Hello. The classification model from the api and end2end notebook are multiclass classification model instead of binary classification model.
To get the binary classification model, I have to change the output number of the Dense layer of default classification model.
How could I do to adjust the output of the predictions layer (Dense ayer) from 2 to 1 and append the Sigmoid activation function ?
Can you run with tao_api_starter_kit/api/automl/classification.ipynb ?
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
Changing does not work since it is using softmax.
system
May 18, 2023, 7:46am
6
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.
