search

tsing90 / pytorch_semantic_human_matting

This is an unofficial implementation of the paper "Semantic human matting":
https://arxiv.org/pdf/1809.01354.pdf
83 stars 18 forks source link

about load pretrained model when training end to end #13

Closed wrrJasmine closed 5 years ago

wrrJasmine commented 5 years ago

when I training the end to end model , I can not load the pretrain model of t_net and m_net! there is not define the t_path and m_path. but after I defined, there is another error occured.

wrrJasmine commented 5 years ago

the error is 'net_T' object has no attribute 'copy'

tsing90 commented 5 years ago

bug fixed, the missing code in the class Train_log() has been added