Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add stdc benchmark & fix mask2former predict bug #286

Merged
merged 12 commits into from
Feb 17, 2023
Merged

Add stdc benchmark & fix mask2former predict bug #286

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
1cf2278
add stdc
haiasd Feb 14, 2023
fe39ff3
add stdc benchmark
haiasd Feb 15, 2023
5ba6572
Merge branch 'master' of github.com:alibaba/EasyCV into support_stdc
haiasd Feb 15, 2023
71d8d03
modify code style
haiasd Feb 15, 2023
bdd4075
add reference
haiasd Feb 15, 2023
efc0bd6
modify config
haiasd Feb 15, 2023
371244e
fix ut bug
haiasd Feb 15, 2023
8540e72
modify datasource
haiasd Feb 15, 2023
61ef32f
modify epoch
haiasd Feb 16, 2023
b8b2a20
Merge branch 'master' of github.com:alibaba/EasyCV into support_stdc
haiasd Feb 17, 2023
cccabbc
add stdc benchmark & fix mask2former predict bug
haiasd Feb 17, 2023
aa67d92
modify mask2former predict test
haiasd Feb 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/source/model_zoo_seg.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ trained on **Cityscapes**.
| Algorithm | Config | Params<br/>(backbone/total) | Train memory<br/>(GB) | inference time(V100)<br/>(ms/img) | mIoU | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| STDC1 | [stdc1_cityscape_8xb6_e1290](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/stdc/stdc1_cityscape_8xb6_e1290.py) | 7.7M/8.5M | 4.5 | 11.9ms | 75.4 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/stdc/stdc1_cityscapes/epoch_1250.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/stdc/stdc1_cityscapes/20230214_173123.log.json) |
| STDC2 | [stdc2_cityscape_8xb6_e1290](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/stdc/stdc2_cityscape_8xb6_e1290.py) | 11.6M/12.6M | 5.6 | 15.4ms | 76.6 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/stdc/stdc2_cityscapes/epoch_1280.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/stdc/stdc2_cityscapes/20230216_110522.log.json) |

## Mask2former

Expand Down
6 changes: 4 additions & 2 deletions easycv/predictors/segmentation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,9 +229,11 @@ def model_forward(self, inputs):
outputs = self.model.forward(**inputs, mode='test', encode=False)
return outputs

def show_panoptic(self, img, masks, labels):
def show_panoptic(self, img, masks, labels_ids, **kwargs):
palette = np.asarray(self.cfg.PALETTE)
palette = palette[labels % 1000]
# ids have already convert to label in process_single function
# palette = palette[labels_ids % 1000]
palette = palette[labels_ids]
panoptic_result = draw_masks(img, masks, palette)
return panoptic_result

Expand Down
10 changes: 2 additions & 8 deletions tests/predictors/test_segmentation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,10 +145,7 @@ def test_panoptic_single(self):
predict_out[0]['labels_ids'].tolist(),
[71, 69, 39, 39, 39, 128, 127, 122, 118, 115, 111, 104, 84, 83])

pan_img = predictor.show_panoptic(
img,
masks=predict_out[0]['masks'],
labels=predict_out[0]['labels_ids'])
pan_img = predictor.show_panoptic(img, **predict_out[0])
cv2.imwrite('pan_out.jpg', pan_img)

def test_panoptic_batch(self):
Expand All @@ -168,10 +165,7 @@ def test_panoptic_batch(self):
self.assertListEqual(predict_out[i]['labels_ids'].tolist(), [
71, 69, 39, 39, 39, 128, 127, 122, 118, 115, 111, 104, 84, 83
])
pan_img = predictor.show_panoptic(
img,
masks=predict_out[i]['masks'],
labels=predict_out[i]['labels_ids'])
pan_img = predictor.show_panoptic(img, **predict_out[i])
cv2.imwrite(save_name, pan_img)

def test_instance_single(self):
Expand Down