Pytorch RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0

python image-processing computer-vision pytorch

I suspect your test_image has an additional alpha channel per pixel, thus it has 4 channels instead of only three.
Try:

test_image = Image.open(test_image_name).convert('RGB')

Related

Equivalent of include() in HTML
Set back default floating point print precision in C++
Why is -didDeselectRowAtIndexPath not being called?
Json.NET serializing float/double with minimal decimal places, i.e. no redundant ".0"?
Load JQuery into a Chrome extension?
Check if all of multiple strings or regexes exist in a file
Area of rectangle-rectangle intersection
Timeout a function in PHP
How to get function parameter lists (so I can drop a function)
SMS URL on Android
How to convert hex string into a bytes array, and a bytes array in the hex string?
How determine if application is web application