fix bug

code/chapter05_CNN/5.5_lenet.ipynb

@@ -12,8 +12,8 @@
    "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:36.424190Z",
-     "start_time": "2019-03-18T14:00:35.632104Z"
+     "end_time": "2019-05-29T13:57:37.383972Z",
+     "start_time": "2019-05-29T13:57:34.520559Z"
     }
    },
    "outputs": [
@@ -21,12 +21,13 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0.4.1\n",
+      "1.0.0\n",
       "cuda\n"
      ]
     }
    ],
    "source": [
+    "import os\n",
     "import time\n",
     "import torch\n",
     "from torch import nn, optim\n",
@@ -34,6 +35,8 @@
     "import sys\n",
     "sys.path.append(\"..\") \n",
     "import d2lzh_pytorch as d2l\n",
+    "\n",
+    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n",
     "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
     "\n",
     "print(torch.__version__)\n",
@@ -52,10 +55,9 @@
    "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:36.462703Z",
-     "start_time": "2019-03-18T14:00:36.425760Z"
-    },
-    "collapsed": true
+     "end_time": "2019-05-29T13:57:37.394997Z",
+     "start_time": "2019-05-29T13:57:37.386720Z"
+    }
    },
    "outputs": [],
    "source": [
@@ -89,8 +91,8 @@
    "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:36.469477Z",
-     "start_time": "2019-03-18T14:00:36.463753Z"
+     "end_time": "2019-05-29T13:57:37.450484Z",
+     "start_time": "2019-05-29T13:57:37.397357Z"
     }
    },
    "outputs": [
@@ -135,10 +137,9 @@
    "execution_count": 4,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:36.592065Z",
-     "start_time": "2019-03-18T14:00:36.470522Z"
-    },
-    "collapsed": true
+     "end_time": "2019-05-29T13:57:38.432567Z",
+     "start_time": "2019-05-29T13:57:37.452521Z"
+    }
    },
    "outputs": [],
    "source": [
@@ -151,10 +152,9 @@
    "execution_count": 5,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:36.625077Z",
-     "start_time": "2019-03-18T14:00:36.594327Z"
-    },
-    "collapsed": true
+     "end_time": "2019-05-29T13:57:38.442887Z",
+     "start_time": "2019-05-29T13:57:38.435111Z"
+    }
    },
    "outputs": [],
    "source": [
@@ -183,10 +183,9 @@
    "execution_count": 6,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:36.656988Z",
-     "start_time": "2019-03-18T14:00:36.628239Z"
-    },
-    "collapsed": true
+     "end_time": "2019-05-29T13:57:38.453480Z",
+     "start_time": "2019-05-29T13:57:38.445655Z"
+    }
    },
    "outputs": [],
    "source": [
@@ -195,22 +194,24 @@
     "    net = net.to(device)\n",
     "    print(\"training on \", device)\n",
     "    loss = torch.nn.CrossEntropyLoss()\n",
+    "    batch_count = 0\n",
     "    for epoch in range(num_epochs):\n",
     "        train_l_sum, train_acc_sum, n, start = 0.0, 0.0, 0, time.time()\n",
     "        for X, y in train_iter:\n",
     "            X = X.to(device)\n",
     "            y = y.to(device)\n",
     "            y_hat = net(X)\n",
-    "            l = loss(y_hat, y).sum()\n",
+    "            l = loss(y_hat, y)\n",
     "            optimizer.zero_grad()\n",
     "            l.backward()\n",
     "            optimizer.step()\n",
     "            train_l_sum += l.cpu().item()\n",
     "            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()\n",
     "            n += y.shape[0]\n",
+    "            batch_count += 1\n",
     "        test_acc = evaluate_accuracy(test_iter, net)\n",
     "        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec'\n",
-    "              % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc, time.time() - start))"
+    "              % (epoch + 1, train_l_sum / batch_count, train_acc_sum / n, test_acc, time.time() - start))"
    ]
   },
   {
@@ -218,8 +219,8 @@
    "execution_count": 7,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-03-18T14:00:48.824449Z",
-     "start_time": "2019-03-18T14:00:36.658020Z"
+     "end_time": "2019-05-29T13:58:00.333237Z",
+     "start_time": "2019-05-29T13:57:38.456012Z"
     }
    },
    "outputs": [
@@ -228,11 +229,11 @@
      "output_type": "stream",
      "text": [
       "training on  cuda\n",
-      "epoch 1, loss 0.0072, train acc 0.322, test acc 0.584, time 3.7 sec\n",
-      "epoch 2, loss 0.0037, train acc 0.649, test acc 0.699, time 1.8 sec\n",
-      "epoch 3, loss 0.0030, train acc 0.718, test acc 0.724, time 1.7 sec\n",
-      "epoch 4, loss 0.0027, train acc 0.741, test acc 0.746, time 1.6 sec\n",
-      "epoch 5, loss 0.0024, train acc 0.759, test acc 0.759, time 1.7 sec\n"
+      "epoch 1, loss 1.7885, train acc 0.337, test acc 0.584, time 2.4 sec\n",
+      "epoch 2, loss 0.4793, train acc 0.614, test acc 0.666, time 2.3 sec\n",
+      "epoch 3, loss 0.2637, train acc 0.704, test acc 0.720, time 2.3 sec\n",
+      "epoch 4, loss 0.1747, train acc 0.734, test acc 0.740, time 2.2 sec\n",
+      "epoch 5, loss 0.1282, train acc 0.751, test acc 0.749, time 2.2 sec\n"
      ]
     }
    ],
@@ -245,9 +246,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": []
   }
@@ -268,7 +267,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.3"
+   "version": "3.6.8"
   },
   "varInspector": {
    "cols": {