| dataset_params: | |
| im_path: "/home/taruntejaneurips23/Ashish/datasets/CelebA/img_align_celeba/img_align_celeba" | |
| im_channels: 3 | |
| im_size: 28 | |
| diffusion_params: | |
| num_timesteps: 1000 | |
| beta_start: 0.0015 | |
| beta_end: 0.0195 | |
| ldm_params: | |
| down_channels: [128, 256, 256, 256] | |
| mid_channels: [256, 256] | |
| down_sample: [False, False, False] | |
| attn_down: [True, True, True] | |
| time_emb_dim: 256 | |
| norm_channels: 32 | |
| num_heads: 16 | |
| conv_out_channels: 128 | |
| num_down_layers: 2 | |
| num_mid_layers: 2 | |
| num_up_layers: 2 | |
| autoencoder_params: | |
| z_channels: 3 | |
| codebook_size: 20 | |
| down_channels: [32, 64, 128] | |
| mid_channels: [128, 128] | |
| down_sample: [True, True] | |
| attn_down: [False, False] | |
| norm_channels: 32 | |
| num_heads: 16 | |
| num_down_layers: 2 | |
| num_mid_layers: 2 | |
| num_up_layers: 2 | |
| train_params: | |
| seed: 4242 | |
| task_name: 'MnistLDM' | |
| ldm_batch_size: 9 | |
| autoencoder_batch_size: 32 | |
| disc_start: 1000 | |
| disc_weight: 0.5 | |
| codebook_weight: 1 | |
| commitment_beta: 0.2 | |
| perceptual_weight: 1 | |
| kl_weight: 0.000005 | |
| ldm_epochs: 10 | |
| autoencoder_epochs: 10 | |
| num_samples: 9 | |
| num_grid_rows: 3 | |
| ldm_lr: 0.00001 | |
| autoencoder_lr: 0.0001 | |
| autoencoder_acc_steps: 1 | |
| autoencoder_img_save_steps: 8 | |
| save_latents: True | |
| vqvae_latent_dir_name: 'vqvae_latents' | |
| ldm_ckpt_name: 'ddpm_ckpt.pth' | |
| vqvae_autoencoder_ckpt_name: 'vqvae_autoencoder_ckpt.pth' | |
| vqvae_discriminator_ckpt_name: 'vqvae_discriminator_ckpt.pth' | |
| checkpoint_dir: './' | |
| training: | |
| _continue_: True | |