| { | |
| "bs_dim": 96, | |
| "train_xy": false, | |
| "feature_dim": 832, | |
| "period": 30, | |
| "max_seq_len": 5000, | |
| "batch_size": 48, | |
| "gpu0_bs": 6, | |
| "valid_batch_size": 8, | |
| "experiment_name": "diffusion_posiguide_hubertbase_tf2", | |
| "data_root": "/mnt/ssd/PianoPose-new", | |
| "preload": true, | |
| "tiny": false, | |
| "adjust": true, | |
| "use_midiguide": false, | |
| "is_random": true, | |
| "return_beta": false, | |
| "up_list": [ | |
| "1467634", | |
| "66685747" | |
| ], | |
| "continue_train": false, | |
| "wav2vec_path": "facebook/hubert-large-ls960-ft", | |
| "piano2posi_path": "logs/piano2posi_hubertbase_tf", | |
| "timesteps": 1000, | |
| "fine_map": 0, | |
| "unet_dim": 256, | |
| "xyz_guide": true, | |
| "remap_noise": true, | |
| "RAG": false, | |
| "hidden_type": "audio_f", | |
| "latest_layer": "tanh", | |
| "encoder_type": "transformer", | |
| "num_layer": 4, | |
| "loss_mode": "naive_l1", | |
| "weight_rec": 1.0, | |
| "weight_vel": 1.0, | |
| "iterations": 100000, | |
| "train_sec": 8, | |
| "lr": 5e-05, | |
| "check_val_every_n_iteration": 1000, | |
| "limit_val_batches": 0.6, | |
| "save_every_n_iteration": 1000, | |
| "save_top_k": 5, | |
| "logdir": "logs" | |
| } |