未验证 提交 7c3def89 编写于 作者: G Guanghua Yu 提交者: GitHub

fix some model link in dygraph (#2256)

上级 07b75a88
...@@ -4,8 +4,8 @@ ...@@ -4,8 +4,8 @@
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: | | :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50-FPN | Cascade Faster | 1 | 1x | ---- | 41.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Cascade Faster | 1 | 1x | ---- | 41.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Mask | 1 | 1x | ---- | 41.6 | 35.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Cascade Mask | 1 | 1x | ---- | 41.8 | 36.3 | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
## Citations ## Citations
``` ```
......
...@@ -9,8 +9,11 @@ ...@@ -9,8 +9,11 @@
| ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 46.5 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 46.5 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Mask | c3-c5 | 1 | 1x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml) | | ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml) | | ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 45.6 | 40.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Faster | c3-c5 | 1 | 1x | - | 42.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 1 | 1x | - | 48.8 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
**注意事项:** **注意事项:**
......
_BASE_: [
'../datasets/coco_detection.yml',
'../runtime.yml',
'../cascade_rcnn/_base_/optimizer_1x.yml',
'../cascade_rcnn/_base_/cascade_rcnn_r50_fpn.yml',
'../cascade_rcnn/_base_/cascade_fpn_reader.yml',
]
weights: output/cascade_rcnn_dcn_r50_fpn_1x_coco/model_final
ResNet:
depth: 50
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
_BASE_: [
'cascade_rcnn_dcn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final
ResNet:
depth: 101
groups: 64
base_width: 4
base_channels: 64
variant: d
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
...@@ -12,9 +12,9 @@ FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free obje ...@@ -12,9 +12,9 @@ FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free obje
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 | | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 |
| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50-FPN | FCOS | 2 | 1x | ---- | 39.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_1x_coco.yml) | | ResNet50-FPN | FCOS | 2 | 1x | ---- | 39.6 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 41.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) | | ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 41.8 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) |
**Notes:** **Notes:**
......
...@@ -30,5 +30,5 @@ ...@@ -30,5 +30,5 @@
| Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs |
| :---------------------- | :------------- | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | | :---------------------- | :------------- | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: |
| HRNetV2p_W18 | Faster | 1 | 1x | - | 36.8 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_hrnetv2p_w18_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco.yml) | | HRNetV2p_W18 | Faster | 1 | 1x | - | 36.8 | - | [model](https://paddledet.bj.bcebos.com/models/faster_rcnn_hrnetv2p_w18_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco.yml) |
| HRNetV2p_W18 | Faster | 1 | 2x | - | 39.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_hrnetv2p_w18_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/hrnet/faster_rcnn_hrnetv2p_w18_2x_coco.yml) | | HRNetV2p_W18 | Faster | 1 | 2x | - | 39.0 | - | [model](https://paddledet.bj.bcebos.com/models/faster_rcnn_hrnetv2p_w18_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/hrnet/faster_rcnn_hrnetv2p_w18_2x_coco.yml) |
...@@ -4,8 +4,16 @@ ...@@ -4,8 +4,16 @@
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------| :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: | | :------------------- | :------------| :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50 | Mask | 1 | 1x | ---- | 36.4 | 31.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml) | | ResNet50 | Mask | 1 | 1x | ---- | 37.4 | 32.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 1x | ---- | 38.3 | 34.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) | | ResNet50 | Mask | 1 | 2x | ---- | 39.7 | 34.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_2x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 1x | ---- | 39.2 | 35.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 2x | ---- | 40.5 | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_2x_coco.yml) |
| ResNet50-vd-FPN | Mask | 1 | 1x | ---- | 40.3 | 36.4 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Mask | 1 | 2x | ---- | 41.4 | 37.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-FPN | Mask | 1 | 1x | ---- | 40.6 | 36.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r101_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.yml) |
| ResNet101-vd-FPN | Mask | 1 | 1x | ---- | 42.4 | 38.1 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | 1 | 1x | ---- | 44.0 | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | 1 | 2x | ---- | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) |
## Citations ## Citations
``` ```
......
