I feel it is slow when training.

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

I feel it is slow when training. #30

Open xuehuachunsheng opened 4 years ago

xuehuachunsheng commented 4 years ago

When I train the TNet, I feel frustrated because the train speed is too slow. I use 'aisegmentcom-matting-human-datasets' to train this model (the number of images is about 34000), batch_size=8, nearly 4400 batches per one epoch. Totally 300 epochs may train about 15 days. Is it normal? Or actually 300 epochs is no necessary?

xuehuachunsheng commented 4 years ago

Single GPU using 1080Ti。

tsing90 commented 4 years ago

what's the resolution of your input? usually the model tends to converge after 50 epochs

xuehuachunsheng commented 4 years ago

I use 800x600 HxW size of image to train the model's T-Net stage, but the trimap seems not too good. Is it normal？