A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
I follow the order mentioned in the instruction, run "preprocess_fer2913.py" first, then "fer.py", and "mainpro_FER.py", but when I run the "mainpro_FER", I got this two errors here:
"ValueError: cannot reshape array of size 0 into shape (28709,48,48)"
"TypeError: init() got an unexpected keyword argument 'split'"
I guess maybe there are some slight difference between python2 and python3, and few codes need to be changed according. Is there someone can help me? Anything helpful will be really appreciated!!!
I follow the order mentioned in the instruction, run "preprocess_fer2913.py" first, then "fer.py", and "mainpro_FER.py", but when I run the "mainpro_FER", I got this two errors here:
"ValueError: cannot reshape array of size 0 into shape (28709,48,48)" "TypeError: init() got an unexpected keyword argument 'split'"
I guess maybe there are some slight difference between python2 and python3, and few codes need to be changed according. Is there someone can help me? Anything helpful will be really appreciated!!!