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

[New model] Support MobileNetV3 #268

Merged
merged 27 commits into from
Dec 26, 2020
Merged

[New model] Support MobileNetV3 #268

merged 27 commits into from
Dec 26, 2020

Conversation

yamengxi
Copy link
Collaborator

@yamengxi yamengxi commented Nov 19, 2020

@codecov
Copy link

codecov bot commented Nov 19, 2020

Codecov Report

Merging #268 (3cd6c00) into master (5dacca3) will increase coverage by 0.66%.
The diff coverage is 98.57%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #268      +/-   ##
==========================================
+ Coverage   85.80%   86.47%   +0.66%     
==========================================
  Files          92       95       +3     
  Lines        4552     4761     +209     
  Branches      724      765      +41     
==========================================
+ Hits         3906     4117     +211     
  Misses        499      499              
+ Partials      147      145       -2     
Flag Coverage Δ
unittests 86.47% <98.57%> (+0.66%) ⬆️

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 100.00% <ø> (+42.85%) ⬆️
mmseg/models/backbones/mobilenet_v3.py 97.47% <97.47%> (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/lraspp_head.py 100.00% <100.00%> (ø)
mmseg/models/utils/__init__.py 100.00% <100.00%> (ø)
mmseg/models/utils/inverted_residual.py 100.00% <100.00%> (+8.00%) ⬆️
mmseg/models/utils/se_layer.py 100.00% <100.00%> (ø)
... and 3 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 5dacca3...dab7273. Read the comment docs.

@yamengxi
Copy link
Collaborator Author

I built the network the same as https://github.com/ekzhang/fastseg, but get a lower result as following:

config mIoU(my result) mIoU(fastseg) mIoU(original paper)
configs/mobilenet_v3/lraspp_m-v3-d8_512x1024_160k_cityscapes.py 67.56 72.3 72.36
configs/mobilenet_v3/lraspp_m-v3s-d8_512x1024_160k_cityscapes.py 61.43 67.4 68.38

I don't know why my training results are lower than original paper (about 5~6 points).
Can anyone give me some advice and help?

@hellock
Copy link
Member

hellock commented Dec 16, 2020

Task linked: CU-fjq4w0 MobileNetV3

.gitignore Outdated Show resolved Hide resolved
inputs = self._transform_inputs(inputs)

x = inputs[-1]
assert x.size(2) >= 49 and x.size(3) >= 49
Copy link
Collaborator

Choose a reason for hiding this comment

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

Why is 49?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

It is proposed in the paper.
image

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

We have to make sure that the input size is not less than 49.

Copy link
Collaborator

Choose a reason for hiding this comment

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

Will PyTorch raise the error if we don't assert? Or we may add comments here.

@xvjiarui xvjiarui merged commit 7fdb400 into open-mmlab:master Dec 26, 2020
bowenroom pushed a commit to bowenroom/mmsegmentation that referenced this pull request Feb 25, 2022
* delete markdownlint

* Support MobileNetV3

* fix import

* add mobilenetv3 head and configs

* Modify MobileNetV3 to semantic segmentation version

* modify mobilenetv3 configs

* add std configs

* fix Conv2dAdaptivePadding bug

* add configs

* add unitest and fix bugs

* fix lraspp unitest bugs

* restore

* fix unitest

* add MobileNetV3 docstring

* add mmcv

* add mmcv

* fix syntax bug

* fix unitest bug

* fix unitest bug

* fix unitest bugs

* fix docstring

* add configs

* restore

* delete unnecessary assert

* modify unitest

* delete benchmark
aravind-h-v pushed a commit to aravind-h-v/mmsegmentation that referenced this pull request Mar 27, 2023
* update expected results of slow tests

* relax sum and mean tests

* Print shapes when reporting exception

* formatting

* fix sentence

* relax test_stable_diffusion_fast_ddim for gpu fp16

* relax flakey tests on GPU

* added comment on large tolerences

* black

* format

* set scheduler seed

* added generator

* use np.isclose

* set num_inference_steps to 50

* fix dep. warning

* update expected_slice

* preprocess if image

* updated expected results

* updated expected from CI

* pass generator to VAE

* undo change back to orig

* use orignal

* revert back the expected on cpu

* revert back values for CPU

* more undo

* update result after using gen

* update mean

* set generator for mps

* update expected on CI server

* undo

* use new seed every time

* cpu manual seed

* reduce num_inference_steps

* style

* use generator for randn

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
wjkim81 pushed a commit to wjkim81/mmsegmentation that referenced this pull request Dec 3, 2023
* Protect against dangerous default value.

* Added comments.
sibozhang pushed a commit to sibozhang/mmsegmentation that referenced this pull request Mar 22, 2024
* make 'FrameSelector' registered

* update changelog

* update changelog

* Update changelog.md
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.

3 participants