Question in pyytorch result

1

how i get the classification result as percentage accuracy% and also as an image with CNN?

help me plzz

2

To get the accuracy you can first initialize a total and correct amount above your dataloader loop but below your epoch loop like this:

for e in epochs:
     total = 0.
     correct = 0.
     for data in dataloader:

then in the dataloader loop you can do this

    output = model(input)
    pred = output.data.max(1, keepdim=True)[1] 
    compare predictions to true label
    correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
    total += images.size(0)

and just print it out when you print out your loss by something like this

print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
        100. * correct / total, correct, total))

and I am not sure what you mean by the image with CNN. This is also assuming you are using softmax.

3

@Dwight_Foster hi, I want the classification result with CNN as an image (the result), is not fair I display the value of the accuracy