Upload folder using huggingface_hub

.gitattributes

@@ -41,3 +41,4 @@ nuscenes/semseg-ptv3_dino-S/test.log filter=lfs diff=lfs merge=lfs -text
 nuscenes/semseg-ptv3_dino-S/train.log filter=lfs diff=lfs merge=lfs -text
 semantic_kitti/semseg-ptv3_dino-L/train.log filter=lfs diff=lfs merge=lfs -text
 scannet200/semseg-ptv3_dino-L/train.log filter=lfs diff=lfs merge=lfs -text
+scannet200/semseg-ptv3_dinov3-L/train.log filter=lfs diff=lfs merge=lfs -text

scannet200/semseg-ptv3_dinov3-L/config.py

@@ -0,0 +1,404 @@
+weight = None
+resume = False
+evaluate = True
+test_only = False
+seed = 14931494
+save_path = 'exp/scannet200/2025-08-16_005918'
+wandb_project = 'semseg_scannet200'
+num_worker = 24
+batch_size = 12
+batch_size_val = None
+batch_size_test = None
+epoch = 800
+eval_epoch = 100
+clip_grad = None
+sync_bn = False
+enable_amp = True
+empty_cache = False
+empty_cache_per_epoch = False
+find_unused_parameters = False
+mix_prob = 0.8
+param_dicts = [dict(keyword='img_enc|block', lr=0.0006)]
+hooks = [
+    dict(type='CheckpointLoader'),
+    dict(type='IterationTimer', warmup_iter=2),
+    dict(type='InformationWriter'),
+    dict(type='SemSegEvaluator'),
+    dict(type='CheckpointSaver', save_freq=None),
+    dict(type='PreciseEvaluator', test_last=False)
+]
+train = dict(type='DefaultTrainer')
+test = dict(type='SemSegTester', verbose=True)
+CLASS_LABELS_200 = (
+    'wall', 'chair', 'floor', 'table', 'door', 'couch', 'cabinet', 'shelf',
+    'desk', 'office chair', 'bed', 'pillow', 'sink', 'picture', 'window',
+    'toilet', 'bookshelf', 'monitor', 'curtain', 'book', 'armchair',
+    'coffee table', 'box', 'refrigerator', 'lamp', 'kitchen cabinet', 'towel',
+    'clothes', 'tv', 'nightstand', 'counter', 'dresser', 'stool', 'cushion',
+    'plant', 'ceiling', 'bathtub', 'end table', 'dining table', 'keyboard',
+    'bag', 'backpack', 'toilet paper', 'printer', 'tv stand', 'whiteboard',
+    'blanket', 'shower curtain', 'trash can', 'closet', 'stairs', 'microwave',
+    'stove', 'shoe', 'computer tower', 'bottle', 'bin', 'ottoman', 'bench',
+    'board', 'washing machine', 'mirror', 'copier', 'basket', 'sofa chair',
+    'file cabinet', 'fan', 'laptop', 'shower', 'paper', 'person',
+    'paper towel dispenser', 'oven', 'blinds', 'rack', 'plate', 'blackboard',
+    'piano', 'suitcase', 'rail', 'radiator', 'recycling bin', 'container',
+    'wardrobe', 'soap dispenser', 'telephone', 'bucket', 'clock', 'stand',
+    'light', 'laundry basket', 'pipe', 'clothes dryer', 'guitar',
+    'toilet paper holder', 'seat', 'speaker', 'column', 'bicycle', 'ladder',
+    'bathroom stall', 'shower wall', 'cup', 'jacket', 'storage bin',
+    'coffee maker', 'dishwasher', 'paper towel roll', 'machine', 'mat',
+    'windowsill', 'bar', 'toaster', 'bulletin board', 'ironing board',
+    'fireplace', 'soap dish', 'kitchen counter', 'doorframe',
+    'toilet paper dispenser', 'mini fridge', 'fire extinguisher', 'ball',
+    'hat', 'shower curtain rod', 'water cooler', 'paper cutter', 'tray',
+    'shower door', 'pillar', 'ledge', 'toaster oven', 'mouse',
+    'toilet seat cover dispenser', 'furniture', 'cart', 'storage container',
+    'scale', 'tissue box', 'light switch', 'crate', 'power outlet',
+    'decoration', 'sign', 'projector', 'closet door', 'vacuum cleaner',
+    'candle', 'plunger', 'stuffed animal', 'headphones', 'dish rack', 'broom',
+    'guitar case', 'range hood', 'dustpan', 'hair dryer', 'water bottle',
+    'handicap bar', 'purse', 'vent', 'shower floor', 'water pitcher',
+    'mailbox', 'bowl', 'paper bag', 'alarm clock', 'music stand',
+    'projector screen', 'divider', 'laundry detergent', 'bathroom counter',
