Deep Learning XOR Revisited Example

[smithjackson35]

I have looked over the code in the repository and still have not found a difference in my code that would cause it to break. I have reworked the entire chapter up to this point and still can not figure it out. Below is the error message and my code in its entirety is attached.

In [121]: with tqdm.trange(3000) as t: ...: for epoch in t: ...: epoch_loss = 0.0 ...: for x, y in zip(xs, ys): ...: predicted = net.forward(x) ...: epoch_loss += loss.loss(predicted, y) ...: gradient = loss.gradient(predicted, y) ...: net.backward(gradient) ...: optimizer.step(net) ...: t.set_description(f"xor loss {epoch_loss:.3f}") ...: 0%| | 0/3000 [00:00<?, ?it/s]

NotImplementedError Traceback (most recent call last) in 3 epoch_loss = 0.0 4 for x, y in zip(xs, ys): ----> 5 predicted = net.forward(x) 6 epoch_loss += loss.loss(predicted, y) 7 gradient = loss.gradient(predicted, y)

in forward(self, input) 10 """Just forward the input through the layers in order.""" 11 for layer in self.layers: ---> 12 input = layer.forward(input) 13 return input 14 def backward(self, gradient):

in forward(self, input) 6 Note the lack of types. We're not going to be perscriptive about what kinds of inputs layers can take and whats kinds of outputs they can return 7 """ ----> 8 raise NotImplementedError 9 def backward(self, gradient): 10 """

NotImplementedError: dsfs_deeplearningissue.txt

[smithjackson35]

I see where i defined some of the Linear class methods out side of the class block. I went back and correct that and still receive the same error