Potential validation/testing leakage due to the absence of switching between train and eval modes

[jinhaoduan]

Thanks for releasing the code.

I noticed that there's no switching between model.train() mode and model.eval() mode when transitioning between the training and validation processes. Could this potentially lead to leakage of validation/test information (BN will track the statistics in the validation/testing set)?

Another minor issue is the incorrect parameter in

SynDiff/train.py

Line 699 in 8e5064e

fake_sample1 = sample_from_model(pos_coeff, gen_diffusive_1, args.num_timesteps, x1_t, T, args)

The generator should be gen_diffusive_2 for T1 -> T2, right?