Skip to content
Snippets Groups Projects
Unverified Commit 58d7bc85 authored by Haian Huang(深度眸)'s avatar Haian Huang(深度眸) Committed by GitHub
Browse files

Update pre-train model URL(faster rcnn and mask rcnn) (#4307) 

* FPN deprecated warning

* FPN deprecated warning

* Update pretrain model url

* Fix pretrain model base url

* Add specific class pre-trained models

* Fix isort error

* Update doc description

* Update model url

* Rename config

* Rename config
parent 6eb3aad0
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Showing
with 30 additions and 5 deletions
configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py
+ 1
− 1
View file @ 58d7bc85
......@@ -35,4 +35,4 @@ lr_config = dict(
total_epochs = 8 # actual epoch = 8 * 8 = 64
log_config = dict(interval=100)
# For better, more stable performance initialize from COCO
load_from = 'https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth' # noqa
load_from = 'https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth' # noqa
configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py
+ 1
− 1
View file @ 58d7bc85
......@@ -42,4 +42,4 @@ lr_config = dict(
total_epochs = 8 # actual epoch = 8 * 8 = 64
log_config = dict(interval=100)
# For better, more stable performance initialize from COCO
load_from = 'https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth' # noqa
load_from = 'https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth' # noqa
configs/faster_rcnn/README.md
+ 9
− 2
View file @ 58d7bc85
......@@ -48,5 +48,12 @@ We also train some models with longer schedules and multi-scale training. The us
| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: |
| [R-50-DC5](./faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py) | caffe | 1x | - | | 37.4 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco_20201028_233851-b33d21b9.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco_20201028_233851.log.json)
| [R-50-DC5](./faster_rcnn_r50_caffe_dc5_mstrain_3x_coco.py) | caffe | 3x | - | | 38.7 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco_20201028_002107-34a53b2c.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco_20201028_002107.log.json)
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco.py) | caffe | 2x | 4.3 | | 39.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco_bbox_mAP-0.397_20200504_231813-10b2de58.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco_20200504_231813.log.json)
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py) | caffe | 3x | 4.3 | | 40.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20200504_163323.log.json)
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py) | caffe | 2x | 4.3 | | 39.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco_bbox_mAP-0.397_20200504_231813-10b2de58.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco_20200504_231813.log.json)
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | caffe | 3x | 4.3 | | 40.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20200504_163323.log.json)
We further finetune some pre-trained models on the COCO subsets, which only contain only a few of the 80 categories.
| Backbone | Style | Class name | Pre-traind model | Mem (GB) | box AP | Config | Download |
| ------------------------------------------------------------ | ----- | ------------------ | ------------------------------------------------------------ | -------- | ------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person.py) | caffe | person | [R-50-FPN-Caffe-3x](./faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | 3.7 | 55.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/faster_rcnn_r50_fpn_1x_coco-person_20201216_175929-d022e227.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/faster_rcnn_r50_fpn_1x_coco-person_20201216_175929.log.json) |
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person-bicycle-car.py) | caffe | person-bicycle-car | [R-50-FPN-Caffe-3x](./faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | 3.7 | 44.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car_20201216_173117-6eda6d92.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car_20201216_173117.log.json) |
configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car.py → configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person-bicycle-car.py
+ 9
− 0
View file @ 58d7bc85
_base_ = './faster_rcnn_r50_fpn_1x_coco.py'
_base_ = './faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py'
model = dict(roi_head=dict(bbox_head=dict(num_classes=3)))
classes = ('person', 'bicycle', 'car')
data = dict(
train=dict(classes=classes),
val=dict(classes=classes),
test=dict(classes=classes))
# TODO: Update model url after bumping to V2.0
load_from = 'https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth' # noqa
load_from = 'http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth' # noqa
configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person.py → configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person.py
+ 9
− 0
View file @ 58d7bc85
_base_ = './faster_rcnn_r50_fpn_1x_coco.py'
_base_ = './faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py'
model = dict(roi_head=dict(bbox_head=dict(num_classes=1)))
classes = ('person', )
data = dict(
train=dict(classes=classes),
val=dict(classes=classes),
test=dict(classes=classes))
load_from = 'http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth' # noqa
docs/tutorials/finetune.md
+ 1
− 1
View file @ 58d7bc85
......@@ -84,6 +84,6 @@ log_config = dict(interval=100)
To use the pre-trained model, the new config add the link of pre-trained models in the `load_from`. The users might need to download the model weights before training to avoid the download time during training.
```python
load_from = 'https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_2x_20181010-41d35c05.pth' # noqa
load_from = 'http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth' # noqa
```
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment