[Feature] Support ICNet #863
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Closed
Codecov Report
@@ Coverage Diff @@
## master #863 +/- ##
==========================================
+ Coverage 89.02% 89.06% +0.03%
==========================================
Files 111 113 +2
Lines 6043 6147 +104
Branches 969 974 +5
==========================================
+ Hits 5380 5475 +95
- Misses 467 476 +9
Partials 196 196
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
|
Sources:
MMSegmentation:
|
|
Can find more results here. |
…nd (open-mmlab#867) * support load gt for evaluation from multi-backend * move some code from get_gt_seg_maps to get_one_gt_seg_map * rename gt_seg_map_loader_conf to gt_seg_map_loader_cfg * fix doc str * rename get_one_gt_seg_map to get_gt_seg_map_by_idx
* [Fix] Convert SyncBN to BN when training on DP. * Modify SyncBN2BN. * Add SyncBN2BN unit test. * Resolve some comments. * use mmcv official revert_sync_batchnorm * Remove local syncbn2bn unit tests. * Update mmcv version. * Fix bugs of gather model tools. * Modify warnings. * Modify docker mmcv version. * Update mmcv version table.
Junjun2016
commented
Sep 17, 2021
| @@ -0,0 +1,36 @@ | |||
| # Icnet for real-time semantic segmentation on high-resolution images | |||
There was a problem hiding this comment.
Suggested change
| # Icnet for real-time semantic segmentation on high-resolution images | |
| # ICNet for real-time semantic segmentation on high-resolution images |
Junjun2016
commented
Sep 17, 2021
|
|
||
| | Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download | | ||
| | ------ | ---------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ||
| | ICNet | R-18-D8 | 832x832 | 80000 | 1.87 | 40.66 | 66.92 | 69.43 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r18-d8_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json) | |
There was a problem hiding this comment.
Maybe we can Aevrage fps.
|
This PR is ended, please review new PR instead: #884 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Support ICNet