Open jeffreydiament95 opened 1 year ago
I got the sample issue, I don't make sense why? this software upgraded?
There appears to have been an API change to HistogramWrapper. It's Return type is now a capsa.RiskTensor containing both the predicted y_hat (tf.Tensor) and the bias value for each input sample (tf.Tensor).
Here want I did to fix up the code...
# Call the risk-aware model to generate scores
#predictions, bias = bias_wrapped_dense_NN(x_test)
prediction = bias_wrapped_dense_NN(x_test)
bias = prediction.bias # fix up
I'll take a try, thanks.
When running the source code without any modifications, I get the following error:
ValueError Traceback (most recent call last) in <cell line: 4>()
2
3 # Call the risk-aware model to generate scores
----> 4 predictions, bias = bias_wrapped_dense_NN(x_test)
5
6 # Visualize the relationship between the input data x and the bias
ValueError: too many values to unpack (expected 2)