Forward_backward expects cond dictionary even if we want to train without conditions

[TolgaAktas]

I am trying to train the improved DDPM without class-conditionals but setting the condition to False doesn't let me skip the following error. Am I missing something?

File "/home/diffusion_experiments/improved_ddpm_experiments/main.py", line 237, in main() File "/home/diffusion_experiments/improved_ddpm_experiments/main.py", line 233, in main ).run_loop() File "/home/diffusion_experiments/improved_ddpm_experiments/improved_diffusion/train_util.py", line 167, in run_loop self.run_step(batch, cond) File "/home/diffusion_experiments/improved_ddpm_experiments/improved_diffusion/train_util.py", line 181, in run_step self.forward_backward(batch, cond) File "/home/diffusion_experiments/improved_ddpm_experiments/improved_diffusion/train_util.py", line 194, in forward_backward for k, v in cond.items() AttributeError: 'NoneType' object has no attribute 'items'