Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

自己寫的 generate_classification_dataset 訓練效果很差 #17

Closed
jacky10001 opened this issue Jan 28, 2022 · 0 comments · Fixed by #33
Closed

自己寫的 generate_classification_dataset 訓練效果很差 #17

jacky10001 opened this issue Jan 28, 2022 · 0 comments · Fixed by #33
Labels
非預期結果 沒有異常錯誤訊息，但不符合預期功能

Comments

@jacky10001
Copy link
Owner

jacky10001 commented Jan 28, 2022 •
edited
Loading

跟官方的 tf.data.Dataset 相比，分類模型準確度非常不好
@jacky10001 jacky10001 added 資料集 非預期結果 沒有異常錯誤訊息，但不符合預期功能 and removed 資料處理 labels Jan 28, 2022
@jacky10001 jacky10001 mentioned this issue Jan 30, 2022
Closed
jacky10001 pushed a commit that referenced this issue Jan 31, 2022
@ioplab
Close #17
46e3681
@jacky10001 jacky10001 mentioned this issue Jan 31, 2022
Merged
jacky10001 added a commit that referenced this issue Jan 31, 2022
@jacky10001
資料擴增開發 (#33)
f6dbcfb 
* fixed #31
* Close #17

根據8ecf7db來驗證不使用資料擴增時，可以訓練至正常該有準確度
jacky10001 added a commit that referenced this issue Feb 2, 2022
@jacky10001
資料擴增開發 (#35)
8cd90db 
* Fixed #31、Close #17
驗證不使用資料擴增時，可以訓練至正常該有準確度

* 修正無拆分模式的錯誤

* 目前在alexnet測試資料擴增所造成的影響，訓練過程之曲線提升較為穩定
驗證曲線雖然震盪較大，但與訓練曲線差異也減少許多，使訓練時間延長，減緩過擬合提早發生
但使用過多資料擴增的手段或是變化太大，使資料之間差異度過大，反而無法有效學習
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
非預期結果 沒有異常錯誤訊息，但不符合預期功能
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

資料擴增開發 jacky10001/tf2-mycnn
1 participant
@jacky10001