Commit dbe154a

authored

Merge pull request MorvanZhou#106 from changmeen/master

Update 504_batch_normalization.ipynb

2 parents 57aaef8 + 8c57548 commit dbe154aCopy full SHA for dbe154a

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
`@@ -96,7 +96,7 @@`
`96`	`96`	`"test_x = Variable(torch.from_numpy(test_x).float(), volatile=True) # not for computing gradients\n",`
`97`	`97`	`"test_y = Variable(torch.from_numpy(test_y).float(), volatile=True)\n",`
`98`	`98`	`"\n",`
`99`		`- "train_dataset = Data.TensorDataset(data_tensor=train_x, target_tensor=train_y)\n",`
	`99`	`+ "train_dataset = Data.TensorDataset(train_x, train_y)\n",`
`100`	`100`	`"train_loader = Data.DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)\n",`
`101`	`101`	`"\n",`
`102`	`102`	`"# show data\n",`
`@@ -274,7 +274,7 @@`
`274`	`274`	`" for net, l in zip(nets, losses):\n",`
`275`	`275`	`" net.eval() # set eval mode to fix moving_mean and moving_var\n",`
`276`	`276`	`" pred, layer_input, pre_act = net(test_x)\n",`
`277`		`- " l.append(loss_func(pred, test_y).data[0])\n",`
	`277`	`+ " l.append(loss_func(pred, test_y).data)\n",`
`278`	`278`	`" layer_inputs.append(layer_input)\n",`
`279`	`279`	`" pre_acts.append(pre_act)\n",`
`280`	`280`	`" net.train() # free moving_mean and moving_var\n",`

Comments

(0)