fix channel mismatch in new_model.py when i==1 #47
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
JingweiZhang12
commented
Sep 17, 2019
JingweiZhang12
commented
- discard useless parameter 'criterion' in Class newModel
- fix channel mismatch in new_model.py when i==1
- change the default cityscapes epoch to 90
- remove args.gpu_ids, replace the 'len(agrs.gpu_ids)' by 'torch.cuda.device_count()'
- some parameters changes considering practical training, not matter
1. fix the error: only 11 layers are passed 2.Set cudnn.bechmark for slightly speeding up. 3. Remove unused argument. 4. epoch 0~19 train weights only and epoch 20~39 train both weights and archs.
update from original repo
fix channel mismatch by add self._filter_multiplier * filter_param_dict[prev_level] in new_model
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Outdated suggestions cannot be applied.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.