| weight = 'weights/volt-small-scannet.pth' |
| resume = False |
| evaluate = True |
| test_only = False |
| seed = 5793371 |
| save_path = 'exp/scannet/2026-07-23_152153' |
| num_worker = 16 |
| batch_size = 8 |
| gradient_accumulation_steps = 1 |
| batch_size_val = None |
| batch_size_test = None |
| epoch = 75 |
| eval_epoch = 75 |
| clip_grad = 10.0 |
| use_ema = False |
| ema_decay = 0.999 |
| dataset_ratios = None |
| sync_bn = False |
| enable_amp = True |
| amp_dtype = 'float16' |
| empty_cache = False |
| empty_cache_per_epoch = False |
| find_unused_parameters = True |
| enable_wandb = True |
| wandb_project = 'Volt' |
| wandb_key = None |
| mix_prob = 0.8 |
| param_dicts = None |
| hooks = [ |
| dict( |
| type='CheckpointLoader', |
| keywords='module.backbone', |
| replacement='module.backbone'), |
| dict(type='IterationTimer', warmup_iter=2), |
| dict(type='InformationWriter'), |
| dict( |
| type='InsSegEvaluator', |
| segment_ignore_index=(-1, 0, 1), |
| instance_ignore_index=-1), |
| dict(type='CheckpointSaver', save_freq=None), |
| dict(type='PreciseEvaluator', test_last=False) |
| ] |
| train = dict(type='DefaultTrainer') |
| test = dict( |
| type='InsSegTester', |
| verbose=True, |
| segment_ignore_index=(-1, 0, 1), |
| instance_ignore_index=-1) |
| CLASS_LABELS_20 = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', |
| 'door', 'window', 'bookshelf', 'picture', 'counter', 'desk', |
| 'curtain', 'refrigerator', 'shower curtain', 'toilet', |
| 'sink', 'bathtub', 'otherfurniture') |
| VALID_CLASS_IDS_20 = (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, |
| 33, 34, 36, 39) |
| class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', |
| 'door', 'window', 'bookshelf', 'picture', 'counter', 'desk', |
| 'curtain', 'refrigerator', 'shower curtain', 'toilet', 'sink', |
| 'bathtub', 'otherfurniture') |
| class_ids = (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34, 36, |
| 39) |
| num_classes = 20 |
| segment_ignore_index = (-1, 0, 1) |
| semantic_num_classes = 18 |
| num_channels = 128 |
| model = dict( |
| type='SPFormer-v1m1', |
| backbone=dict( |
| type='Volt', |
| in_channels=6, |
| embed_dim=384, |
| depth=12, |
| num_heads=6, |
| mlp_ratio=4, |
| init_values=None, |
| qk_norm=True, |
| drop_path=0.3, |
| stride=5, |
| kernel_size=5, |
| increase_drop_path=True, |
| up_mlp_dim=128), |
| decoder=dict( |
| type='SPFormerDecoder', |
| num_class=18, |
| in_channel=128, |
| num_layer=6, |
| num_query=400, |
| d_model=384, |
| nhead=8, |
| hidden_dim=1024, |
| dropout=0.0, |
| activation_fn='gelu', |
| iter_pred=True, |
| attn_mask=True, |
| use_query_pos=False, |
| use_score=False, |
| use_param_query=True), |
| criterion=dict( |
| type='SPFormerCriterion', |
| matcher=dict( |
| type='SPFormerHungarianMatcher', |
| costs=[ |
| dict(type='SPFormerQueryClassificationCost', weight=0.5), |
| dict(type='SPFormerMaskBCECost', weight=1.0), |
| dict(type='SPFormerMaskDiceCost', weight=1.0) |
| ]), |
| loss_weight=[0.2, 1.0, 1.0, 0.5], |
| num_classes=18, |
| non_object_weight=0.1, |
| fix_dice_loss_weight=False, |
| iter_matcher=True, |
| fix_mean_loss=True), |
| semantic_num_classes=18, |
| semantic_ignore_index=-1, |
| segment_ignore_index=(-1, 0, 1), |
| instance_ignore_index=-1, |
| topk_insts=100, |
| score_thr=0.0, |
| npoint_thr=100, |
| nms=True) |
| optimizer = dict(type='AdamW', lr=0.0003, weight_decay=0.1) |
| scheduler = dict(type='PolyLR') |
| dataset_type = 'ScanNetDataset' |
| data_root = 'data/scannet' |
| data = dict( |
| num_classes=20, |
| ignore_index=-1, |
| names=('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', 'door', |
| 'window', 'bookshelf', 'picture', 'counter', 'desk', 'curtain', |
| 'refrigerator', 'shower curtain', 'toilet', 'sink', 'bathtub', |
| 'otherfurniture'), |
| ids=(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34, 36, |
| 39), |
| train=dict( |
| type='ScanNetDataset', |
| split='train', |
| data_root='data/scannet', |
| transform=[ |
| dict(type='CenterShift', apply_z=True), |
| dict( |
| type='RandomDropout', |
| dropout_ratio=0.2, |
| dropout_application_ratio=0.5), |
| dict(type='RandomFlip', p=0.5), |
| dict( |
| type='RandomRotate', |
| angle=[-1, 1], |
| axis='z', |
| center=[0, 0, 0], |
| p=0.95), |
