Commit 759aa01

authored

Merge pull request MorvanZhou#62 from keineahnung2345/502-squeeze

502 - remove squeeze for 1-D tensor

2 parents 818b4b4 + 5d6d4f0 commit 759aa01Copy full SHA for 759aa01

1 file changed

Lines changed: 2 additions & 2 deletions

File tree

Lines changed: 2 additions & 2 deletions

Original file line number	Diff line number	Diff line change
`@@ -68,7 +68,7 @@ def forward(self, x):`
`68`	`68`	`test_output = cnn(test_x)`
`69`	`69`
`70`	`70`	`# !!!!!!!! Change in here !!!!!!!!! #`
`71`		`- pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze() # move the computation in GPU`
	`71`	`+ pred_y = torch.max(test_output, 1)[1].cuda().data # move the computation in GPU`
`72`	`72`
`73`	`73`	`accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)`
`74`	`74`	`print('Epoch: ', epoch, '\| train loss: %.4f' % loss.data.cpu().numpy(), '\| test accuracy: %.2f' % accuracy)`
`@@ -77,7 +77,7 @@ def forward(self, x):`
`77`	`77`	`test_output = cnn(test_x[:10])`
`78`	`78`
`79`	`79`	`# !!!!!!!! Change in here !!!!!!!!! #`
`80`		`-pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze() # move the computation in GPU`
	`80`	`+pred_y = torch.max(test_output, 1)[1].cuda().data # move the computation in GPU`
`81`	`81`
`82`	`82`	`print(pred_y, 'prediction number')`
`83`	`83`	`print(test_y[:10], 'real number')`

Comments

(0)