{ "models": { "encoder": { "name": "SparseUnetVaeEncoder", "args": { "in_channels": 6, "model_channels": [64, 128, 256, 512, 1024], "latent_channels": 32, "num_blocks": [0, 4, 8, 16, 4], "block_type": [ "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d" ], "down_block_type": [ "SparseResBlockS2C3d", "SparseResBlockS2C3d", "SparseResBlockS2C3d", "SparseResBlockS2C3d" ], "block_args": [ { "use_checkpoint": true }, { "use_checkpoint": true }, { "use_checkpoint": false }, { "use_checkpoint": false }, { "use_checkpoint": false } ], "use_fp16": true } }, "decoder": { "name": "SparseUnetVaeDecoder", "args": { "out_channels": 6, "model_channels": [1024, 512, 256, 128, 64], "latent_channels": 32, "num_blocks": [4, 16, 8, 4, 0], "block_type": [ "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d", "SparseConvNeXtBlock3d" ], "up_block_type": [ "SparseResBlockC2S3d", "SparseResBlockC2S3d", "SparseResBlockC2S3d", "SparseResBlockC2S3d" ], "block_args": [ { "use_checkpoint": false }, { "use_checkpoint": false }, { "use_checkpoint": false }, { "use_checkpoint": true }, { "use_checkpoint": true } ], "use_fp16": true, "pred_subdiv": false } } }, "dataset": { "name": "SparseVoxelPbrDataset", "args": { "resolution": 256, "min_aesthetic_score": 4.5, "max_active_voxels": 1000000, "max_num_faces": 1000000, "with_mesh": false, "attrs": [ "base_color", "metallic", "roughness", "alpha" ] } }, "trainer": { "name": "PbrVaeTrainer", "args": { "max_steps": 1000000, "batch_size_per_gpu": 8, "batch_split": 1, "optimizer": { "name": "AdamW", "args": { "lr": 1e-4, "weight_decay": 0.0 } }, "ema_rate": [ 0.9999 ], "fp16_mode": "inflat_all", "fp16_scale_growth": 0.001, "grad_clip": { "name": "AdaptiveGradClipper", "args": { "max_norm": 1.0, "clip_percentile": 95 } }, "i_log": 500, "i_sample": 10000, "i_save": 10000, "lambda_kl": 1e-6, "loss_type": "l1", "lambda_render": 0.0 } } }