Same results for Classification models

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hi,
I am using tao-toolkit-tf:v3.22.05-tf1.15.5-py3
I trained classification models with same epochs and batch several times and the validation results for all models but EFFICIENTNET are the same.
For example the following is the classification report for the Darknet_19:

Classification Report
precision recall f1-score support

1 0.00 0.00 0.00 2
2 0.80 1.00 0.89 8

accuracy 0.80 10
macro avg 0.40 0.50 0.44 10
weighted avg 0.64 0.80 0.71 10

And this is for the GoogleNet:

Classification Report
precision recall f1-score support

1 0.00 0.00 0.00 2
2 0.80 1.00 0.89 8

accuracy 0.80 10
macro avg 0.40 0.50 0.44 10
weighted avg 0.64 0.80 0.71 10

3

Could you please use more images to run evaluation?

4

In another dataset I used 161 images to run evaluation, but the results were the same again.

5

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Please share full log and corresponding spec file for both experiments. Thanks a lot.

7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.