Update for latest MEAP, PyTorch v1.3.0, p2ch14.

p1ch3/1_tensors.ipynb

@@ -510,7 +510,6 @@
     }
    ],
    "source": [
-    "points = torch.tensor([[4.0, 1.0], [5.0, 3.0], [2.0, 1.0]])\n",
     "second_point = points[1]\n",
     "second_point.size()"
    ]
@@ -727,9 +726,9 @@
     }
    ],
    "source": [
-    "some_tensor = torch.ones(3, 4, 5)\n",
-    "some_tensor_t = some_tensor.transpose(0, 2)\n",
-    "some_tensor.shape"
+    "some_t = torch.ones(3, 4, 5)\n",
+    "transpose_t = some_t.transpose(0, 2)\n",
+    "some_t.shape"
    ]
   },
   {
@@ -749,7 +748,7 @@
     }
    ],
    "source": [
-    "some_tensor_t.shape"
+    "transpose_t.shape"
    ]
   },
   {
@@ -769,7 +768,7 @@
     }
    ],
    "source": [
-    "some_tensor.stride()"
+    "some_t.stride()"
    ]
   },
   {
@@ -789,7 +788,7 @@
     }
    ],
    "source": [
-    "some_tensor_t.stride()"
+    "transpose_t.stride()"
    ]
   },
   {
@@ -1179,7 +1178,7 @@
    "source": [
     "f = h5py.File('../data/p1ch3/ourpoints.hdf5', 'r')\n",
     "dset = f['coords']\n",
-    "last_points = dset[1:]"
+    "last_points = dset[-2:]"
    ]
   },
   {
@@ -1188,7 +1187,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "last_points = torch.from_numpy(dset[1:])\n",
+    "last_points = torch.from_numpy(dset[-2:])\n",
     "f.close()"
    ]
   },

p1ch4/2_time_series_bikes.ipynb

@@ -150,7 +150,7 @@
    "source": [
     "weather_onehot.scatter_(\n",
     "    dim=1, \n",
-    "    index=first_day[:,9].unsqueeze(1) - 1, # <1>\n",
+    "    index=first_day[:,9].unsqueeze(1).long() - 1, # <1>\n",
     "    value=1.0)"
    ]
   },

p1ch4/3_text_jane_austin.ipynb

@@ -60,8 +60,8 @@
     }
    ],
    "source": [
-    "letter_tensor = torch.zeros(len(line), 128) # <1> \n",
-    "letter_tensor.shape"
+    "letter_t = torch.zeros(len(line), 128) # <1> \n",
+    "letter_t.shape"
    ]
   },
   {
@@ -72,7 +72,7 @@
    "source": [
     "for i, letter in enumerate(line.lower().strip()):\n",
     "    letter_index = ord(letter) if ord(letter) < 128 else 0  # <1>\n",
-    "    letter_tensor[i][letter_index] = 1"
+    "    letter_t[i][letter_index] = 1"
    ]
   },
   {
@@ -161,13 +161,13 @@
     }
    ],
    "source": [
-    "word_tensor = torch.zeros(len(words_in_line), len(word2index_dict))\n",
+    "word_t = torch.zeros(len(words_in_line), len(word2index_dict))\n",
     "for i, word in enumerate(words_in_line):\n",
     "    word_index = word2index_dict[word]\n",
-    "    word_tensor[i][word_index] = 1\n",
+    "    word_t[i][word_index] = 1\n",
     "    print('{:2} {:4} {}'.format(i, word_index, word))\n",
     "    \n",
-    "print(word_tensor.shape)\n"
+    "print(word_t.shape)\n"
    ]
   },
   {
@@ -187,8 +187,8 @@
     }
    ],
    "source": [
-    "word_tensor = word_tensor.unsqueeze(1)\n",
-    "word_tensor.shape"
+    "word_t = word_t.unsqueeze(1)\n",
+    "word_t.shape"
    ]
   },
   {

p1ch4/4_audio_chirp.ipynb

@@ -167,9 +167,9 @@
    ],
    "source": [
     "sp_left = sp_right = sp_arr\n",
-    "sp_left_tensor = torch.from_numpy(sp_left)\n",
-    "sp_right_tensor = torch.from_numpy(sp_right)\n",
-    "sp_left_tensor.shape, sp_right_tensor.shape"
+    "sp_left_t = torch.from_numpy(sp_left)\n",
+    "sp_right_t = torch.from_numpy(sp_right)\n",
+    "sp_left_t.shape, sp_right_t.shape"
    ]
   },
   {
@@ -197,8 +197,8 @@
     }
    ],
    "source": [
-    "sp_tensor = torch.stack((sp_left_tensor, sp_right_tensor), dim=0)\n",
-    "sp_tensor.shape"
+    "sp_t = torch.stack((sp_left_t, sp_right_t), dim=0)\n",
+    "sp_t.shape"
    ]
   },
   {

p1ch4/5_image_dog.ipynb

@@ -63,7 +63,7 @@
     "import os\n",
     "\n",
     "data_dir = '../data/p1ch4/image-cats/'\n",
-    "filenames = [name for name in os.listdir(data_dir) if os.path.splitext(name) == '.png']\n",
+    "filenames = [name for name in os.listdir(data_dir) if os.path.splitext(name)[-1] == '.png']\n",
     "for i, filename in enumerate(filenames):\n",
     "    img_arr = imageio.imread(filename)\n",
     "    batch[i] = torch.transpose(torch.from_numpy(img_arr), 0, 2)"

p1ch6/1_neural_networks.ipynb

@@ -262,10 +262,10 @@
    "source": [
     "def training_loop(n_epochs, optimizer, model, loss_fn, t_u_train, t_u_val, t_c_train, t_c_val):\n",
     "    for epoch in range(1, n_epochs + 1):\n",
-    "        t_p_train = model(t_un_train) # <1>\n",
+    "        t_p_train = model(t_u_train) # <1>\n",
     "        loss_train = loss_fn(t_p_train, t_c_train)\n",
     "\n",
-    "        t_p_val = model(t_un_val) # <1>\n",
+    "        t_p_val = model(t_u_val) # <1>\n",
     "        loss_val = loss_fn(t_p_val, t_c_val)\n",
     "        \n",
     "        optimizer.zero_grad()\n",

p1ch7/1_datasets.ipynb

@@ -42,7 +42,7 @@
    ],
    "source": [
     "from torchvision import datasets\n",
-    "data_path = '../data-unversioned/p1ch6/''\n",
+    "data_path = '../data-unversioned/p1ch6/'\n",
     "cifar10 = datasets.CIFAR10(data_path, train=True, download=True)\n",
     "cifar10_val = datasets.CIFAR10(data_path, train=False, download=True)"
    ]