Number of parameters inconsistent with the paper? about indexnet_matting HOT 4 CLOSED

Hi @yinmustark,
I just run the code on my computer. The model parameter is indeed 8.15M and GFLOPs is 6.2988.
When setting use_nonlinear=False, use_context=False, #Param=4.27M, GFLOPs=4.34; when use_nonlinear=False, use_context=True, #Param=5.12M, GFLOPs=5.82.

Maybe double check your code.

from indexnet_matting.

Hi @yinmustark,
I just run the code on my computer. The model parameter is indeed 8.15M and GFLOPs is 6.2988.
When setting use_nonlinear=False, use_context=False, #Param=4.27M, GFLOPs=4.34; when use_nonlinear=False, use_context=True, #Param=5.12M, GFLOPs=5.82.

Maybe double check your code.

Thanks for your reply!
I redownloaded your repo and ran the hlmobilenetv2.py file. I only changed "decoder='indexnet'". The result of "nonlinear+context" is still what I posted,, while the other two results are totally correct.
I think the model itself is nothing wrong because the pretrained model can be loaded successfully.

from indexnet_matting.

@yinmustark,
I figure out the problem. You're right.
In my original research code, I doubled the number of channels of the second convolutional layer in the index block under the m2o-depthwise-nonlinear-context setting, which is where I report the #parameters.
Afterwards, I find that this intermediate layer does not affect the performance, so I keep the dimension the same in the final version, but forget to modify the #Param.
This is not a big problem. But still thanks for mentioning this to others.

from indexnet_matting.

Problem solved.
Thanks anyway : )

from indexnet_matting.