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.

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

Cgnet #107

Closed
wants to merge 2 commits into from
Closed

Cgnet #107

wants to merge 2 commits into from

Conversation

KID-7391
Copy link
Contributor

@KID-7391 KID-7391 commented Sep 5, 2020

No description provided.

@CLAassistant
Copy link

CLAassistant commented Sep 5, 2020

CLA assistant check
All committers have signed the CLA.

@codecov
Copy link

codecov bot commented Sep 5, 2020

Codecov Report

Merging #107 into master will increase coverage by 0.30%.
The diff coverage is 86.55%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #107      +/-   ##
==========================================
+ Coverage   81.34%   81.65%   +0.30%     
==========================================
  Files          79       83       +4     
  Lines        3597     3832     +235     
  Branches      565      611      +46     
==========================================
+ Hits         2926     3129     +203     
- Misses        560      578      +18     
- Partials      111      125      +14     
Flag Coverage Δ
#unittests 81.65% <86.55%> (+0.30%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmseg/models/utils/make_divisible.py 57.14% <57.14%> (ø)
mmseg/models/backbones/mobilenet_v2.py 76.85% <76.85%> (ø)
mmseg/models/backbones/cgnet.py 96.22% <96.22%> (ø)
mmseg/__init__.py 73.68% <100.00%> (ø)
mmseg/models/backbones/__init__.py 100.00% <100.00%> (ø)
mmseg/models/decode_heads/__init__.py 100.00% <100.00%> (ø)
mmseg/models/decode_heads/cg_head.py 100.00% <100.00%> (ø)
mmseg/models/utils/__init__.py 100.00% <100.00%> (ø)
... and 2 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 3c6dd9e...691cbff. Read the comment docs.

@xvjiarui
Copy link
Collaborator

xvjiarui commented Sep 6, 2020

Hi @KID-7391
Could you please sign CLA?


# stage 1
self.level1 = nn.ModuleList()
for i in range(0, num_blocks[0]):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
for i in range(0, num_blocks[0]):
for i in range(num_blocks[0]):

Comment on lines +162 to +165
num_channels=[32, 64, 128],
num_blocks=[3, 21],
dilation=[2, 4],
reduction=[8, 16],
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Use tuple instead.

out_channels (int): Number of output feature channels.
dilation (int): Dilation rate for surrounding context extractor.
reduction (int): Reductions for global context extractor.
add (bool): Add input to output or not.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Use more readable names like skip_connect or use_residual.

dilation (int): Dilation rate for surrounding context extractor.
reduction (int): Reductions for global context extractor.
add (bool): Add input to output or not.
down (bool): Downsample the input to 1/2 or not.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
down (bool): Downsample the input to 1/2 or not.
downsample (bool): Downsample the input to 1/2 or not.

norm_cfg=norm_cfg,
act_cfg=act_cfg)

self.F_loc = build_conv_layer(
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

F_loc rename.

@Junjun2016 Junjun2016 closed this Jul 4, 2021
wjkim81 pushed a commit to wjkim81/mmsegmentation that referenced this pull request Dec 3, 2023
sibozhang pushed a commit to sibozhang/mmsegmentation that referenced this pull request Mar 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants