Error in Visualize_video.py when using result/SINet/SINet.pth about ext_portrait_segmentation

[cyf518]

same issue

[qiutzh]

@cyf518 Hi, did you solve the problem?

[cyf518]

@qiutzh
i change net = Dnc_SINet(classes=1, p=2, q=8, chnn=1) to net = Dnc_SINet(classes=2, p=2, q=8, chnn=1)

[YAwei666]

@qiutzh
i change net = Dnc_SINet(classes=1, p=2, q=8, chnn=1) to net = Dnc_SINet(classes=2, p=2, q=8, chnn=1)
RuntimeError: weight tensor should be defined either for all or no classes at /pytorch/aten/src/THCUNN/generic/SpatialClassNLLCriterion.cu:27
when I changed this,another problem accurs. do you know how to solve this ?

[aguthrie19]

It looks like at least one of these, maybe both, is incorrect:

• the "chnn" integer in your .json (ex setting/SINet.json or whichever you're using when loading your model)
• or the "resume" checkpoint in your .json (ex result/training_session/checkpoint.pth.tar)

For whatever reason, your code is trying to combine a SINet.pth model with a checkpoint model, but it can't because SINet.pth expects 2 channels and your checkpoint provides configurations for only 1 channel.

Hope this helps! Share a snippet of the code you're running for more help.