-
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
[New model] Support MobileNetV3 #268
Conversation
Codecov Report
@@ 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
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
I built the network the same as https://github.com/ekzhang/fastseg, but get a lower result as following:
I don't know why my training results are lower than original paper (about 5~6 points). |
Task linked: CU-fjq4w0 MobileNetV3 |
inputs = self._transform_inputs(inputs) | ||
|
||
x = inputs[-1] | ||
assert x.size(2) >= 49 and x.size(3) >= 49 |
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.
Why is 49?
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.
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.
We have to make sure that the input size is not less than 49.
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.
Will PyTorch raise the error if we don't assert? Or we may add comments here.
* 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
* 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>
* Protect against dangerous default value. * Added comments.
* make 'FrameSelector' registered * update changelog * update changelog * Update changelog.md
Reference: https://github.com/ekzhang/fastseg