Trying to fix ruff and isort on push

Author: Seilmast

tests/test_dataloaders.py

@@ -48,8 +48,12 @@ def test_svhn_dataset():
         )
 
         assert dataset.__len__() != 0
-        assert os.path.exists(os.path.join(tempdir, "test_32x32.mat")), f'No such file as test_32x32.mat. Try running download=True'
-        assert os.path.exists(os.path.join(tempdir, "svhn_testdata.h5")), f'No such file as svhn_testdata.h5. Try running download=True'
+        assert os.path.exists(os.path.join(tempdir, "test_32x32.mat")), (
+            f"No such file as test_32x32.mat. Try running download=True"
+        )
+        assert os.path.exists(os.path.join(tempdir, "svhn_testdata.h5")), (
+            f"No such file as svhn_testdata.h5. Try running download=True"
+        )
 
         img, label = dataset.__getitem__(0)
         assert len(img.size()) == 3 and img.size() == (1, 28, 28) and img.size(0) == 1

tests/test_metrics.py

@@ -104,11 +104,14 @@ def test_entropypred():
 
     pred_logits = th.rand(6, 5)
     true_lab = th.rand(6, 5)
-    
+
     metric = EntropyPrediction(averages="mean")
     metric2 = EntropyPrediction(averages="sum")
-    
+
     # Test for averaging metric consistency
     metric(true_lab, pred_logits)
     metric2(true_lab, pred_logits)
-    assert (th.abs(th.sum(6 * metric.__returnmetric__() - metric2.__returnmetric__())) < 1e-5)
+    assert (
+        th.abs(th.sum(6 * metric.__returnmetric__() - metric2.__returnmetric__()))
+        < 1e-5
+    )

utils/dataloaders/svhn.py

@@ -1,6 +1,6 @@
 import os
 
-import h5py 
+import h5py
 import numpy as np
 from PIL import Image
 from scipy.io import loadmat
@@ -37,15 +37,16 @@ def __init__(
 
         self.nr_channels = nr_channels
         self.transforms = transform
-        
-        
-        assert os.path.exists(os.path.join(self.data_path, f'svhn_{self.split}data.h5')), f'File svhn_{self.split}data.h5 does not exists. Run download=True'
-        with h5py.File(os.path.join(self.data_path, f'svhn_{self.split}data.h5'), 'r') as h5f:
-            self.labels = h5f['labels'][:]
-        
+
+        assert os.path.exists(
+            os.path.join(self.data_path, f"svhn_{self.split}data.h5")
+        ), f"File svhn_{self.split}data.h5 does not exists. Run download=True"
+        with h5py.File(
+            os.path.join(self.data_path, f"svhn_{self.split}data.h5"), "r"
+        ) as h5f:
+            self.labels = h5f["labels"][:]
+
         self.num_classes = len(np.unique(self.labels))
-        
-        
 
     def _download_data(self, path: str):
         """
@@ -55,17 +56,19 @@ def _download_data(self, path: str):
         """
         print(f"Downloading SVHN data into {path}")
         SVHN(path, split=self.split, download=True)
-        data = loadmat(os.path.join(path, f'{self.split}_32x32.mat'))
+        data = loadmat(os.path.join(path, f"{self.split}_32x32.mat"))
 
-        images, labels = data['X'], data['y']
-        images = images.transpose(3,1,0,2)
+        images, labels = data["X"], data["y"]
+        images = images.transpose(3, 1, 0, 2)
         labels[labels == 10] = 0
         labels = labels.flatten()
-        
-        with h5py.File(os.path.join(self.data_path, f'svhn_{self.split}data.h5'), 'w') as h5f:
-            h5f.create_dataset('images', data=images)
-            h5f.create_dataset('labels', data=labels)
- 
+
+        with h5py.File(
+            os.path.join(self.data_path, f"svhn_{self.split}data.h5"), "w"
+        ) as h5f:
+            h5f.create_dataset("images", data=images)
+            h5f.create_dataset("labels", data=labels)
+
     def __len__(self):
         """
         Returns the number of samples in the dataset.
@@ -83,14 +86,15 @@ def __getitem__(self, index):
             tuple: A tuple containing the image and its corresponding label.
         """
         lab = self.labels[index]
-        with h5py.File(os.path.join(self.data_path, f'svhn_{self.split}data.h5'), 'r') as h5f:
-            img = Image.fromarray(h5f['images'][index])
-            
+        with h5py.File(
+            os.path.join(self.data_path, f"svhn_{self.split}data.h5"), "r"
+        ) as h5f:
+            img = Image.fromarray(h5f["images"][index])
+
         if self.nr_channels == 1:
-            img = img.convert('L')
-            
+            img = img.convert("L")
+
         if self.transforms is not None:
             img = self.transforms(img)
 
         return img, lab
-

utils/metrics/EntropyPred.py

@@ -1,6 +1,6 @@
-import torch as th 
-import torch.nn as nn
 import numpy as np
+import torch as th
+import torch.nn as nn
 from scipy.stats import entropy
 
 
@@ -34,21 +34,20 @@ def __call__(self, y_true: th.Tensor, y_logits: th.Tensor):
             torch.Tensor: The aggregated entropy value(s) based on the specified
                           method ('mean', 'sum', or 'none').
         """
-        
-        assert len(y_logits.size()) == 2, f'y_logits shape: {y_logits.size()}'
+
+        assert len(y_logits.size()) == 2, f"y_logits shape: {y_logits.size()}"
         y_pred = nn.Softmax(dim=1)(y_logits)
-        print(f'y_pred: {y_pred}')
+        print(f"y_pred: {y_pred}")
         entropy_values = entropy(y_pred, axis=1)
         entropy_values = th.from_numpy(entropy_values)
 
         # Fix numerical errors for perfect guesses
         entropy_values[entropy_values == th.inf] = 0
         entropy_values = th.nan_to_num(entropy_values)
-        print(f'Entropy Values: {entropy_values}')
+        print(f"Entropy Values: {entropy_values}")
         for sample in entropy_values:
             self.stored_entropy_values.append(sample.item())
 
-
     def __returnmetric__(self):
         stored_entropy_values = th.from_numpy(np.asarray(self.stored_entropy_values))
 
@@ -57,9 +56,8 @@ def __returnmetric__(self):
         elif self.averages == "sum":
             stored_entropy_values = th.sum(stored_entropy_values)
         elif self.averages == "none":
-            pass 
+            pass
         return stored_entropy_values
 
     def __reset__(self):
         self.stored_entropy_values = []
-