+    'object', 'bathroom vanity', 'closet wall', 'laundry hamper',
+    'bathroom stall door', 'ceiling light', 'trash bin', 'dumbbell',
+    'stair rail', 'tube', 'bathroom cabinet', 'cd case', 'closet rod',
+    'coffee kettle', 'structure', 'shower head', 'keyboard piano',
+    'case of water bottles', 'coat rack', 'storage organizer', 'folded chair',
+    'fire alarm', 'power strip', 'calendar', 'poster', 'potted plant',
+    'luggage', 'mattress')
+model = dict(
+    type='DefaultSegmentorV2',
+    num_classes=200,
+    backbone_out_channels=64,
+    backbone=dict(
+        type='PT-v3m1-dinov3',
+        in_channels=6,
+        order=('z', 'z-trans', 'hilbert', 'hilbert-trans'),
+        stride=(2, 2, 2, 2),
+        enc_depths=(2, 2, 2, 6, 2),
+        enc_channels=(32, 64, 128, 256, 512),
+        enc_num_head=(2, 4, 8, 16, 32),
+        enc_patch_size=(1024, 1024, 1024, 1024, 1024),
+        dec_depths=(2, 2, 2, 2),
+        dec_channels=(64, 64, 128, 256),
+        dec_num_head=(4, 4, 8, 16),
+        dec_patch_size=(1024, 1024, 1024, 1024),
+        mlp_ratio=4,
+        qkv_bias=True,
+        qk_scale=None,
+        init_values=None,
+        attn_drop=0.0,
+        proj_drop=0.0,
+        drop_path=0.3,
+        shuffle_orders=True,
+        pre_norm=True,
+        enable_rpe=False,
+        enable_flash=True,
+        upcast_attention=False,
+        upcast_softmax=False,
+        cls_mode=False,
+        pdnorm_bn=False,
+        pdnorm_ln=False,
+        pdnorm_decouple=True,
+        pdnorm_adaptive=False,
+        pdnorm_affine=True,
+        pdnorm_conditions=('ScanNet', 'S3DIS', 'Structured3D'),
+        dinov2='large',
+        image_size=(480, 640)),
+    criteria=[
+        dict(type='CrossEntropyLoss', loss_weight=1.0, ignore_index=-1),
+        dict(
+            type='LovaszLoss',
+            mode='multiclass',
+            loss_weight=1.0,
+            ignore_index=-1)
+    ])
+optimizer = dict(type='AdamW', lr=0.006, weight_decay=0.05)
+scheduler = dict(
+    type='OneCycleLR',
+    max_lr=[0.006, 0.0006],
+    pct_start=0.05,
+    anneal_strategy='cos',
+    div_factor=10.0,
+    final_div_factor=1000.0)
+dataset_type = 'ScanNet200Dataset'
+data_root = 'data/scannet'
+data = dict(
+    num_classes=200,
+    ignore_index=-1,
+    names=(
+        'wall', 'chair', 'floor', 'table', 'door', 'couch', 'cabinet', 'shelf',
+        'desk', 'office chair', 'bed', 'pillow', 'sink', 'picture', 'window',
+        'toilet', 'bookshelf', 'monitor', 'curtain', 'book', 'armchair',
+        'coffee table', 'box', 'refrigerator', 'lamp', 'kitchen cabinet',
+        'towel', 'clothes', 'tv', 'nightstand', 'counter', 'dresser', 'stool',
+        'cushion', 'plant', 'ceiling', 'bathtub', 'end table', 'dining table',
+        'keyboard', 'bag', 'backpack', 'toilet paper', 'printer', 'tv stand',
+        'whiteboard', 'blanket', 'shower curtain', 'trash can', 'closet',
+        'stairs', 'microwave', 'stove', 'shoe', 'computer tower', 'bottle',
+        'bin', 'ottoman', 'bench', 'board', 'washing machine', 'mirror',
+        'copier', 'basket', 'sofa chair', 'file cabinet', 'fan', 'laptop',
+        'shower', 'paper', 'person', 'paper towel dispenser', 'oven', 'blinds',
+        'rack', 'plate', 'blackboard', 'piano', 'suitcase', 'rail', 'radiator',
+        'recycling bin', 'container', 'wardrobe', 'soap dispenser',
+        'telephone', 'bucket', 'clock', 'stand', 'light', 'laundry basket',
+        'pipe', 'clothes dryer', 'guitar', 'toilet paper holder', 'seat',
+        'speaker', 'column', 'bicycle', 'ladder', 'bathroom stall',
