Automated tutorials push

Author: pytorchbot

_downloads/6042bacf7948939030769777afe22e55/data_loading_tutorial.py

@@ -124,7 +124,7 @@ class FaceLandmarksDataset(Dataset):
 
     def __init__(self, csv_file, root_dir, transform=None):
         """
-        Args:
+        Arguments:
             csv_file (string): Path to the csv file with annotations.
             root_dir (string): Directory with all the images.
             transform (callable, optional): Optional transform to be applied
@@ -197,7 +197,7 @@ def __getitem__(self, idx):
 #    swap axes).
 #
 # We will write them as callable classes instead of simple functions so
-# that parameters of the transform need not be passed everytime it's
+# that parameters of the transform need not be passed every time it's
 # called. For this, we just need to implement ``__call__`` method and
 # if required, ``__init__`` method. We can then use a transform like this:
 #
@@ -291,12 +291,12 @@ def __call__(self, sample):
         image = image.transpose((2, 0, 1))
         return {'image': torch.from_numpy(image),
                 'landmarks': torch.from_numpy(landmarks)}
-    
+
 ######################################################################
 # .. note::
 #     In the example above, `RandomCrop` uses an external library's random number generator 
-#     (in this case, Numpy's `np.random.int`). This can result in unexpected behavior with `DataLoader` 
-#     (see https://pytorch.org/docs/stable/notes/faq.html#my-data-loader-workers-return-identical-random-numbers). 
+#     (in this case, Numpy's `np.random.int`). This can result in unexpected behavior with `DataLoader`
+#     (see `here <https://pytorch.org/docs/stable/notes/faq.html#my-data-loader-workers-return-identical-random-numbers>`_).
 #     In practice, it is safer to stick to PyTorch's random number generator, e.g. by using `torch.randint` instead.
 
 ######################################################################
@@ -404,7 +404,7 @@ def show_landmarks_batch(sample_batched):
         plt.title('Batch from dataloader')
 
 # if you are using Windows, uncomment the next line and indent the for loop.
-# you might need to go back and change "num_workers" to 0. 
+# you might need to go back and change ``num_workers`` to 0.
 
 # if __name__ == '__main__':
 for i_batch, sample_batched in enumerate(dataloader):
@@ -444,21 +444,21 @@ def show_landmarks_batch(sample_batched):
 # which operate on ``PIL.Image`` like  ``RandomHorizontalFlip``, ``Scale``,
 # are also available. You can use these to write a dataloader like this: ::
 #
-#   import torch
-#   from torchvision import transforms, datasets
-#
-#   data_transform = transforms.Compose([
-#           transforms.RandomSizedCrop(224),
-#           transforms.RandomHorizontalFlip(),
-#           transforms.ToTensor(),
-#           transforms.Normalize(mean=[0.485, 0.456, 0.406],
-#                                std=[0.229, 0.224, 0.225])
-#       ])
-#   hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',
-#                                              transform=data_transform)
-#   dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,
-#                                                batch_size=4, shuffle=True,
-#                                                num_workers=4)
+#    import torch
+#    from torchvision import transforms, datasets
+#
+#    data_transform = transforms.Compose([
+#            transforms.RandomSizedCrop(224),
+#            transforms.RandomHorizontalFlip(),
+#            transforms.ToTensor(),
+#            transforms.Normalize(mean=[0.485, 0.456, 0.406],
+#                                 std=[0.229, 0.224, 0.225])
+#        ])
+#    hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',
+#                                               transform=data_transform)
+#    dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,
+#                                                 batch_size=4, shuffle=True,
+#                                                 num_workers=4)
 #
 # For an example with training code, please see
 # :doc:`transfer_learning_tutorial`.

