search

cyclomon / UNSB

Official Repository of "Unpaired Image-to-Image Translation via Neural Schrödinger Bridge" (ICLR 2024)
MIT License
154 stars 5 forks source link

Multi GPU Training #6

Closed JigneshChowdary closed 1 year ago

JigneshChowdary commented 1 year ago

Hi, I want to train our approach on two gpu. So I have provided the GPU IDs in train options. But I am getting this error " raceback (most recent call last): File "train.py", line 44, in model.data_dependent_initialize(data,data2) File "models/sb_model.py", line 106, in data_dependent_initialize self.forward() # compute fake images: G(A) File "models/sb_model.py", line 184, in forward for t in range(self.time_idx.int().item()+1): ValueError: only one element tensors can be converted to Python scalars "

Can you help me in this regard

cyclomon commented 1 year ago

Hi, in this version, the training process is available with only single GPU and batch size of 1.

We will upload more generalized version later.

Sorry for inconvenience.

MasalaKimchi commented 1 year ago

Hi, astounding works on new unpaired translation methods!

My group was wondering if you have any plans on updating the codes to provide for multi-gpu training anytime soon.

best,