+        'shower wall', 'cup', 'jacket', 'storage bin', 'coffee maker',
+        'dishwasher', 'paper towel roll', 'machine', 'mat', 'windowsill',
+        'bar', 'toaster', 'bulletin board', 'ironing board', 'fireplace',
+        'soap dish', 'kitchen counter', 'doorframe', 'toilet paper dispenser',
+        'mini fridge', 'fire extinguisher', 'ball', 'hat',
+        'shower curtain rod', 'water cooler', 'paper cutter', 'tray',
+        'shower door', 'pillar', 'ledge', 'toaster oven', 'mouse',
+        'toilet seat cover dispenser', 'furniture', 'cart',
+        'storage container', 'scale', 'tissue box', 'light switch', 'crate',
+        'power outlet', 'decoration', 'sign', 'projector', 'closet door',
+        'vacuum cleaner', 'candle', 'plunger', 'stuffed animal', 'headphones',
+        'dish rack', 'broom', 'guitar case', 'range hood', 'dustpan',
+        'hair dryer', 'water bottle', 'handicap bar', 'purse', 'vent',
+        'shower floor', 'water pitcher', 'mailbox', 'bowl', 'paper bag',
+        'alarm clock', 'music stand', 'projector screen', 'divider',
+        'laundry detergent', 'bathroom counter', 'object', 'bathroom vanity',
+        'closet wall', 'laundry hamper', 'bathroom stall door',
+        'ceiling light', 'trash bin', 'dumbbell', 'stair rail', 'tube',
+        'bathroom cabinet', 'cd case', 'closet rod', 'coffee kettle',
+        'structure', 'shower head', 'keyboard piano', 'case of water bottles',
+        'coat rack', 'storage organizer', 'folded chair', 'fire alarm',
+        'power strip', 'calendar', 'poster', 'potted plant', 'luggage',
+        'mattress'),
+    train=dict(
+        type='ScanNet200Dataset',
+        split='train',
+        data_root='data/scannet',
+        with_images=10,
+        transform=[
+            dict(type='ImageResize', size=[480, 640]),
+            dict(
+                type='ImageColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.2,
+                hue=0.1),
+            dict(type='ImageRandomHorizontalFlip'),
+            dict(type='ImageNormalize'),
+            dict(type='CenterShift', apply_z=True),
+            dict(
+                type='RandomDropout',
+                dropout_ratio=0.2,
+                dropout_application_ratio=0.2),
+            dict(
+                type='RandomRotate',
+                angle=[-1, 1],
+                axis='z',
+                center=[0, 0, 0],
+                p=0.5),
+            dict(
+                type='RandomRotate',
+                angle=[-0.015625, 0.015625],
+                axis='x',
+                p=0.5),
+            dict(
+                type='RandomRotate',
+                angle=[-0.015625, 0.015625],
+                axis='y',
+                p=0.5),
+            dict(type='RandomScale', scale=[0.9, 1.1]),
+            dict(type='RandomFlip', p=0.5),
+            dict(type='RandomJitter', sigma=0.005, clip=0.02),
+            dict(
+                type='ElasticDistortion',
+                distortion_params=[[0.2, 0.4], [0.8, 1.6]]),
+            dict(type='ChromaticAutoContrast', p=0.2, blend_factor=None),
+            dict(type='ChromaticTranslation', p=0.95, ratio=0.05),
+            dict(type='ChromaticJitter', p=0.95, std=0.05),
+            dict(
+                type='GridSample',
+                grid_size=0.02,
+                hash_type='fnv',
+                mode='train',
+                keys=('coord', 'color', 'normal', 'segment', 'image_coord',
+                      'image_mask'),
+                return_grid_coord=True),
+            dict(type='SphereCrop', point_max=102400, mode='random'),
+            dict(type='CenterShift', apply_z=False),
