-
Notifications
You must be signed in to change notification settings - Fork 64
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.
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
how to predict by trained model? #23
Comments
np.argmax(embedded_features[0]) - > Class label |
this is class feature, not class probability |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
cosface_model = load_model('models/attention_vgg8_cosface_3d/model.hdf5', custom_objects={'CosFace': CosFace}) cosface_model = Model(inputs=cosface_model.input[0], outputs=cosface_model.layers[-3].output) cosface_features = cosface_model.predict(X_test, verbose=1) cosface_features /= np.linalg.norm(cosface_features, axis=1, keepdims=True)
as far as i know, cosface_features is 3d-coordinate for each cls, how to get a result when set a input. when 10-cls like mnist, output will be [*, 10]
The text was updated successfully, but these errors were encountered: