Update ImageNet training code #16
Merged
Conversation
This file contains hidden or 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
Member
colesbury
commented
Dec 2, 2016
colesbury
commented
- add learning rate schedule and weight decay
- checkpointing
- use pinned memory in data loader
- don't use Trainer API for now
- add learning rate schedule and weight decay - checkpointing - use pinned memory in data loader - don't use Trainer API for now
soumith
approved these changes
Dec 2, 2016
| batch_size=args.batch_size, shuffle=False, | ||
| num_workers=args.workers, pin_memory=True) | ||
|
|
||
| # parallelize model across all visible GPUs |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
| model = torch.nn.DataParallel(model) | ||
|
|
||
| # define loss function (criterion) and pptimizer | ||
| criterion = nn.CrossEntropyLoss().cuda() |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
| def adjust_learning_rate(optimizer, epoch): | ||
| """Sets the learning rate to the initial LR decayed by 10 every 30 epochs""" | ||
| lr = args.lr * (0.1 ** (epoch // 30)) | ||
| for param_group in optimizer.state_dict()['param_groups']: |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
| @@ -114,7 +114,7 @@ def _make_layer(self, block, planes, blocks, stride=1): | |||
|
|
|||
| layers = [] | |||
| layers.append(block(self.inplanes, planes, stride, downsample)) | |||
| self.inplanes = planes * block.expansion | |||
| self.inplanes = planes * block.expansion | |||
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
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.