Merge branch 'main' into svekars-patch-65

Author: sekyondaMeta

beginner_source/blitz/tensor_tutorial.py

@@ -105,9 +105,9 @@
 #
 
 # We move our tensor to the GPU if available
-if torch.cuda.is_available():
-  tensor = tensor.to('cuda')
-  print(f"Device tensor is stored on: {tensor.device}")
+device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else 'cpu'
+tensor = tensor.to(device)
+print(f"Device tensor is stored on: {tensor.device}")
 
 
 ######################################################################

beginner_source/ddp_series_multigpu.rst

@@ -202,6 +202,7 @@ Running the distributed training job
 Here's what the code looks like:
 
 .. code-block:: python
+
    def main(rank, world_size, total_epochs, save_every):
       ddp_setup(rank, world_size)
       dataset, model, optimizer = load_train_objs()
@@ -218,7 +219,6 @@ Here's what the code looks like:
       mp.spawn(main, args=(world_size, total_epochs, save_every,), nprocs=world_size)
 
 
-
 Further Reading
 ---------------
 

beginner_source/introyt/modelsyt_tutorial.py

@@ -48,12 +48,12 @@ class is a subclass of ``torch.Tensor``, with the special behavior that
 class TinyModel(torch.nn.Module):
 
     def __init__(self):
-        super(TinyModel, self).__init__()
+        super().__init__()
 
         self.linear1 = torch.nn.Linear(100, 200)
         self.activation = torch.nn.ReLU()
         self.linear2 = torch.nn.Linear(200, 10)
-        self.softmax = torch.nn.Softmax()
+        self.softmax = torch.nn.Softmax(dim=1)
 
     def forward(self, x):
         x = self.linear1(x)
@@ -150,7 +150,7 @@ def forward(self, x):
 class LeNet(torch.nn.Module):
 
     def __init__(self):
-        super(LeNet, self).__init__()
+        super().__init__()
         # 1 input image channel (black & white), 6 output channels, 5x5 square convolution
         # kernel
         self.conv1 = torch.nn.Conv2d(1, 6, 5)
@@ -249,7 +249,7 @@ def num_flat_features(self, x):
 class LSTMTagger(torch.nn.Module):
 
     def __init__(self, embedding_dim, hidden_dim, vocab_size, tagset_size):
-        super(LSTMTagger, self).__init__()
+        super().__init__()
         self.hidden_dim = hidden_dim
 
         self.word_embeddings = torch.nn.Embedding(vocab_size, embedding_dim)