Update SVTR Tiny Model #486
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
hadipash
reviewed
Jul 6, 2023
hadipash
approved these changes
Jul 10, 2023
HaoyangLee
reviewed
Jul 11, 2023
| @@ -38,7 +38,7 @@ According to our experiments, the evaluation results on public benchmark dataset | |||
|
|
|||
| | **Model** | **Context** | **Avg Accuracy** | **Train T.** | **FPS** | **Recipe** | **Download** | | |||
| | :-----: | :-----------: | :--------------: | :----------: | :--------: | :--------: |:----------: | | |||
| | SVTR-Tiny | D910x4-MS1.10-G | 89.02% | 4866 s/epoch | 2968 | [yaml](https://github.com/mindspore-lab/mindocr/blob/main/configs/rec/svtr/svtr_tiny.yaml) | [ckpt](https://download.mindspore.cn/toolkits/mindocr/svtr/svtr_tiny-8542b3bb.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/svtr/svtr_tiny-8542b3bb-5cf5a130.mindir) | | |||
| | SVTR-Tiny | D910x4-MS1.10-G | 90.23% | 3638 s/epoch | 4560 | [yaml](https://github.com/mindspore-lab/mindocr/blob/main/configs/rec/svtr/svtr_tiny.yaml) | [ckpt](https://download.mindspore.cn/toolkits/mindocr/svtr/svtr_tiny-950be1c3.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/svtr/svtr_tiny-950be1c3-86ece8c8.mindir) | | |||
There was a problem hiding this comment.
After the PR is merging, ask @jianyunchao to delete the former ckpt/mindir files in https://download.mindspore.cn/toolkits/mindocr/svtr/
configs/rec/svtr/README.md
Outdated
| │ ├── data.mdb | ||
| │ └── lock.mdb | ||
| └── validation | ||
| ├── data.mdb | ||
| └── lock.mdb | ||
| ``` | ||
|
|
||
| #### 3.1.3 Dataset Usage | ||
|
|
||
| Here we used the datasets under `training/` folders for training, and the union dataset `validation/` for validation. After training, we used the datasets under `evaluation/` to evaluate model accuracy. | ||
|
|
||
| **Training:** (total 14,442,049 samples) |
There was a problem hiding this comment.
Since the ST dataset size is changed, the number of total training samples should also change?
|
Nice work. What leads to the FPS improved from 2968 to 4560? |
Not very sure. Seems removing some long text sample will be helpful. (CTC loss has max. length limit, too.long image will not contributed to the loss value but still cost some time in the previous setting) |
HaoyangLee
approved these changes
Jul 12, 2023
| scale_img = cv2.pyrDown(scale_img) | ||
| scale_img = cv2.resize(scale_img, (src_w, src_h), interpolation=get_interpolation()) | ||
| return scale_img | ||
|
|
||
|
|
||
| class CVGaussianNoise(object): | ||
| def __init__(self, mean=0, var=20): | ||
| def __init__(self, mean=0, varience=20): |
There was a problem hiding this comment.
Suggested change
| def __init__(self, mean=0, varience=20): | |
| def __init__(self, mean=0, variance=20): |
Do you mean variance? Same in class SVTRDeterioration
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.
__call__instead of__init__nn.Dropoutandms_functionThank 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)