Error with shortcut layer in yolov3

I face the following error with this line
x = outputs[i-1] + outputs[i+from_]
RuntimeError: The size of tensor a (210) must match the size of tensor b (208) at non-singleton dimension 3

Is outputs a list containing tensors with different shapes?
If so, you would have to make sure the shapes are equal on the tensors, which should be added together. Otherwise this shape mismatch error will be raised.

I’m beginner. I try to run the model in that link:

the output is dictionary caches the outputs for the route layer