Add description for Dataset objects (#384)

* add __repr__ for datasets

* fix lint

torchvision/datasets/cifar.py

@@ -159,6 +159,18 @@ class CIFAR10(data.Dataset):
         tar.close()
         os.chdir(cwd)
 
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        tmp = 'train' if self.train is True else 'test'
+        fmt_str += '    Split: {}\n'.format(tmp)
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str
+
 
 class CIFAR100(CIFAR10):
     """`CIFAR100 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.

torchvision/datasets/coco.py

@@ -125,3 +125,13 @@ class CocoDetection(data.Dataset):
 
     def __len__(self):
         return len(self.ids)
+
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str

torchvision/datasets/fakedata.py

@@ -54,3 +54,12 @@ class FakeData(data.Dataset):
 
     def __len__(self):
         return self.size
+
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str

torchvision/datasets/folder.py

@@ -129,3 +129,13 @@ class ImageFolder(data.Dataset):
 
     def __len__(self):
         return len(self.imgs)
+
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str

torchvision/datasets/lsun.py

@@ -143,4 +143,11 @@ class LSUN(data.Dataset):
         return self.length
 
     def __repr__(self):
-        return self.__class__.__name__ + ' (' + self.db_path + ')'
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str

torchvision/datasets/mnist.py

@@ -139,6 +139,18 @@ class MNIST(data.Dataset):
 
         print('Done!')
 
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        tmp = 'train' if self.train is True else 'test'
+        fmt_str += '    Split: {}\n'.format(tmp)
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str
+
 
 class FashionMNIST(MNIST):
     """`Fashion-MNIST <https://github.com/zalandoresearch/fashion-mnist>`_ Dataset.

torchvision/datasets/phototour.py

@@ -152,6 +152,16 @@ class PhotoTour(data.Dataset):
         with open(self.data_file, 'wb') as f:
             torch.save(dataset, f)
 
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        tmp = 'train' if self.train is True else 'test'
+        fmt_str += '    Split: {}\n'.format(tmp)
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str
+
 
 def read_image_file(data_dir, image_ext, n):
     """Return a Tensor containing the patches

torchvision/datasets/semeion.py

@@ -91,3 +91,13 @@ class SEMEION(data.Dataset):
 
         root = self.root
         download_url(self.url, root, self.filename, self.md5_checksum)
+
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str

torchvision/datasets/stl10.py

@@ -126,3 +126,14 @@ class STL10(CIFAR10):
             images = np.transpose(images, (0, 1, 3, 2))
 
         return images, labels
+
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        fmt_str += '    Split: {}\n'.format(self.split)
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str

torchvision/datasets/svhn.py

@@ -115,3 +115,14 @@ class SVHN(data.Dataset):
     def download(self):
         md5 = self.split_list[self.split][2]
         download_url(self.url, self.root, self.filename, md5)
+
+    def __repr__(self):
+        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
+        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
+        fmt_str += '    Split: {}\n'.format(self.split)
+        fmt_str += '    Root Location: {}\n'.format(self.root)
+        tmp = '    Transforms (if any): '
+        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        tmp = '    Target Transforms (if any): '
+        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
+        return fmt_str