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
sample.py's implementation depends on K.evaluation.compute_features() and it generates n samples and return them in the memory at once. And it looks not efficient in terms of memoy usage. It should save a chunk of generate image files and free or reuse the memory instead before it generates and gathers all the samples in the memory.
The text was updated successfully, but these errors were encountered:
Yea I'm getting CUDA OOM errors after I sample my first batch because the second batch doubles the VRAM usage, and the 3rd batch triples it, etc. Wasn't expecting this behavior. For now, I guess I'll wrap sample.py in loop in a shell script and only let n = batch_size when calling sample.
sample.py's implementation depends on
K.evaluation.compute_features()
and it generatesn
samples and return them in the memory at once. And it looks not efficient in terms of memoy usage. It should save a chunk of generate image files and free or reuse the memory instead before it generates and gathers all the samples in the memory.The text was updated successfully, but these errors were encountered: