Outputs not matching on newer versions of numpy.

[ThomAbe]

Using version 1.21.0 of numpy the outputs do not match the outputs from the book. I was able to rectify this issue by finding the version you used the first video on the companion series on your Youtube channel version 1.18.2. I am not sure if you would want to add a comment on the readme, update the outputs, or update the nnfs package to work with the newer version. Adding it to the readme would be the least maintenance in the future.

[jayteaftw]

In chapter 9, I am getting the right loss and accuracy values but when I print out the loss_activation.output[:5] and the dweights and dbiases, I get the wrong values.

Here is my output
[[0.33333334 0.33333334 0.33333334]
[0.3333332 0.3333332 0.33333364]
[0.3333329 0.33333293 0.3333342 ]
[0.3333326 0.33333263 0.33333477]
[0.33333233 0.3333324 0.33333528]]
loss: 1.0986104
acc: 0.34
[[ 1.5766357e-04 7.8368583e-05 4.7324400e-05]
[ 1.8161038e-04 1.1045573e-05 -3.3096312e-05]]
[[-3.60553473e-04 9.66117223e-05 -1.03671395e-04]]
[[ 5.44109462e-05 1.07411419e-04 -1.61822361e-04]
[-4.07913431e-05 -7.16780924e-05 1.12469446e-04]
[-5.30112993e-05 8.58172934e-05 -3.28059905e-05]]
[[-1.0729185e-05 -9.4610732e-06 2.0027859e-05]]

I tried using the solution code from Github and I get the same output. I also did what you referenced above about changing the version of NumPy but I still get the same output.