You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The flag settings in the README were tested with a host having 8 V100 GPUs connected, so that would be for 16G of RAM. If you have fewer GPUs or less memory, you can adapt the --accum_steps flag accordingly (e.g. --accum_steps=$((8*16)) if you have a single GPU with 16G of RAM). For inference you'll need less RAM, so you can try to decrease the --accum_steps flag until you run out of memory. Note that you can also change the --batch_size flag, but for training you will then also need to find a new value for the learning rate.
Hi, authors,
What are the minimum GPU memory required for running vision_transformer during inference and training, respectively?
The text was updated successfully, but these errors were encountered: