update

tutorial-contents/302_classification.py

@@ -63,7 +63,7 @@ for t in range(100):
         pred_y = prediction.data.numpy().squeeze()
         target_y = y.data.numpy()
         plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=pred_y, s=100, lw=0, cmap='RdYlGn')
-        accuracy = sum(pred_y == target_y)/200
+        accuracy = sum(pred_y == target_y)/200.
         plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color':  'red'})
         plt.pause(0.1)
 

tutorial-contents/401_CNN.py

@@ -98,7 +98,7 @@ for epoch in range(EPOCH):
         if step % 50 == 0:
             test_output = cnn(test_x)
             pred_y = torch.max(test_output, 1)[1].data.squeeze()
-            accuracy = sum(pred_y == test_y) / test_y.size(0)
+            accuracy = sum(pred_y == test_y) / float(test_y.size(0))
             print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)
 
 

tutorial-contents/402_RNN_classifier.py

@@ -97,7 +97,7 @@ for epoch in range(EPOCH):
         if step % 50 == 0:
             test_output = rnn(test_x)                   # (samples, time_step, input_size)
             pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
-            accuracy = sum(pred_y == test_y) / test_y.size
+            accuracy = sum(pred_y == test_y) / float(test_y.size)
             print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)
 
 # print 10 predictions from test data