release_note.md 1.9 KB
Newer Older
1 2 3 4 5 6 7
[toc]

## release note

- for convenient,I tag the version of the project (mainly on the client ) with data time
- the time(version) was create by powershell :

8 9 10 11 12 13 14 15 16 17 18 19
  - ```powershell
    Get-Date -Format "yyyy-MM-dd@HH:mm:ss"
    ```
  
  - copy to clipbord automatically
  
    ```bash
    Get-Date -Format "yyyy-MM-dd@HH:mm:ss"|scb
    ```
  
    
  
20 21 22 23
  

### versions with time

xuchaoxin1375's avatar
xuchaoxin1375 已提交
24 25 26 27 28 29
- **<u>input version under this line:</u>**
  - new notes:"Sort update records in descending order of time".That would be convenient to update new version notes in the future.
- 
- 2023-05-09@19:10:05
  - fix some bugs.
  - certain adjustments to the project code.
30

xuchaoxin1375's avatar
xuchaoxin1375 已提交
31 32 33
### old notes

- old notes:"Sort update records in ascending order of time".
34 35 36 37

- 2023-04-25@21:35:50
  - new:
    - update the layout of the client
38 39 40
    - use the table element to show "test_score","train_score" and "predict_proba" if it is usable
    - update the file viwer part function and operation logic with more flexibility.
  - kwon problems:
41 42 43 44 45 46 47
    - with the display or not display the predict_proba layout,the left column may need to resize the window to make the last part of view to visible!

- 2023-04-27@22:04:52
  - "update the client layout with more available parameters cross-validation(`kfold`/`shufflesplit`/`StratifiedShuffleSplit`)
  - support the `n_splits` as a slider element for use to adjust th
  - update the `confusion matrix table`show button 

48 49
- 2023-04-28@11:27:17
  - "update the make_window function in the ccser_client main file with more clear modular extraction"
xuchaoxin1375's avatar
xuchaoxin1375 已提交
50 51 52
- 2023-04-30@00:02:03
  - "update PCA transformer to the SER system"
  - "there are some problems with recognize the single audio with pca preprocessing,the idea is to save the pca transformer when it was first fited,and then try to load corresponding file(joblib or pickle) when you need to recognize several audios that need extract the required dimension feature"
xuchaoxin1375's avatar
xuchaoxin1375 已提交
53 54
-