+            dict(type='NormalizeColor'),
+            dict(type='ToTensor'),
+            dict(
+                type='Collect',
+                keys=('coord', 'grid_coord', 'segment', 'image', 'image_coord',
+                      'image_mask'),
+                feat_keys=('color', 'normal'))
+        ],
+        test_mode=False,
+        loop=8),
+    val=dict(
+        type='ScanNet200Dataset',
+        split='val',
+        data_root='data/scannet',
+        with_images=10,
+        transform=[
+            dict(type='ImageResize', size=[480, 640]),
+            dict(type='ImageNormalize'),
+            dict(type='CenterShift', apply_z=True),
+            dict(
+                type='GridSample',
+                grid_size=0.02,
+                hash_type='fnv',
+                mode='train',
+                keys=('coord', 'color', 'normal', 'segment', 'image_coord',
+                      'image_mask'),
+                return_grid_coord=True),
+            dict(type='CenterShift', apply_z=False),
+            dict(type='NormalizeColor'),
+            dict(type='ToTensor'),
+            dict(
+                type='Collect',
+                keys=('coord', 'grid_coord', 'segment', 'image', 'image_coord',
+                      'image_mask'),
+                feat_keys=('color', 'normal'))
+        ],
+        test_mode=False),
+    test=dict(
+        type='ScanNet200Dataset',
+        split='val',
+        data_root='data/scannet',
+        with_images=10,
+        transform=[
+            dict(type='CenterShift', apply_z=True),
+            dict(type='NormalizeColor')
+        ],
+        test_mode=True,
+        test_cfg=dict(
+            voxelize=dict(
+                type='GridSample',
+                grid_size=0.02,
+                hash_type='fnv',
+                mode='test',
+                keys=('coord', 'color', 'normal', 'image_coord', 'image_mask'),
+                return_grid_coord=True),
+            crop=None,
+            post_transform=[
+                dict(type='ImageResize', size=[480, 640]),
+                dict(type='ImageNormalize'),
+                dict(type='CenterShift', apply_z=False),
+                dict(type='ToTensor'),
+                dict(
+                    type='Collect',
+                    keys=('coord', 'grid_coord', 'index', 'image',
+                          'image_coord', 'image_mask'),
+                    feat_keys=('color', 'normal'))
+            ],
+            aug_transform=[[{
+                'type': 'RandomRotateTargetAngle',
+                'angle': [0],
+                'axis': 'z',
+                'center': [0, 0, 0],
+                'p': 1
+            }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }], [{
+                               'type': 'RandomFlip',
+                               'p': 1
+                           }]])))

scannet200/semseg-ptv3_dinov3-L/events.out.tfevents.1755298870.n23g0015.hpc.itc.rwth-aachen.de

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f493c0982e44631c551c89a32f9a4dc23a1c7160b7515e5a06ab86f8ea6eb85
+size 7830557

scannet200/semseg-ptv3_dinov3-L/model/model_best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c583ee37e761b9695297c2a42e27220db4dd2fbc5b2d1c76b32cc9bf2ca61b6
+size 561061040

scannet200/semseg-ptv3_dinov3-L/model/model_last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e000a839a685c67c1c5d271f1260a10a6eb886b9d106ec4eb2aba4e317d77062
+size 561061040

scannet200/semseg-ptv3_dinov3-L/train.log

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03021b0354343cc40c6add98d7929be537a03f81e8e8114e8e3e03e567d2cd6
+size 18715664