1

我正在尝试使用暗网 yolov1 来训练单类对象检测。但是，当我尝试训练时，CPU 工作但速度很慢，GPU 给出的结果如下：

layer     filters    size              input                output
    0 conv     64  7 x 7 / 2   448 x 448 x   3   ->   224 x 224 x  64
    1 max          2 x 2 / 2   224 x 224 x  64   ->   112 x 112 x  64
    2 conv    192  3 x 3 / 1   112 x 112 x  64   ->   112 x 112 x 192
    3 max          2 x 2 / 2   112 x 112 x 192   ->    56 x  56 x 192
    4 conv    128  1 x 1 / 1    56 x  56 x 192   ->    56 x  56 x 128
    5 conv    256  3 x 3 / 1    56 x  56 x 128   ->    56 x  56 x 256
    6 conv    256  1 x 1 / 1    56 x  56 x 256   ->    56 x  56 x 256
    7 conv    512  3 x 3 / 1    56 x  56 x 256   ->    56 x  56 x 512
    8 max          2 x 2 / 2    56 x  56 x 512   ->    28 x  28 x 512
    9 conv    256  1 x 1 / 1    28 x  28 x 512   ->    28 x  28 x 256
   10 conv    512  3 x 3 / 1    28 x  28 x 256   ->    28 x  28 x 512
   11 conv    256  1 x 1 / 1    28 x  28 x 512   ->    28 x  28 x 256
   12 conv    512  3 x 3 / 1    28 x  28 x 256   ->    28 x  28 x 512
   13 conv    256  1 x 1 / 1    28 x  28 x 512   ->    28 x  28 x 256
   14 conv    512  3 x 3 / 1    28 x  28 x 256   ->    28 x  28 x 512
   15 conv    256  1 x 1 / 1    28 x  28 x 512   ->    28 x  28 x 256
   16 conv    512  3 x 3 / 1    28 x  28 x 256   ->    28 x  28 x 512
   17 conv    512  1 x 1 / 1    28 x  28 x 512   ->    28 x  28 x 512
   18 conv   1024  3 x 3 / 1    28 x  28 x 512   ->    28 x  28 x1024
   19 max          2 x 2 / 2    28 x  28 x1024   ->    14 x  14 x1024
   20 conv    512  1 x 1 / 1    14 x  14 x1024   ->    14 x  14 x 512
   21 conv   1024  3 x 3 / 1    14 x  14 x 512   ->    14 x  14 x1024
   22 conv    512  1 x 1 / 1    14 x  14 x1024   ->    14 x  14 x 512
   23 conv   1024  3 x 3 / 1    14 x  14 x 512   ->    14 x  14 x1024
   24 conv   1024  3 x 3 / 1    14 x  14 x1024   ->    14 x  14 x1024
   25 conv   1024  3 x 3 / 2    14 x  14 x1024   ->     7 x   7 x1024
   26 conv   1024  3 x 3 / 1     7 x   7 x1024   ->     7 x   7 x1024
   27 conv   1024  3 x 3 / 1     7 x   7 x1024   ->     7 x   7 x1024
   28 Local Layer: 7 x 7 x 1024 image, 256 filters -> 7 x 7 x 256 image
   29 dropout       p = 0.50               12544  ->  12544
   30 connected                            12544  ->   784
   31 Detection Layer
forced: Using default '0'
Loading weights from darknet.conv.weights...Done!
Learning Rate: 0.0005, Momentum: 0.9, Decay: 0.0005
Loaded: 1.446220 seconds
Detection Avg IOU: 0.000000, Pos Cat: 0.000000, All Cat: 0.000000, Pos Obj: 0.000000, Any Obj: 0.000000, count: 18
Detection Avg IOU: 0.000000, Pos Cat: 0.000000, All Cat: 0.000000, Pos Obj: 0.000000, Any Obj: 0.000000, count: 19
Detection Avg IOU: 0.000000, Pos Cat: 0.000000, All Cat: 0.000000, Pos Obj: 0.000000, Any Obj: 0.000000, count: 19
Detection Avg IOU: 0.000000, Pos Cat: 0.000000, All Cat: 0.000000, Pos Obj: 0.000000, Any Obj: 0.000000, count: 18
1: 27.096424, 27.096424 avg, 0.000500 rate, 9.151883 seconds, 64 images
Loaded: 0.000042 seconds

有谁知道为什么会这样？GPU训练似乎没有任何结果。

4

1 回答 1

0

问题解决了。我将暗网版本恢复为 2016 年 11 月 22 日版本的 pjreddie/darknet，它能够使用 GPU 进行训练

于 2017-12-06T08:49:58.883 回答