 52.2 | 3.10 | 3.85 | 19.75 | [model](https://paddledet.bj.bcebos.com/models/picodet_lcnet_1_5x_416_coco.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_lcnet_1_5x_416_coco.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/more_config/picodet_lcnet_1_5x_416_coco.yml) |
## Deployment ## Deployment
......
ppdet/engine/trainer.py
浏览文件 @ 35a93b11
...@@ -597,6 +597,13 @@ class Trainer(object): ...@@ -597,6 +597,13 @@ class Trainer(object):
static_model = None static_model = None
pruned_input_spec = input_spec pruned_input_spec = input_spec
# TODO: Hard code, delete it when support prune input_spec.
if self.cfg.architecture == 'PicoDet':
pruned_input_spec = [{
"image": InputSpec(
shape=image_shape, name='image')
}]
return static_model, pruned_input_spec return static_model, pruned_input_spec
def export(self, output_dir='output_inference'): def export(self, output_dir='output_inference'):
......
ppdet/slim/__init__.py
浏览文件 @ 35a93b11
...@@ -63,6 +63,9 @@ def build_slim_model(cfg, slim_cfg, mode='train'): ...@@ -63,6 +63,9 @@ def build_slim_model(cfg, slim_cfg, mode='train'):
load_pretrain_weight(model, cfg.pretrain_weights) load_pretrain_weight(model, cfg.pretrain_weights)
slim = create(cfg.slim) slim = create(cfg.slim)
cfg['slim_type'] = cfg.slim cfg['slim_type'] = cfg.slim
# TODO: fix quant export model in framework.
if mode == 'test' and slim_load_cfg['slim'] == 'QAT':
slim.quant_config['activation_preprocess_type'] = None
cfg['model'] = slim(model) cfg['model'] = slim(model)
cfg['slim'] = slim cfg['slim'] = slim
if mode != 'train': if mode != 'train':
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或