resize image using transforms in image segmentation examples about hub HOT 2 OPEN

BTW just let me know if you think that it's useful enough to be considered in the examples and I'll myself modify the code in the Markdown files (and maybe add some more lines to the explanation).

from hub.

Another note to take into consideration may be using the Image URL of the image presented in the posts Deeplabv3-ResNet101 and FCN-ResNet101, which is the image images/deeplab1.png rather than the images/dog.jpg used in the tutorial of the post.

Then the following piece of code:

# Download an example image from the pytorch website
import urllib
url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)

should be modified to:

# Download an example image from the pytorch/hub repository
import urllib
url, filename = ("https://github.com/pytorch/hub/raw/master/images/deeplab1.png", "deeplab1.png")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)

Note: everything applies to both Image Segmentation models Deeplabv3-ResNet101 and FCN-ResNet101, as both entries use the "wrong" image. (?)

from hub.