| { | |
| "models": { | |
| "decoder": { | |
| "name": "SparseUnetVaeDecoder", | |
| "args": { | |
| "out_channels": 32, | |
| "model_channels": [ | |
| 1280, | |
| 640, | |
| 160 | |
| ], | |
| "latent_channels": 64, | |
| "num_blocks": [ | |
| 8, | |
| 6, | |
| 4 | |
| ], | |
| "block_type": [ | |
| "SparseConvNeXtBlock3d", | |
| "SparseConvNeXtBlock3d", | |
| "SparseConvNeXtBlock3d" | |
| ], | |
| "up_block_type": [ | |
| "SparseResBlockC2S3d", | |
| "SparseResBlockC2S3d" | |
| ], | |
| "block_args": [ | |
| { | |
| "use_checkpoint": false | |
| }, | |
| { | |
| "use_checkpoint": false | |
| }, | |
| { | |
| "use_checkpoint": false | |
| } | |
| ], | |
| "use_fp16": true, | |
| "pred_subdiv": true | |
| } | |
| } | |
| }, | |
| "dataset": { | |
| "args": { | |
| "normalization": { | |
| "mean": [ | |
| 0.781296, | |
| 0.018091, | |
| -0.495192, | |
| -0.558457, | |
| 1.06053, | |
| 0.093252, | |
| 1.518149, | |
| -0.933218, | |
| -0.732996, | |
| 2.604095, | |
| -0.118341, | |
| -2.143904, | |
| 0.495076, | |
| -2.179512, | |
| -2.130751, | |
| -0.996944, | |
| 0.261421, | |
| -2.217463, | |
| 1.260067, | |
| -0.150213, | |
| 3.790713, | |
| 1.481266, | |
| -1.046058, | |
| -1.523667, | |
| -0.059621, | |
| 2.22078, | |
| 1.621212, | |
| 0.87723, | |
| 0.567247, | |
| -3.175944, | |
| -3.186688, | |
| 1.578665 | |
| ], | |
| "std": [ | |
| 5.972266, | |
| 4.706852, | |
| 5.44501, | |
| 5.209927, | |
| 5.32022, | |
| 4.547237, | |
| 5.020802, | |
| 5.444004, | |
| 5.226681, | |
| 5.683095, | |
| 4.831436, | |
| 5.286469, | |
| 5.652043, | |
| 5.367606, | |
| 5.525084, | |
| 4.730578, | |
| 4.805265, | |
| 5.124013, | |
| 5.530808, | |
| 5.619001, | |
| 5.10393, | |
| 5.41767, | |
| 5.269677, | |
| 5.547194, | |
| 5.634698, | |
| 5.235274, | |
| 6.110351, | |
| 5.511298, | |
| 6.237273, | |
| 4.879207, | |
| 5.347008, | |
| 5.405691 | |
| ] | |
| } | |
| } | |
| }, | |
| "trainer": { | |
| "args": { | |
| "ema_rate": 0.9999 | |
| } | |
| } | |
| } | |