[Fix] Align GreedyNAS retraining details with huangtao's code #1
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
2. update lr config to align lr curve with huangtao 3. IterBasedRunner -> EpochBaseRunner
2. fix the rand-m9-mstd-0.5 config in mmcls style 3. training with full imagenet
2. align init_cfg 3. add default mutable_cfg 4. eval and save ckpt by epoch
humu789
reviewed
Apr 26, 2022
| optimizer = dict( | ||
| type='RMSpropTF', | ||
| lr=0.048, | ||
| eps=0.001, | ||
| weight_decay=1e-5, | ||
| momentum=0.9, | ||
| filter_bias_and_bn=True) |
There was a problem hiding this comment.
params = _add_weight_decay(model, lr, weight_decay)
weight_decay = 0
humu789
reviewed
Apr 26, 2022
| @@ -5,28 +5,27 @@ | |||
| ] | |||
|
|
|||
| init_cfg = [ | |||
| dict(type='FanOutNormal', layer=['Conv2d']), | |||
There was a problem hiding this comment.
nn.init.kaiming_uniform_(m.weight, mode='fan_in', nonlinearity='linear')
humu789
pushed a commit
that referenced
this pull request
Feb 13, 2023
* add function marker and model extractor * add fsaf split & partial mask rcnn split, import extract.py * 1. add value renaming 2. add apply_marks in config to turn on/off marks * rewind changes on pytorch2onnx.py Co-authored-by: q.yao <[email protected]>
humu789
pushed a commit
that referenced
this pull request
Feb 13, 2023
Co-authored-by: Yifan Zhou <[email protected]> Co-authored-by: lvhan028 <[email protected]> Co-authored-by: Yifan Zhou <[email protected]> Co-authored-by: lvhan028 <[email protected]>
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Outdated suggestions cannot be applied.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.
Motivation
There are some inconsistencies with Huang Tao's code, and I fixed them in this PR.
Modification
RMSPropTFtoOPTIMIZERand remove the hard code in the train api.lr_config.GlobalAveragePooling)init_cfgwith huangtaorand-m9-mstd-0.5config in mmcls style