Plot the accuracy vs the params graph for the learning rate

[DantrazTrev]

No description provided.

[exoushia]

working on issue #6

I was debugging the code and trying to run the test database, and i ran into this error:
Traceback (most recent call last):
File "test.py", line 25, in
net.SGD(training_data, 30, 10, 3.0, test_data=test_data)
File "/home/mitushi/Desktop/kwoc/Neural-Networks/network.py", line 35, in SGD
self.update_mini_batch(mini_batch, eta)
File "/home/mitushi/Desktop/kwoc/Neural-Networks/network.py", line 45, in update_mini_batch
delta_nabla_b, delta_nabla_w,net = backprop(self,x, y)
File "/home/mitushi/Desktop/kwoc/Neural-Networks/backpropogation.py", line 17, in backprop
delta = net.cost_derivative(activations[-1], y) *
File "/home/mitushi/Desktop/kwoc/Neural-Networks/network.py", line 59, in cost_derivative
return (output_activations-y)
ValueError: operands could not be broadcast together with shapes (30,1) (10,1)

I guess there's a mismatch between the expected output shape and the shape of the database. How should i fix this?

[DantrazTrev]

I think the issue was in the way we were handling the network update in the backpropogation.py. I've tried to fix it, the issue was not intentional, you can check there is still an issue up which is unlisted

[DantrazTrev]

@exoushia I guess that issue has been solved now.