Open insomniaaac opened 5 months ago
I have a batch of data to process.
python launch.py --config custom/threestudio-mvimg-gen/configs/stable-zero123.yaml --train --gpu 0 data.image_path=./load/images/000001_rgba.png python launch.py --config custom/threestudio-mvimg-gen/configs/stable-zero123.yaml --train --gpu 0 data.image_path=./load/images/000002_rgba.png
it will load model twice.
Does there any why to process data one by one without reload model?
Moreover, if i want to distribute my data to multi-gpu, how can i do?
I have a batch of data to process.
it will load model twice.
Does there any why to process data one by one without reload model?
Moreover, if i want to distribute my data to multi-gpu, how can i do?