_downloads/f498e3bcd9b6159ecfb1a07d6551287d/data_loading_tutorial.ipynb

@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "class FaceLandmarksDataset(Dataset):\n    \"\"\"Face Landmarks dataset.\"\"\"\n\n    def __init__(self, csv_file, root_dir, transform=None):\n        \"\"\"\n        Args:\n            csv_file (string): Path to the csv file with annotations.\n            root_dir (string): Directory with all the images.\n            transform (callable, optional): Optional transform to be applied\n                on a sample.\n        \"\"\"\n        self.landmarks_frame = pd.read_csv(csv_file)\n        self.root_dir = root_dir\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.landmarks_frame)\n\n    def __getitem__(self, idx):\n        if torch.is_tensor(idx):\n            idx = idx.tolist()\n\n        img_name = os.path.join(self.root_dir,\n                                self.landmarks_frame.iloc[idx, 0])\n        image = io.imread(img_name)\n        landmarks = self.landmarks_frame.iloc[idx, 1:]\n        landmarks = np.array([landmarks])\n        landmarks = landmarks.astype('float').reshape(-1, 2)\n        sample = {'image': image, 'landmarks': landmarks}\n\n        if self.transform:\n            sample = self.transform(sample)\n\n        return sample"
+        "class FaceLandmarksDataset(Dataset):\n    \"\"\"Face Landmarks dataset.\"\"\"\n\n    def __init__(self, csv_file, root_dir, transform=None):\n        \"\"\"\n        Arguments:\n            csv_file (string): Path to the csv file with annotations.\n            root_dir (string): Directory with all the images.\n            transform (callable, optional): Optional transform to be applied\n                on a sample.\n        \"\"\"\n        self.landmarks_frame = pd.read_csv(csv_file)\n        self.root_dir = root_dir\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.landmarks_frame)\n\n    def __getitem__(self, idx):\n        if torch.is_tensor(idx):\n            idx = idx.tolist()\n\n        img_name = os.path.join(self.root_dir,\n                                self.landmarks_frame.iloc[idx, 0])\n        image = io.imread(img_name)\n        landmarks = self.landmarks_frame.iloc[idx, 1:]\n        landmarks = np.array([landmarks])\n        landmarks = landmarks.astype('float').reshape(-1, 2)\n        sample = {'image': image, 'landmarks': landmarks}\n\n        if self.transform:\n            sample = self.transform(sample)\n\n        return sample"
       ]
     },
     {
@@ -105,7 +105,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Transforms\n\nOne issue we can see from the above is that the samples are not of the\nsame size. Most neural networks expect the images of a fixed size.\nTherefore, we will need to write some preprocessing code.\nLet's create three transforms:\n\n-  ``Rescale``: to scale the image\n-  ``RandomCrop``: to crop from image randomly. This is data\n   augmentation.\n-  ``ToTensor``: to convert the numpy images to torch images (we need to\n   swap axes).\n\nWe will write them as callable classes instead of simple functions so\nthat parameters of the transform need not be passed everytime it's\ncalled. For this, we just need to implement ``__call__`` method and\nif required, ``__init__`` method. We can then use a transform like this:\n\n::\n\n    tsfm = Transform(params)\n    transformed_sample = tsfm(sample)\n\nObserve below how these transforms had to be applied both on the image and\nlandmarks.\n\n\n"
+        "## Transforms\n\nOne issue we can see from the above is that the samples are not of the\nsame size. Most neural networks expect the images of a fixed size.\nTherefore, we will need to write some preprocessing code.\nLet's create three transforms:\n\n-  ``Rescale``: to scale the image\n-  ``RandomCrop``: to crop from image randomly. This is data\n   augmentation.\n-  ``ToTensor``: to convert the numpy images to torch images (we need to\n   swap axes).\n\nWe will write them as callable classes instead of simple functions so\nthat parameters of the transform need not be passed every time it's\ncalled. For this, we just need to implement ``__call__`` method and\nif required, ``__init__`` method. We can then use a transform like this:\n\n::\n\n    tsfm = Transform(params)\n    transformed_sample = tsfm(sample)\n\nObserve below how these transforms had to be applied both on the image and\nlandmarks.\n\n\n"
       ]
     },
     {
@@ -123,7 +123,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "<div class=\"alert alert-info\"><h4>Note</h4><p>In the example above, `RandomCrop` uses an external library's random number generator \n    (in this case, Numpy's `np.random.int`). This can result in unexpected behavior with `DataLoader` \n    (see https://pytorch.org/docs/stable/notes/faq.html#my-data-loader-workers-return-identical-random-numbers). \n    In practice, it is safer to stick to PyTorch's random number generator, e.g. by using `torch.randint` instead.</p></div>\n\n"
+        "<div class=\"alert alert-info\"><h4>Note</h4><p>In the example above, `RandomCrop` uses an external library's random number generator \n    (in this case, Numpy's `np.random.int`). This can result in unexpected behavior with `DataLoader`\n    (see [here](https://pytorch.org/docs/stable/notes/faq.html#my-data-loader-workers-return-identical-random-numbers)).\n    In practice, it is safer to stick to PyTorch's random number generator, e.g. by using `torch.randint` instead.</p></div>\n\n"
       ]
     },
     {
@@ -177,14 +177,14 @@
       },
       "outputs": [],
       "source": [
-        "dataloader = DataLoader(transformed_dataset, batch_size=4,\n                        shuffle=True, num_workers=0)\n\n\n# Helper function to show a batch\ndef show_landmarks_batch(sample_batched):\n    \"\"\"Show image with landmarks for a batch of samples.\"\"\"\n    images_batch, landmarks_batch = \\\n            sample_batched['image'], sample_batched['landmarks']\n    batch_size = len(images_batch)\n    im_size = images_batch.size(2)\n    grid_border_size = 2\n\n    grid = utils.make_grid(images_batch)\n    plt.imshow(grid.numpy().transpose((1, 2, 0)))\n\n    for i in range(batch_size):\n        plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size + (i + 1) * grid_border_size,\n                    landmarks_batch[i, :, 1].numpy() + grid_border_size,\n                    s=10, marker='.', c='r')\n\n        plt.title('Batch from dataloader')\n\n# if you are using Windows, uncomment the next line and indent the for loop.\n# you might need to go back and change \"num_workers\" to 0. \n\n# if __name__ == '__main__':\nfor i_batch, sample_batched in enumerate(dataloader):\n    print(i_batch, sample_batched['image'].size(),\n          sample_batched['landmarks'].size())\n\n    # observe 4th batch and stop.\n    if i_batch == 3:\n        plt.figure()\n        show_landmarks_batch(sample_batched)\n        plt.axis('off')\n        plt.ioff()\n        plt.show()\n        break"
+        "dataloader = DataLoader(transformed_dataset, batch_size=4,\n                        shuffle=True, num_workers=0)\n\n\n# Helper function to show a batch\ndef show_landmarks_batch(sample_batched):\n    \"\"\"Show image with landmarks for a batch of samples.\"\"\"\n    images_batch, landmarks_batch = \\\n            sample_batched['image'], sample_batched['landmarks']\n    batch_size = len(images_batch)\n    im_size = images_batch.size(2)\n    grid_border_size = 2\n\n    grid = utils.make_grid(images_batch)\n    plt.imshow(grid.numpy().transpose((1, 2, 0)))\n\n    for i in range(batch_size):\n        plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size + (i + 1) * grid_border_size,\n                    landmarks_batch[i, :, 1].numpy() + grid_border_size,\n                    s=10, marker='.', c='r')\n\n        plt.title('Batch from dataloader')\n\n# if you are using Windows, uncomment the next line and indent the for loop.\n# you might need to go back and change ``num_workers`` to 0.\n\n# if __name__ == '__main__':\nfor i_batch, sample_batched in enumerate(dataloader):\n    print(i_batch, sample_batched['image'].size(),\n          sample_batched['landmarks'].size())\n\n    # observe 4th batch and stop.\n    if i_batch == 3:\n        plt.figure()\n        show_landmarks_batch(sample_batched)\n        plt.axis('off')\n        plt.ioff()\n        plt.show()\n        break"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Afterword: torchvision\n\nIn this tutorial, we have seen how to write and use datasets, transforms\nand dataloader. ``torchvision`` package provides some common datasets and\ntransforms. You might not even have to write custom classes. One of the\nmore generic datasets available in torchvision is ``ImageFolder``.\nIt assumes that images are organized in the following way: ::\n\n    root/ants/xxx.png\n    root/ants/xxy.jpeg\n    root/ants/xxz.png\n    .\n    .\n    .\n    root/bees/123.jpg\n    root/bees/nsdf3.png\n    root/bees/asd932_.png\n\nwhere 'ants', 'bees' etc. are class labels. Similarly generic transforms\nwhich operate on ``PIL.Image`` like  ``RandomHorizontalFlip``, ``Scale``,\nare also available. You can use these to write a dataloader like this: ::\n\n  import torch\n  from torchvision import transforms, datasets\n\n  data_transform = transforms.Compose([\n          transforms.RandomSizedCrop(224),\n          transforms.RandomHorizontalFlip(),\n          transforms.ToTensor(),\n          transforms.Normalize(mean=[0.485, 0.456, 0.406],\n                               std=[0.229, 0.224, 0.225])\n      ])\n  hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',\n                                             transform=data_transform)\n  dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,\n                                               batch_size=4, shuffle=True,\n                                               num_workers=4)\n\nFor an example with training code, please see\n:doc:`transfer_learning_tutorial`.\n\n"
+        "## Afterword: torchvision\n\nIn this tutorial, we have seen how to write and use datasets, transforms\nand dataloader. ``torchvision`` package provides some common datasets and\ntransforms. You might not even have to write custom classes. One of the\nmore generic datasets available in torchvision is ``ImageFolder``.\nIt assumes that images are organized in the following way: ::\n\n    root/ants/xxx.png\n    root/ants/xxy.jpeg\n    root/ants/xxz.png\n    .\n    .\n    .\n    root/bees/123.jpg\n    root/bees/nsdf3.png\n    root/bees/asd932_.png\n\nwhere 'ants', 'bees' etc. are class labels. Similarly generic transforms\nwhich operate on ``PIL.Image`` like  ``RandomHorizontalFlip``, ``Scale``,\nare also available. You can use these to write a dataloader like this: ::\n\n   import torch\n   from torchvision import transforms, datasets\n\n   data_transform = transforms.Compose([\n           transforms.RandomSizedCrop(224),\n           transforms.RandomHorizontalFlip(),\n           transforms.ToTensor(),\n           transforms.Normalize(mean=[0.485, 0.456, 0.406],\n                                std=[0.229, 0.224, 0.225])\n       ])\n   hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',\n                                              transform=data_transform)\n   dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,\n                                                batch_size=4, shuffle=True,\n                                                num_workers=4)\n\nFor an example with training code, please see\n:doc:`transfer_learning_tutorial`.\n\n"
       ]
     }
   ],

_images/sphx_glr_char_rnn_classification_tutorial_001.png

@@ -516,9 +516,9 @@ models run single threaded.
  .. code-block:: none
 
     loss: 5.167
-    elapsed time (seconds): 174.8
+    elapsed time (seconds): 184.6
     loss: 5.168
-    elapsed time (seconds): 105.4
+    elapsed time (seconds): 107.0
 
 
 
@@ -540,7 +540,7 @@ Thanks for reading! As always, we welcome any feedback, so please create an issu
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 4 minutes  49.111 seconds)
+   **Total running time of the script:** ( 5 minutes  0.415 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py: