yolov3 pytorch錯誤集合
File "D:\tmp\pytorch-yolo3\cfg.py", line 134, in print_cfg
assert(prev_width == out_widths[layers[1]])
是因為cfg中有除法，python3中除法自動轉為float型別，需要//變成整除
這個錯誤，把網路後面幾層變成了55，
原版的：
87 conv 256 1 x 1 / 1 26 x 26 x 768 -> 26 x 26 x 256
88 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512
89 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256
90 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512
91 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256
92 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512
93 conv 255 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 255
94 detection
95 route 91
96 conv 128 1 x 1 / 1 26 x 26 x 256 -> 26 x 26 x 128
97 upsample * 2 26 x 26 x 128 -> 52 x 52 x 128
98 route 97 36
99 conv 128 1 x 1 / 1 52 x 52 x 384 -> 52 x 52 x 128
100 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256
101 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128
102 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256
103 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128
104 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256
105 conv 255 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 255
106 detection
變錯的：
87 conv 256 1 x 1 / 1 27 x 27 x 768 -> 27 x 27 x 256
88 conv 512 3 x 3 / 1 27 x 27 x 256 -> 27 x 27 x 512
89 conv 256 1 x 1 / 1 27 x 27 x 512 -> 27 x 27 x 256
90 conv 512 3 x 3 / 1 27 x 27 x 256 -> 27 x 27 x 512
91 conv 256 1 x 1 / 1 27 x 27 x 512 -> 27 x 27 x 256
92 conv 512 3 x 3 / 1 27 x 27 x 256 -> 27 x 27 x 512
93 conv 255 1 x 1 / 1 27 x 27 x 512 -> 27 x 27 x 255
94 detection
95 route 91
96 conv 128 1 x 1 / 1 27 x 27 x 256 -> 27 x 27 x 128
97 upsample * 2 27 x 27 x 128 -> 55 x 55 x 128
98 route 97 36
99 conv 128 1 x 1 / 1 55 x 55 x 384 -> 55 x 55 x 128
100 conv 256 3 x 3 / 1 55 x 55 x 128 -> 55 x 55 x 256
101 conv 128 1 x 1 / 1 55 x 55 x 256 -> 55 x 55 x 128
102 conv 256 3 x 3 / 1 55 x 55 x 128 -> 55 x 55 x 256
103 conv 128 1 x 1 / 1 55 x 55 x 256 -> 55 x 55 x 128
104 conv 256 3 x 3 / 1 55 x 55 x 128 -> 55 x 55 x 256
105 conv 255 1 x 1 / 1 55 x 55 x 256 -> 55 x 55 x 255
106 detection