| { | |
| "experiment": { | |
| "tokenizer_checkpoint": "tokenizer_titok_l32.bin", | |
| "generator_checkpoint": "generator_titok_l32.bin", | |
| "output_dir": "titok_l_32" | |
| }, | |
| "model": { | |
| "vq_model": { | |
| "codebook_size": 4096, | |
| "token_size": 12, | |
| "use_l2_norm": true, | |
| "commitment_cost": 0.25, | |
| "vit_enc_model_size": "large", | |
| "vit_dec_model_size": "large", | |
| "vit_enc_patch_size": 16, | |
| "vit_dec_patch_size": 16, | |
| "num_latent_tokens": 32 | |
| }, | |
| "generator": { | |
| "model_type": "ViT", | |
| "hidden_size": 768, | |
| "num_hidden_layers": 24, | |
| "num_attention_heads": 16, | |
| "intermediate_size": 3072, | |
| "dropout": 0.1, | |
| "attn_drop": 0.1, | |
| "num_steps": 8, | |
| "mask_schedule_strategy": "arccos", | |
| "class_label_dropout": 0.1, | |
| "image_seq_len": "${model.vq_model.num_latent_tokens}", | |
| "condition_num_classes": 1000, | |
| "randomize_temperature": 9.5, | |
| "guidance_scale": 4.5, | |
| "guidance_decay": "linear" | |
| } | |
| }, | |
| "dataset": { | |
| "preprocessing": { | |
| "crop_size": 256 | |
| } | |
| } | |
| } |