Merge branch 'main' into spellcheck-addons

Author: malfet

beginner_source/basics/buildmodel_tutorial.py

@@ -32,12 +32,17 @@
 #############################################
 # Get Device for Training
 # -----------------------
-# We want to be able to train our model on a hardware accelerator like the GPU,
-# if it is available. Let's check to see if
-# `torch.cuda <https://pytorch.org/docs/stable/notes/cuda.html>`_ is available, else we
-# continue to use the CPU.
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# We want to be able to train our model on a hardware accelerator like the GPU or MPS,
+# if available. Let's check to see if `torch.cuda <https://pytorch.org/docs/stable/notes/cuda.html>`_
+# or `torch.backends.mps <https://pytorch.org/docs/stable/notes/mps.html>`_ are available, otherwise we use the CPU.
+
+device = (
+    "cuda"
+    if torch.cuda.is_available()
+    else "mps"
+    if torch.backends.mps.is_available()
+    else "cpu"
+)
 print(f"Using {device} device")
 
 ##############################################

beginner_source/basics/quickstart_tutorial.py

@@ -84,10 +84,16 @@
 # To define a neural network in PyTorch, we create a class that inherits
 # from `nn.Module <https://pytorch.org/docs/stable/generated/torch.nn.Module.html>`_. We define the layers of the network
 # in the ``__init__`` function and specify how data will pass through the network in the ``forward`` function. To accelerate
-# operations in the neural network, we move it to the GPU if available.
-
-# Get cpu or gpu device for training.
-device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+# operations in the neural network, we move it to the GPU or MPS if available.
+
+# Get cpu, gpu or mps device for training.
+device = (
+    "cuda"
+    if torch.cuda.is_available()
+    else "mps"
+    if torch.backends.mps.is_available()
+    else "cpu"
+)
 print(f"Using {device} device")
 
 # Define model

beginner_source/basics/saveloadrun_tutorial.py

@@ -26,14 +26,14 @@
 # state dictionary, called ``state_dict``. These can be persisted via the ``torch.save``
 # method:
 
-model = models.vgg16(pretrained=True)
+model = models.vgg16(weights='IMAGENET1K_V1')
 torch.save(model.state_dict(), 'model_weights.pth')
 
 ##########################
 # To load model weights, you need to create an instance of the same model first, and then load the parameters
 # using ``load_state_dict()`` method.
 
-model = models.vgg16() # we do not specify pretrained=True, i.e. do not load default weights
+model = models.vgg16() # we do not specify weights, i.e. create untrained model
 model.load_state_dict(torch.load('model_weights.pth'))
 model.eval()
 

beginner_source/dcgan_faces_tutorial.py

@@ -459,7 +459,7 @@ def forward(self, input):
 # With :math:`D` and :math:`G` setup, we can specify how they learn
 # through the loss functions and optimizers. We will use the Binary Cross
 # Entropy loss
-# (`BCELoss <https://pytorch.org/docs/stable/nn.html#torch.nn.BCELoss>`__)
+# (`BCELoss <https://pytorch.org/docs/stable/generated/torch.nn.BCELoss.html#torch.nn.BCELoss>`__)
 # function which is defined in PyTorch as:
 # 
 # .. math:: \ell(x, y) = L = \{l_1,\dots,l_N\}^\top, \quad l_n = - \left[ y_n \cdot \log x_n + (1 - y_n) \cdot \log (1 - x_n) \right]

beginner_source/introyt/captumyt.py

@@ -155,7 +155,7 @@
 # now.
 # 
 
-model = models.resnet101(pretrained=True)
+model = models.resnet101(weights='IMAGENET1K_V1')
 model = model.eval()
 
 

beginner_source/transfer_learning_tutorial.py

@@ -250,7 +250,7 @@ def visualize_model(model, num_images=6):
 # Load a pretrained model and reset final fully connected layer.
 #
 
-model_ft = models.resnet18(pretrained=True)
+model_ft = models.resnet18(weights='IMAGENET1K_V1')
 num_ftrs = model_ft.fc.in_features
 # Here the size of each output sample is set to 2.
 # Alternatively, it can be generalized to ``nn.Linear(num_ftrs, len(class_names))``.
@@ -295,7 +295,7 @@ def visualize_model(model, num_images=6):
 # `here <https://pytorch.org/docs/notes/autograd.html#excluding-subgraphs-from-backward>`__.
 #
 
-model_conv = torchvision.models.resnet18(pretrained=True)
+model_conv = torchvision.models.resnet18(weights='IMAGENET1K_V1')
 for param in model_conv.parameters():
     param.requires_grad = False
 

intermediate_source/FSDP_tutorial.rst

@@ -249,7 +249,7 @@ We add the following code snippets to a python script “FSDP_mnist.py”.
 
         if args.save_model:
             # use a barrier to make sure training is done on all ranks
-            dist_barrier()
+            dist.barrier()
             # state_dict for FSDP model is only available on Nightlies for now
             states = model.state_dict()
             if rank == 0:

intermediate_source/flask_rest_api_tutorial.py

@@ -161,8 +161,8 @@ def transform_image(image_bytes):
 
 from torchvision import models
 
-# Make sure to pass `pretrained` as `True` to use the pretrained weights:
-model = models.densenet121(pretrained=True)
+# Make sure to set `weights` as `'IMAGENET1K_V1'` to use the pretrained weights:
+model = models.densenet121(weights='IMAGENET1K_V1')
 # Since we are using our model only for inference, switch to `eval` mode:
 model.eval()
 
@@ -269,7 +269,7 @@ def get_prediction(image_bytes):
 #
 #   app = Flask(__name__)
 #   imagenet_class_index = json.load(open('<PATH/TO/.json/FILE>/imagenet_class_index.json'))
-#   model = models.densenet121(pretrained=True)
+#   model = models.densenet121(weights='IMAGENET1K_V1')
 #   model.eval()
 #
 #

intermediate_source/tensorboard_profiler_tutorial.py

@@ -68,7 +68,7 @@
 # To run on GPU, move model and loss to GPU device.
 
 device = torch.device("cuda:0")
-model = torchvision.models.resnet18(pretrained=True).cuda(device)
+model = torchvision.models.resnet18(weights='IMAGENET1K_V1').cuda(device)
 criterion = torch.nn.CrossEntropyLoss().cuda(device)
 optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
 model.train()