...@@ -79,6 +79,7 @@ MaskHead: ...@@ -79,6 +79,7 @@ MaskHead:
share_bbox_feat: true share_bbox_feat: true
MaskFeat: MaskFeat:
num_convs: 0
out_channels: 256 out_channels: 256
MaskAssigner: MaskAssigner:
......
_BASE_: [
'mask_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
weights: output/mask_rcnn_r50_vd_fpn_1x_coco/model_final
ResNet:
# index 0 stands for res2
depth: 50
variant: d
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
_BASE_: [
'mask_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/mask_rcnn_x101_vd_64x4d_fpn_2x_coco/model_final
ResNet:
# for ResNeXt: groups, base_width, base_channels
depth: 101
variant: d
groups: 64
base_width: 4
base_channels: 64
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
epoch: 24
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.1
steps: 1000
...@@ -15,8 +15,8 @@ ...@@ -15,8 +15,8 @@
| 模型 | 压缩策略 | GFLOPs | 模型体积(MB) | 输入尺寸 | 预测时延(SD855)| Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 | | 模型 | 压缩策略 | GFLOPs | 模型体积(MB) | 输入尺寸 | 预测时延(SD855)| Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| :----------------| :-------: | :------------: | :-------------: | :------: | :--------: | :------: | :-----------------------------------------------------: |:-------------: | :------: | | :----------------| :-------: | :------------: | :-------------: | :------: | :--------: | :------: | :-----------------------------------------------------: |:-------------: | :------: |
| YOLOv3-MobileNetV1 | baseline | 24.13 | 93 | 608 | 289.9ms | 75.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | - | | YOLOv3-MobileNetV1 | baseline | 24.13 | 93 | 608 | 289.9ms | 75.1 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | - |
| YOLOv3-MobileNetV1 | 剪裁-l1_norm(sensity) | 15.78(-34.49%) | 66(-29%) | 608 | - | 77.6(+2.5) | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/slim/yolov3_mobilenet_v1_voc_prune_l1_norm.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/slim/prune/yolov3_prune_l1_norm.yml) | | YOLOv3-MobileNetV1 | 剪裁-l1_norm(sensity) | 15.78(-34.49%) | 66(-29%) | 608 | - | 77.6(+2.5) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_voc_prune_l1_norm.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/slim/prune/yolov3_prune_l1_norm.yml) |
### 量化 ### 量化
...@@ -24,10 +24,10 @@ ...@@ -24,10 +24,10 @@
| 模型 | 压缩策略 | 输入尺寸 | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 | | 模型 | 压缩策略 | 输入尺寸 | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| ------------------ | ------------ | -------- | :---------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | ------------------ | ------------ | -------- | :---------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| YOLOv3-MobileNetV1 | baseline | 608 | 28.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | - | | YOLOv3-MobileNetV1 | baseline | 608 | 28.8 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | - |
| YOLOv3-MobileNetV1 | 普通在线量化 | 608 | 27.5 (-1.3) | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/slim/yolov3_mobilenet_v1_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/quant/yolov3_mobilenet_v1_qat.yml) | | YOLOv3-MobileNetV1 | 普通在线量化 | 608 | 27.5 (-1.3) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/slim/quant/yolov3_mobilenet_v1_qat.yml) |
| YOLOv3-MobileNetV3 | baseline | 608 | 31.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | - | | YOLOv3-MobileNetV3 | baseline | 608 | 31.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | - |
| YOLOv3-MobileNetV3 | PACT在线量化 | 608 | 29.0 (-2.4) | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/slim/yolov3_mobilenet_v3_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/quant/yolov3_mobilenet_v3_qat.yml) | | YOLOv3-MobileNetV3 | PACT在线量化 | 608 | 29.0 (-2.4) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v3_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/slim/quant/yolov3_mobilenet_v3_qat.yml) |
- SD855预测时延为使用PaddleLite部署,使用arm8架构并使用4线程(4 Threads)推理时延 - SD855预测时延为使用PaddleLite部署,使用arm8架构并使用4线程(4 Threads)推理时延
......
