How much memory is required during training and inference？

jiwoon-ahn / psa

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

MIT License

380 stars 62 forks source link

Closed zhwis closed 6 years ago

zhwis commented 6 years ago

Thanks. The computer stops responding when I take the second step

jiwoon-ahn commented 6 years ago

Not much memory is required on a VGG-16 based network, but you still need a decent GPU device. In my setting, it takes less than 4GB GPU memory.