| dict( |
| type='RandomRotate', |
| angle=[-0.041666666666666664, 0.041666666666666664], |
| axis='x', |
| p=0.95), |
| dict( |
| type='RandomRotate', |
| angle=[-0.041666666666666664, 0.041666666666666664], |
| axis='y', |
| p=0.95), |
| dict(type='RandomScale', scale=[0.8, 1.2]), |
| dict( |
| type='RandomShift', |
| shift=[(-0.5, 0.5), (-0.5, 0.5), (-0.5, 0.5)]), |
| dict( |
| type='ElasticDistortion', |
| distortion_params=[[0.2, 0.4], [0.8, 1.6]]), |
| dict(type='ChromaticAutoContrast', p=0.5, blend_factor=None), |
| dict(type='ChromaticTranslation', p=0.95, ratio=0.1), |
| dict(type='ChromaticJitter', p=0.95, std=0.05), |
| dict(type='SphereCrop', sample_rate=0.6, mode='random'), |
| dict(type='SphereCrop', point_max=102400, mode='random'), |
| dict( |
| type='Copy', |
| keys_dict=dict( |
| coord='origin_coord', |
| instance='origin_instance', |
| segment='origin_segment')), |
| dict( |
| type='Update', |
| keys_dict=dict(index_valid_keys=[ |
| 'coord', 'color', 'normal', 'strength', 'segment', |
| 'instance', 'image_coord', 'image_mask' |
| ])), |
| dict( |
| type='GridSample', |
| grid_size=0.02, |
| hash_type='fnv', |
| mode='train', |
| return_grid_coord=True, |
| return_inverse=True), |
| dict(type='NormalizeColor'), |
| dict( |
| type='InstanceParser', |
| segment_ignore_index=(-1, 0, 1), |
| instance_ignore_index=-1), |
| dict(type='ToTensor'), |
| dict( |
| type='Collect', |
| keys=('coord', 'origin_coord', 'grid_coord', 'segment', |
| 'origin_segment', 'instance', 'origin_instance', |
| 'superpoint', 'inverse'), |
| feat_keys=('color', 'normal'), |
| offset_keys_dict=dict( |
| offset='coord', origin_offset='origin_coord')) |
| ], |
| test_mode=False, |
| loop=1), |
| val=dict( |
| type='ScanNetDataset', |
| split='val', |
| data_root='data/scannet', |
| transform=[ |
| dict(type='MeanShift'), |
| dict( |
| type='RandomRotate', |
| angle=[0.35, 0.35], |
| axis='z', |
| center=[0, 0, 0], |
| always_apply=True), |
| dict( |
| type='Copy', |
| keys_dict=dict( |
| coord='origin_coord', |
| instance='origin_instance', |
| segment='origin_segment')), |
| dict( |
| type='Update', |
| keys_dict=dict(index_valid_keys=[ |
| 'coord', 'color', 'normal', 'strength', 'segment', |
| 'instance', 'image_coord', 'image_mask' |
| ])), |
| dict( |
| type='GridSample', |
| grid_size=0.02, |
| hash_type='fnv', |
| mode='train', |
| deterministic=True, |
| return_grid_coord=True, |
| return_inverse=True), |
| dict(type='NormalizeColor'), |
| dict( |
| type='InstanceParser', |
| segment_ignore_index=(-1, 0, 1), |
| instance_ignore_index=-1), |
| dict(type='ToTensor'), |
| dict( |
| type='Collect', |
| keys=('coord', 'origin_coord', 'grid_coord', 'segment', |
| 'origin_segment', 'instance', 'origin_instance', |
| 'superpoint', 'inverse', 'name'), |
| feat_keys=('color', 'normal'), |
| offset_keys_dict=dict( |
| offset='coord', origin_offset='origin_coord')) |
| ], |
| test_mode=False), |
| test=dict( |
| type='ScanNetDataset', |
| split='val', |
| data_root='data/scannet', |
| transform=[ |
| dict(type='MeanShift'), |
| dict( |
| type='RandomRotate', |
| angle=[0.35, 0.35], |
| axis='z', |
| center=[0, 0, 0], |
| always_apply=True), |
| dict( |
| type='Copy', |
| keys_dict=dict( |
| coord='origin_coord', |
| instance='origin_instance', |
| segment='origin_segment')), |
| dict( |
| type='Update', |
| keys_dict=dict(index_valid_keys=[ |
| 'coord', 'color', 'normal', 'strength', 'segment', |
| 'instance', 'image_coord', 'image_mask' |
| ])), |
| dict( |
| type='GridSample', |
| grid_size=0.02, |
| hash_type='fnv', |
| mode='train', |
| deterministic=True, |
| return_grid_coord=True, |
| return_inverse=True), |
| dict(type='NormalizeColor'), |
| dict( |
| type='InstanceParser', |
| segment_ignore_index=(-1, 0, 1), |
| instance_ignore_index=-1), |
| dict(type='ToTensor'), |
| dict( |
| type='Collect', |
| keys=('coord', 'origin_coord', 'grid_coord', 'segment', |
| 'origin_segment', 'instance', 'origin_instance', |
| 'superpoint', 'inverse', 'name'), |
| feat_keys=('color', 'normal'), |
| offset_keys_dict=dict( |
| offset='coord', origin_offset='origin_coord')) |
| ], |
| test_mode=False)) |
| num_worker_per_gpu = 8 |
| batch_size_per_gpu = 4 |
| batch_size_val_per_gpu = 1 |
| batch_size_test_per_gpu = 1 |
|
|
