Cocktail branch inconsistencies

autoPyTorch/pipeline/components/setup/network/base_network.py

@@ -131,13 +131,14 @@ def _predict(self, network: torch.nn.Module, loader: torch.utils.data.DataLoader
         # Batch prediction
         Y_batch_preds = list()
 
-        for i, (X_batch, Y_batch) in enumerate(loader):
-            # Predict on batch
-            X_batch = X_batch.float().to(self.device)
-            Y_batch_pred = network(X_batch)
-            if self.final_activation is not None:
-                Y_batch_pred = self.final_activation(Y_batch_pred)
-            Y_batch_preds.append(Y_batch_pred.detach().cpu())
+        with torch.no_grad():
+            for i, (X_batch, Y_batch) in enumerate(loader):
+                # Predict on batch
+                X_batch = X_batch.float().to(self.device)
+                Y_batch_pred = network(X_batch)
+                if self.final_activation is not None:
+                    Y_batch_pred = self.final_activation(Y_batch_pred)
+                Y_batch_preds.append(Y_batch_pred.detach().cpu())
 
         return torch.cat(Y_batch_preds, 0)
 

autoPyTorch/pipeline/components/setup/network_backbone/utils.py

@@ -94,7 +94,7 @@ def backward(ctx: typing.Any,
 
 def shake_get_alpha_beta(is_training: bool, is_cuda: bool
                          ) -> typing.Tuple[torch.tensor, torch.tensor]:
-    if is_training:
+    if not is_training:
         result = (torch.FloatTensor([0.5]), torch.FloatTensor([0.5]))
         return result if not is_cuda else (result[0].cuda(), result[1].cuda())
 
@@ -118,10 +118,10 @@ def shake_drop_get_bl(
 ) -> torch.tensor:
     pl = 1 - ((block_index + 1) / num_blocks) * (1 - min_prob_no_shake)
 
-    if not is_training:
+    if is_training:
         # Move to torch.randn(1) for reproducibility
         bl = torch.tensor(1.0) if torch.randn(1) <= pl else torch.tensor(0.0)
-    if is_training:
+    else:
         bl = torch.tensor(pl)
 
     if is_cuda:

autoPyTorch/pipeline/components/training/data_loader/base_data_loader.py

@@ -148,6 +148,8 @@ def get_loader(self, X: np.ndarray, y: Optional[np.ndarray] = None, batch_size:
         dataset = BaseDataset(
             train_tensors=(X, y),
             # This dataset is used for loading test data in a batched format
+            seed=self.random_state.get_state()[1][0],
+            shuffle=False,
             train_transforms=self.test_transform,
             val_transforms=self.test_transform,
         )

autoPyTorch/pipeline/tabular_classification.py

@@ -91,12 +91,7 @@ def _predict_proba(self, X: np.ndarray) -> np.ndarray:
         loader = self.named_steps['data_loader'].get_loader(X=X)
         pred = self.named_steps['network'].predict(loader)
         if isinstance(self.dataset_properties['output_shape'], int):
-            proba = pred[:, :self.dataset_properties['output_shape']]
-            normalizer = proba.sum(axis=1)[:, np.newaxis]
-            normalizer[normalizer == 0.0] = 1.0
-            proba /= normalizer
-
-            return proba
+          return pred
 
         else:
             all_proba = []
@@ -147,8 +142,8 @@ def predict_proba(self, X: np.ndarray, batch_size: Optional[int] = None) -> np.n
 
         # Neural networks might not be fit to produce a [0-1] output
         # For instance, after small number of epochs.
-        y = np.clip(y, 0, 1)
-        y = sklearn.preprocessing.normalize(y, axis=1, norm='l1')
+        # y = np.clip(y, 0, 1)
+        # y = sklearn.preprocessing.normalize(y, axis=1, norm='l1')
 
         return y