...@@ -19,8 +19,8 @@ SOLOv2 (Segmenting Objects by Locations) is a fast instance segmentation framewo ...@@ -19,8 +19,8 @@ SOLOv2 (Segmenting Objects by Locations) is a fast instance segmentation framewo
| BlendMask | R50-FPN | True | 3x | 37.8 | 13.5 | V100 | - | - | | BlendMask | R50-FPN | True | 3x | 37.8 | 13.5 | V100 | - | - |
| SOLOv2 (Paper) | R50-FPN | False | 1x | 34.8 | 18.5 | V100 | - | - | | SOLOv2 (Paper) | R50-FPN | False | 1x | 34.8 | 18.5 | V100 | - | - |
| SOLOv2 (Paper) | X101-DCN-FPN | True | 3x | 42.4 | 5.9 | V100 | - | - | | SOLOv2 (Paper) | X101-DCN-FPN | True | 3x | 42.4 | 5.9 | V100 | - | - |
| SOLOv2 | R50-FPN | False | 1x | 35.5 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/solov2_r50_fpn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/solov2_r50_fpn_1x_coco.yml) | | SOLOv2 | R50-FPN | False | 1x | 35.5 | 21.9 | V100 | [model](https://paddledet.bj.bcebos.com/models/solov2_r50_fpn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/solov2_r50_fpn_1x_coco.yml) |
| SOLOv2 | R50-FPN | True | 3x | 37.9 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/solov2_r50_fpn_3x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/solov2_r50_fpn_3x_coco.yml) | | SOLOv2 | R50-FPN | True | 3x | 38.0 | 21.9 | V100 | [model](https://paddledet.bj.bcebos.com/models/solov2_r50_fpn_3x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/solov2_r50_fpn_3x_coco.yml) |
**Notes:** **Notes:**
......
...@@ -6,8 +6,8 @@ ...@@ -6,8 +6,8 @@
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 | | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 |
| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| VGG | SSD | 8 | 240e | ---- | 78.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/ssd_vgg16_300_240e_voc.yml) | | VGG | SSD | 8 | 240e | ---- | 78.2 | [下载链接](https://paddledet.bj.bcebos.com/models/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/ssd_vgg16_300_240e_voc.yml) |
| MobileNet v1 | SSD | 32 | 120e | ---- | 73.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_mobilenet_v1_300_120e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) | | MobileNet v1 | SSD | 32 | 120e | ---- | 73.3 | [下载链接](https://paddledet.bj.bcebos.com/models/ssd_mobilenet_v1_300_120e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) |
**注意:** SSD-VGG使用4GPU在总batch size为32下训练240个epoch。SSD-MobileNetv1使用2GPU在总batch size为64下训练120周期。 **注意:** SSD-VGG使用4GPU在总batch size为32下训练240个epoch。SSD-MobileNetv1使用2GPU在总batch size为64下训练120周期。
......
...@@ -13,7 +13,7 @@ TTFNet是一种用于实时目标检测且对训练时间友好的网络,对Ce ...@@ -13,7 +13,7 @@ TTFNet是一种用于实时目标检测且对训练时间友好的网络,对Ce
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 | | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 |
| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| DarkNet53 | TTFNet | 12 | 1x | ---- | 33.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ttfnet_darknet53_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ttfnet/ttfnet_darknet53_1x_coco.yml) | | DarkNet53 | TTFNet | 12 | 1x | ---- | 33.5 | [下载链接](https://paddledet.bj.bcebos.com/models/ttfnet_darknet53_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ttfnet/ttfnet_darknet53_1x_coco.yml) |
## Citations ## Citations
``` ```
......
...@@ -237,8 +237,6 @@ class CascadeHead(BBoxHead): ...@@ -237,8 +237,6 @@ class CascadeHead(BBoxHead):
clip_box = clip_bbox(boxes_per_image, im_shape[i]) clip_box = clip_bbox(boxes_per_image, im_shape[i])
if self.training: if self.training:
keep = nonempty_bbox(clip_box) keep = nonempty_bbox(clip_box)
if keep.shape[0] == 0:
continue
clip_box = paddle.gather(clip_box, keep) clip_box = paddle.gather(clip_box, keep)
rois.append(clip_box) rois.append(clip_box)
rois_num = paddle.concat([paddle.shape(r)[0] for r in rois]) rois_num = paddle.concat([paddle.shape(r)[0] for r in rois])
......
Markdown is supported
0% .
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