Open tanglang96 opened 6 years ago
in file model.py , your function conv3x3() is a simple 2d convolution , but I found it should be depthwise conv according to the paper , the computation cost is totally different
in file model.py , your function conv3x3() is a simple 2d convolution , but I found it should be depthwise conv according to the paper , the computation cost is totally different