Unused field: 'bin_output = 1'

[dexception]

I am trying to train yolov3-tiny_xnor and getting the following output while testing on 2000 epochs.

layer     filters    size              input                output
   0 conv     16  3 x 3 / 1   416 x 416 x   3   ->   416 x 416 x  16 0.150 BF
   1 max          2 x 2 / 2   416 x 416 x  16   ->   208 x 208 x  16 0.003 BF
   2 conv     32  3 x 3 / 1   208 x 208 x  16   ->   208 x 208 x  32 0.399 BF
Unused field: 'bin_output = 1'
   3 max          2 x 2 / 2   208 x 208 x  32   ->   104 x 104 x  32 0.001 BF
   4 conv     64  3 x 3 / 1   104 x 104 x  32   ->   104 x 104 x  64 0.399 BF
Unused field: 'bin_output = 1'
   5 max          2 x 2 / 2   104 x 104 x  64   ->    52 x  52 x  64 0.001 BF
   6 conv    128  3 x 3 / 1    52 x  52 x  64   ->    52 x  52 x 128 0.399 BF
Unused field: 'bin_output = 1'
   7 max          2 x 2 / 2    52 x  52 x 128   ->    26 x  26 x 128 0.000 BF
   8 conv    256  3 x 3 / 1    26 x  26 x 128   ->    26 x  26 x 256 0.399 BF
   9 max          2 x 2 / 2    26 x  26 x 256   ->    13 x  13 x 256 0.000 BF
  10 conv    512  3 x 3 / 1    13 x  13 x 256   ->    13 x  13 x 512 0.399 BF
Unused field: 'bin_output = 1'
  11 max          2 x 2 / 1    13 x  13 x 512   ->    13 x  13 x 512 0.000 BF
  12 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
Unused field: 'bin_output = 1'
  13 conv    256  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 256 0.089 BF
  14 conv    512  3 x 3 / 1    13 x  13 x 256   ->    13 x  13 x 512 0.399 BF
  15 conv     18  1 x 1 / 1    13 x  13 x 512   ->    13 x  13 x  18 0.003 BF
  16 yolo
  17 route  13
  18 conv    128  1 x 1 / 1    13 x  13 x 256   ->    13 x  13 x 128 0.011 BF
  19 upsample            2x    13 x  13 x 128   ->    26 x  26 x 128
  20 route  19 8
  21 conv    256  3 x 3 / 1    26 x  26 x 384   ->    26 x  26 x 256 1.196 BF
  22 conv     18  1 x 1 / 1    26 x  26 x 256   ->    26 x  26 x  18 0.006 BF
  23 yolo
Total BFLOPS 5.448
Loading weights from tiny-xnor_2000.weights...
 seen 32
Done!
video file: E:\test\1.mp4
Video stream: 1280 x 720

[AlexeyAB]

Update your code from GitHub to use the latest version of XNOR-net. It is still in progress.

[dexception]

8bit quantization is 30% faster but how fast is 1bit for yolov3_xnor ?

Also I have noticed there is no cfg file for yolov3-xnor ?

[AlexeyAB]

@dexception

I didn't well tested yolov3-tiny-xnor. But I tested yolov2-tiny-xnor.

For https://github.com/AlexeyAB/darknet/blob/master/cfg/tiny-yolo_xnor.cfg at the moment

• 3x-4x times on CPU (+300% faster) if is used AVX=1 in the Makefile
• 1.2-2.0x faster on GPU (+20% - +100% faster), it depends on GPU, and it will be improved

[dexception]

@AlexeyAB So there is no xnor version of the full yolov3 model ?