support feature extraction of mindcv backbone: resnet and mobiletnet v3 #213
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
zhtmike
changed the title
|
由mindcv backbone 生成的model可能无法跟旧有的checkpoint兼容，因此不改动原有config配置。用mindcv backbone产生文件的实例可参考第一个commit |
SamitHuang
approved these changes
Apr 25, 2023
HaoyangLee
approved these changes
Apr 26, 2023
colawyee
pushed a commit
that referenced
this pull request
Jan 2, 2024
… pass on 910b (#213) * add script * Change softmax, sigmoid to compute in FP32, config lora scale for CLI * fix format * Update lora_finetune.md * add file * allow more config in args * lora finetune ok now on MS2.2.1.20231028+CANN-7.0.0.6.220 * sd1.5 vanilla train ok when all fusion pass off * rm debug log * fix format * allow upcate attention and sigmoid compute type to fp32 * fix format * del file * rename * fix typo --------- Co-authored-by: root <root@localhost.localdomain>
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Outdated suggestions cannot be applied.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.
Support intermediate feature extractions using backbones from mindcv (resnet and mobilenetv3).
It is migrated fro this PR
You need to add
features_onlyandout_indicesin backbone configuration, to extract the feature pyramid. The examples is shown in the modifieddb_r50_icdar15.yamlThank you for your contribution to the MindOCR repo.
Before submitting this PR, please make sure:
Motivation
(Write your motivation for proposed changes here.)
Test Plan
(How should this PR be tested? Do you require special setup to run the test or repro the fixed bug?)
Related Issues and PRs
(Is this PR part of a group of changes? Link the other relevant PRs and Issues here. Use https://help.github.com/en/articles/closing-issues-using-keywords for help on GitHub syntax)