You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As I see Capsa return a wrapped Tensor (<RiskTensor: shape=(500, 1), dtype=float32, risk=(bias,)>), wich wraps bias.
Should be something like prediction_wrap = bias_wrapped_dense_NN(x_test)
instead, e then use prediction_wrap.bias...
Note: if this is an intentional mistake, please excuse the issue
The text was updated successfully, but these errors were encountered:
I had the problem at first evaluation for the model, near the end of section
https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab3/Part1_IntroductionCapsa.ipynb#scrollTo=1_3_Evaluating_bias
As I see Capsa return a wrapped Tensor (
<RiskTensor: shape=(500, 1), dtype=float32, risk=(bias,)>
), wich wrapsbias
.Should be something like
prediction_wrap = bias_wrapped_dense_NN(x_test)
instead, e then use
prediction_wrap.bias
...Note: if this is an intentional mistake, please excuse the issue
The text was updated successfully, but these errors were encountered: