pytorch dataloader 取batch_size时候 出现bug

1、RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 342 and 281 in dimension 3 at /pytorch/aten/src/TH/generic/THTensorMoreMath.cpp:1333
2、RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 3 and 1 in dimension 1
bug1 修改方法是将图片resize 成一个尺度:
解决1:
如果用transforms来resize ,关于尺寸的transform就是transforms.Resize(input_size, interpolation=3)了。
查看Resize的文档:
size (sequence or int) – Desired output size. If size is a sequence like (h, w), output size will be matched to this.
If size is an int, smaller edge of the image will be matched to this number. i.e, if height > width, then image will be rescaled to (size * height / width, size)
size这个参数既可以是一个数字,又可以是一个tuple,如果是数字,图片处理后的输出尺寸每次都会被重新计算为(input_size*height/width, size),这样如果输入图片尺寸不一致,输出图片尺寸会不一致, 将导致bug1 问题
解决2:
也可以直接用opencv resize
bug2 将图片全部转成一个channel 比如RGB