update for new version of torch

MorvanZhou · MorvanZhou · commit 3e2d0b8a4079 · 2018-11-13T10:26:34.000+08:00
diff --git a/tutorial-contents-notebooks/502_GPU.ipynb b/tutorial-contents-notebooks/502_GPU.ipynb
@@ -213,7 +213,7 @@
     "            # !!!!!!!! Change in here !!!!!!!!! #\n",
     "            pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze()  # move the computation in GPU\n",
     "\n",
-    "            accuracy = sum(pred_y == test_y) / test_y.size(0)\n",
+    "            accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)\n",
     "            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)\n"
    ]
   },

Original file line number	Diff line number	Diff line change
`@@ -213,7 +213,7 @@`
`213`	`213`	`" # !!!!!!!! Change in here !!!!!!!!! #\n",`
`214`	`214`	`" pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze() # move the computation in GPU\n",`
`215`	`215`	`"\n",`
`216`		`- " accuracy = sum(pred_y == test_y) / test_y.size(0)\n",`
	`216`	`+ " accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)\n",`
`217`	`217`	`" print('Epoch: ', epoch, '\| train loss: %.4f' % loss.data[0], '\| test accuracy: %.2f' % accuracy)\n"`
`218`	`218`	`]`
`219`	`219`	`},`