ref : https://github.com/josharnoldjosh/Resnet-Extract-Image-Feature-Pytorch-Python/blob/master/extract_image_feature.py RuntimeError : The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0 def get_vector(image_name): # 1. Load the image with Pillow library img = Image.open(image_name).convert('RGB') 코드를 .convert('RGB')로 수정하면 작동
