RuntimeError: Need input.size[1] == 3 but got 4 instead.

[lclin1010]

When I run :

python demo.py --model_name DenseASPP161 --model_path ./weights/denseASPP161.pkl --img_dir ./img

I got this:

loading pre-trained weight
1.png
Traceback (most recent call last):
File "demo.py", line 19, in
infer.folder_inference(args.img_dir, is_multiscale=False)
File "/home/dl/code/DenseASPP/inference.py", line 71, in folder_inference
pre = self.single_inference(img)
File "/home/dl/code/DenseASPP/inference.py", line 94, in single_inference
pre = self.seg_model.forward(image)
File "/home/dl/code/DenseASPP/models/DenseASPP.py", line 114, in forward
feature = self.features(_input)
File "/home/dl/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/home/dl/anaconda2/lib/python2.7/site-packages/torch/nn/modules/container.py", line 67, in forward
input = module(input)
File "/home/dl/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/home/dl/anaconda2/lib/python2.7/site-packages/torch/nn/modules/conv.py", line 254, in forward
self.padding, self.dilation, self.groups)
File "/home/dl/anaconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 52, in conv2d
return f(input, weight, bias)
RuntimeError: Need input.size[1] == 3 but got 4 instead.

Do you know what is the problem? Thank you!