search

mcahny / Deep-Video-Inpainting

Official pytorch implementation for "Deep Video Inpainting" (CVPR 2019)
508 stars 95 forks source link

Can batch size only be set to 1 when you train? #20

Closed daisy-disc closed 4 years ago

mcahny commented 4 years ago

I used bs=16 for single time step training (only feature aggregation), and bs=4 for recurrent training (time step = 4).