Looking at src/parse.c, this happens because the h and w don't match up for the 4 different layers (82 80 78 77) feeding into the route layer (83) preceding the convolutional layer. In other instances of a route layer having multiple arguments, h and w are the same for the different sources while only c is allowed to differ (and is summed for the output).

Could there have been a change to parsing that wasn't committed along with this new config file?

Confirm, the same issue

Sorry, i messed with maxpool layers a bit, should be fixed now from e209b3b

@pjreddie

Now it`s works, thank you!

@pjreddie
Does it brake [maxpool]-layer with stride=1 in the yolov3-tiny.cfg?

• It was pad_mode = SAME (in terms of Caffe/Tensorflow) in the Darknet

  darknet/src/maxpool_layer.c

  Lines 30 to 31 in 49ba88d

  	l.out_w = (w + 2*padding)/stride;
  	l.out_h = (h + 2*padding)/stride;

• But currently with new fix

  darknet/src/maxpool_layer.c

  Lines 30 to 31 in e209b3b

  	l.out_w = (w + 2*padding - size)/stride + 1;
  	l.out_h = (h + 2*padding - size)/stride + 1;

• the pad_mode = VALID (in terms of Caffe/Tensorflow) should be: https://www.tensorflow.org/api_guides/python/nn#Convolution

 l.out_w = (w - size + 1)/stride; 
 l.out_h = (h - size + 1)/stride; 

https://stackoverflow.com/a/37675359/1558037

well hm....

I have a fix but i'd have to commit everything i've been working on and i'm not sure if it breaks stuff, let me check

It is distinctly possible that b13f67b fixes this

@pjreddie Thanks

But why is there int w_offset = -pad/2; in the maxpool_layer_kernels.cu

• b13f67b#diff-9b5ceb8892a4a6227260f670a226d503R27
• b13f67b#diff-9b5ceb8892a4a6227260f670a226d503R69

But there is int w_offset = -l.pad/l.stride; in the maxpool_layer.c

• b13f67b#diff-9f8eac4bd4bbc86cabfe69de7a0a7a60R82

Are you going to update the cfg and weights or are they unaffected?

ERROR :
cifar_small
1
First section must be [net] or [network]: No error
assertion "0" failed: file "./src/utils.c", line 256, function: ### ### error
Aborted (core dumped)

still exist while training cifar

Hello,
I am trying to train the model using yolov3 with image resolution 200200 and I'm getting no results when I used the yolov3 .cfg after changing the number of classes. If I change the width and height in the config file from 608 * 608 to 200200 respectively, I'm getting an error
87 Layer before convolutional layer must output image.: File exists
darknet: ./src/utils.c:256: error: Assertion `0' failed.

@shouryasimha width and height should be multiple of 32 due to 5 subsampling layers. pow(2,5)=32