search

msight-tech / research-charnet

CharNet: Convolutional Character Networks
Other
610 stars 142 forks source link

Training mode error #30

Open drahmad89 opened 4 years ago

drahmad89 commented 4 years ago

I have added a training module and I noticed when forwarding the hourglass88 with torch.no_grad it works just fine but when removing torch.no_grad the gpu (12GB) run out of memory just by forwarding one image sample. I get this message:

RuntimeError: CUDA out of memory. Tried to allocate 46.00 MiB (GPU 0; 10.91 GiB total capacity; 10.21 GiB already allocated; 44.75 MiB free; 92.41 MiB cached).

It seems by the paper that you training not 1 but 4 images per mini-batch.

ashishgupta2598 commented 4 years ago

Hii, Is the training code available!!! Thanks

chenzeng11 commented 4 years ago

Hi, could you share your training code? Thank you!

HHeracles commented 3 years ago

@drahmad89 Hi, could you share your training code? Thank you!

XFGforever commented 3 years ago

@drahmad89 Hi, could you share your training code? Thank you!