We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters
Hello! I am inspired by your great work.
I found that it might be beneficial to use DDP, but it does not seem to have been implemented in your code. I tried to use DDP or PytorchLightning, but both seem to get stuck in the progress:
DDP: stuck in the line DDP(system)
Lightning: stuck in "[rank: 0] Seed set to 42
Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/2"
Would you please help me out by telling me how to DDP? Thanks!
Hello! I am inspired by your great work. I found that it might be beneficial to use DDP, but it does not seem to have been implemented in your code. I tried to use DDP or PytorchLightning, but both seem to get stuck in the progress: DDP: stuck in the line DDP(system) Lightning: stuck in "[rank: 0] Seed set to 42 Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/2"
Would you please help me out by telling me how to DDP? Thanks!