Roe

Change the line lstsq(A,b) to lstsq(A,b,rcond=None)

I see that the validation loss profile for the L2 regularized model peaks at around 0.4 in the figure while the standard model peaks at 0.8. The validation loss axis...

Thanks for pointing it out. I had to add: val_acc = history.history['val_acc'], just below line 3 ('val_acc_values=...') in Listing 3.10. I also added: acc=history.history['acc'] as Line 5 in Listing 3.9...

Thanks a lot for the pointers. Appreciated. Have a good day. On 5 Apr 2020 23:12, "Srinath Srinivasan" wrote: > Hey, for me it was solved by typing 'accuracy' instead...

It is still open because there are lots of us and new students who are struggling with coding (unlike you). Do not follow the thread if it is a waste...

Watch out for what? On 4 Sep 2020 17:02, "Aryan Choudhary" wrote: > bro the issue is solved above that's why I was saying that .... people > like without...

True that. I changed it in the hardcover version of the book and in my notes. Thanks.

Definitely axis 0 is specified. It should be (axis 1, the batch dimension, is unspecified...)

I had an issue with the second line there but my error was different : 'SyntaxError: positional argument follows keyword argument...'. I edited the line to: network.add(layers.Dense(512, input_shape=(28*28,), activation='relu')). After...

You do not need to explicitly downgrade Numpy. Use the following code to 'allow_pickle': `old = np.load, np.load = lambda *a, **k:old(*a, **k, allow_pickle=TRUE), from keras.datasets import mnist, np.load=old, del(old)`...