자주 까먹기 때문에 글을 남겨둠. Convolution - Batch Normalization - Activation - Dropout - Pooling 자세한 내용은 아래 블로그 확인! gaussian37.github.io/dl-concept-order_of_regularization_term/BatchNormalization, Dropout, Pooling 적용 순서gaussian37's bloggaussian37.github.io

기존 계산은 다음과 같음. 하지만 pytorch에서 convolution layer output shape를 계산식은 다음과 같음 함수 def cal_conv_output_shape_torch(h_w, layer): from math import floor dilation = layer.dilation kernel_size = layer.kernel_size stride = layer.stride pad = layer.padding if type(dilation) is not tuple: pass else : dilation = dilation[0] stride = stride[0] pad = pad[0] if type(kernel_size) is not tuple: kernel_size = (kerne..