Merge branch 'main' into fabio

Author: Svetlana Karslioglu

beginner_source/deep_learning_60min_blitz.rst

@@ -20,11 +20,12 @@ Goal of this tutorial:
 - Understand PyTorch’s Tensor library and neural networks at a high level.
 - Train a small neural network to classify images
 
-To run the tutorials below, make sure you have the `torch`_ and `torchvision`_
-packages installed.
+To run the tutorials below, make sure you have the `torch`_, `torchvision`_,
+and `matplotlib`_ packages installed.
 
 .. _torch: https://github.com/pytorch/pytorch
 .. _torchvision: https://github.com/pytorch/vision
+.. _matplotlib: https://github.com/matplotlib/matplotlib
 
 .. toctree::
    :hidden:

beginner_source/introyt/trainingyt.py

@@ -290,15 +290,19 @@ def train_one_epoch(epoch_index, tb_writer):
     model.train(True)
     avg_loss = train_one_epoch(epoch_number, writer)
 
-    # We don't need gradients on to do reporting
-    model.train(False)
-    
+
     running_vloss = 0.0
-    for i, vdata in enumerate(validation_loader):
-        vinputs, vlabels = vdata
-        voutputs = model(vinputs)
-        vloss = loss_fn(voutputs, vlabels)
-        running_vloss += vloss
+    # Set the model to evaluation mode, disabling dropout and using population 
+    # statistics for batch normalization.
+    model.eval()
+
+    # Disable gradient computation and reduce memory consumption.
+    with torch.no_grad():
+        for i, vdata in enumerate(validation_loader):
+            vinputs, vlabels = vdata
+            voutputs = model(vinputs)
+            vloss = loss_fn(voutputs, vlabels)
+            running_vloss += vloss
 
     avg_vloss = running_vloss / (i + 1)
     print('LOSS train {} valid {}'.format(avg_loss, avg_vloss))

intermediate_source/torchvision_tutorial.rst

@@ -145,7 +145,7 @@ Let’s write a ``torch.utils.data.Dataset`` class for this dataset.
            num_objs = len(obj_ids)
            boxes = []
            for i in range(num_objs):
-               pos = np.where(masks[i])
+               pos = np.nonzero(masks[i])
                xmin = np.min(pos[1])
                xmax = np.max(pos[1])
                ymin = np.min(pos[0])