Accuracy stops increasing at around 82%

Rishav_Sen · December 30, 2021, 3:10am

I was wondering how I should weight the data as my accuracy stops at around 82%.

Test Classes Actual: [138, 156, 407, 450, 9334, 2192, 12087, 987, 828]
Test Classes Classified by Model: [81, 16, 252, 12, 9069, 0, 15339, 982, 0]

How should I weight the values, because when I make the weights all equal, I get this?

Test Classes Classified by Model: [430, 141, 934, 912, 6619, 7395, 8332, 1050, 0]

Any help would be appreciated.

Thanks,
Rishav

Renu_Patel · September 9, 2023, 11:17am

Welcome to the TensorFlow Forum!

The given information is not sufficient to understand the issue. Please provide minimal reproducible code to replicate the error.

Topic		Replies	Views
Low accuracy on a classification model General Discussion model , accuracy , classification	4	117	June 6, 2024
Not getting Accuracy while retraining the model General Discussion models , keras	3	399	October 9, 2023
The accuracy do not increase when I train model General Discussion models , keras , help_request	2	985	February 20, 2023
Tensorflow2.6 accuracy lower than Tensorflow2.0 General Discussion models , training , help_request	1	1080	September 9, 2022
Validation loss keeps increasing even though accuracy levels out General Discussion validation , accuracy	1	101	May 24, 2024