-
Notifications
You must be signed in to change notification settings - Fork 2.6k
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.
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
[Feature] Support FastFCN #885
Conversation
Codecov Report
@@ Coverage Diff @@
## master #885 +/- ##
==========================================
+ Coverage 89.77% 89.83% +0.06%
==========================================
Files 116 117 +1
Lines 6511 6555 +44
Branches 1011 1019 +8
==========================================
+ Hits 5845 5889 +44
Misses 463 463
Partials 203 203
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
configs/fastfcn/fastfcn-jpu_deeplabv3_512x1024_80k_cityscapes.py
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please rename all the config names accordingly.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, please also resolve the comment.
d604b0b
to
b1d8281
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Please resolve the conflict.
* FastFCN first commit * FastFCN first commit * Fixing lint error * Fixing lint error * use for loop on JPU * Use For Loop * Refactor FastFCN * FastFCN * FastFCN * temp * Uploading models & logs (4x4) * Fixing typos * fix typos * rename config * change README.md * use _delete_=True * change configs * change start_level to 0 * change start_level to 0 * jpu * add unittest for start_level!=0
* add default test and train args * remove partition field from default args to the parser * fix typo in config * fix typo in model list
[fix] Correct the key name of ‘eval_results’ dictionary for metric 'mmit_mean_average_precision'
Introduction
Support an interesting algorithm which could use smaller feature map getting good results with less computation (FLOPs), FastFCN: Rethinking Dilated Convolution in the Backbone for SemanticSegmentation.
Original Repo: https://github.com/wuhuikai/FastFCN
Its framework is shown as below:
And core novelty of it is Joint Pyramid Upsampling (JPU):
Modification
Current results on Cityscapes using MMSegmentation are below:
Future work
TO DO:
(Optional) Results on ADE20K and Pascal Context.