Upload folder using huggingface_hub

.gitattributes

@@ -39,3 +39,4 @@ nuscenes/semseg-ptv3_dino-B/test.log filter=lfs diff=lfs merge=lfs -text
 nuscenes/semseg-ptv3_dino-B/train.log filter=lfs diff=lfs merge=lfs -text
 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

semantic_kitti/semseg-ptv3_dino-L/config.py

@@ -0,0 +1,244 @@
+weight = 'exp/semantic_kitti/semseg-ptv3_dino-L/model/model_best.pth'
+resume = False
+evaluate = True
+test_only = False
+seed = 32226192
+save_path = 'exp/semantic_kitti/semseg-ptv3_dino-L'
+wandb_project = 'semseg_kitti'
+num_worker = 16
+batch_size = 8
+batch_size_val = None
+batch_size_test = None
+epoch = 50
+eval_epoch = 50
+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='block', lr=0.0002)]
+hooks = [
+    dict(type='CheckpointLoader'),
+    dict(type='IterationTimer', warmup_iter=2),
+    dict(type='InformationWriter'),
+    dict(type='SemSegEvaluator'),
+    dict(type='CheckpointSaver', save_freq=None)
+]
+train = dict(type='DefaultTrainer')
+test = dict(type='SemSegTester', verbose=True)
+model = dict(
+    type='DefaultSegmentorV2',
+    num_classes=19,
+    backbone_out_channels=64,
+    backbone=dict(
+        type='PT-v3m1-image',
+        in_channels=4,
+        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,
+        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=('nuScenes', 'SemanticKITTI', 'Waymo'),
+        dinov2='large',
+        dinov2_missing_embedding=False,
+        dinov2_drop=0.0),
+    criteria=[
+        dict(
+            type='CrossEntropyLoss',
+            weight=[
+                3.1557, 8.7029, 7.8281, 6.1354, 6.3161, 7.9937, 8.9704,
+                10.1922, 1.6155, 4.2187, 1.9385, 5.5455, 2.0198, 2.6261,
+                1.3212, 5.1102, 2.5492, 5.8585, 7.3929
+            ],
+            loss_weight=1.0,
+            ignore_index=-1),
+        dict(
+            type='LovaszLoss',
+            mode='multiclass',
+            loss_weight=1.0,
+            ignore_index=-1)
+    ])
+optimizer = dict(type='AdamW', lr=0.002, weight_decay=0.005)
+scheduler = dict(
+    type='OneCycleLR',
+    max_lr=[0.002, 0.0002],
+    pct_start=0.04,
+    anneal_strategy='cos',
+    div_factor=10.0,
+    final_div_factor=100.0)
+dataset_type = 'SemanticKITTIDataset'
+data_root = 'data/semantic_kitti'
+ignore_index = -1
+names = [
+    'car', 'bicycle', 'motorcycle', 'truck', 'other-vehicle', 'person',
+    'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk', 'other-ground',
+    'building', 'fence', 'vegetation', 'trunk', 'terrain', 'pole',
+    'traffic-sign'
+]
+data = dict(
+    num_classes=19,
+    ignore_index=-1,
+    names=[
+        'car', 'bicycle', 'motorcycle', 'truck', 'other-vehicle', 'person',
+        'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk',
+        'other-ground', 'building', 'fence', 'vegetation', 'trunk', 'terrain',
+        'pole', 'traffic-sign'
+    ],
+    train=dict(
+        type='SemanticKITTIDataset',
+        split='train',
+        data_root='data/semantic_kitti',
+        with_images=True,
+        transform=[
+            dict(type='ImageResize', size=[378, 1246]),
+            dict(
+                type='ImageColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.2,
+                hue=0.1),
+            dict(type='ImageRandomHorizontalFlip'),
+            dict(type='ImageNormalize'),
+            dict(
+                type='RandomRotate',
+                angle=[-1, 1],
+                axis='z',
+                center=[0, 0, 0],
+                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='GridSample',
+                grid_size=0.05,
+                hash_type='fnv',
+                mode='train',
+                keys=('coord', 'strength', 'segment', 'image_coord',
+                      'image_mask'),
+                return_grid_coord=True),
+            dict(
+                type='PointClip',
+                point_cloud_range=(-35.2, -35.2, -4, 35.2, 35.2, 2)),
+            dict(type='SphereCrop', sample_rate=0.8, mode='random'),
+            dict(type='SphereCrop', point_max=120000, mode='random'),
+            dict(type='ToTensor'),
+            dict(
+                type='Collect',
+                keys=('coord', 'grid_coord', 'segment', 'image', 'image_coord',
+                      'image_mask'),
+                feat_keys=('coord', 'strength'))
+        ],
+        test_mode=False,
+        ignore_index=-1,
+        loop=1),
+    val=dict(
+        type='SemanticKITTIDataset',
+        split='val',
+        data_root='data/semantic_kitti',
+        with_images=True,
+        transform=[
+            dict(type='ImageResize', size=[378, 1246]),
+            dict(type='ImageNormalize'),
+            dict(
+                type='GridSample',
+                grid_size=0.05,
+                hash_type='fnv',
+                mode='train',
+                keys=('coord', 'strength', 'segment', 'image_coord',
+                      'image_mask'),
+                return_grid_coord=True),
+            dict(
+                type='PointClip',
+                point_cloud_range=(-35.2, -35.2, -4, 35.2, 35.2, 2)),
+            dict(type='ToTensor'),
+            dict(
+                type='Collect',
+                keys=('coord', 'grid_coord', 'segment', 'image', 'image_coord',
+                      'image_mask'),
+                feat_keys=('coord', 'strength'))
+        ],
+        test_mode=False,
+        ignore_index=-1),
+    test=dict(
+        type='SemanticKITTIDataset',
+        split='val',
+        data_root='data/semantic_kitti',
+        with_images=True,
+        transform=[dict(type='ImageResize', size=[378, 1246])],
+        test_mode=True,
+        test_cfg=dict(
+            voxelize=dict(
+                type='GridSample',
+                grid_size=0.05,
+                hash_type='fnv',
+                mode='test',
+                return_grid_coord=True,
+                keys=('coord', 'strength', 'segment', 'image_coord',
+                      'image_mask')),
+            crop=None,
+            post_transform=[
+                dict(type='ImageNormalize'),
+                dict(
+                    type='PointClip',
+                    point_cloud_range=(-35.2, -35.2, -4, 35.2, 35.2, 2)),
+                dict(type='ToTensor'),
+                dict(
+                    type='Collect',
+                    keys=('coord', 'grid_coord', 'index', 'image',
+                          'image_coord', 'image_mask'),
+                    feat_keys=('coord', 'strength'))
+            ],
+            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
+                           }]]),
+        ignore_index=-1))

semantic_kitti/semseg-ptv3_dino-L/events.out.tfevents.1730404883.penguin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7b89074a12dcbf5002c2d31e32d17d991d63e2198650649badef8abc40dcb5
+size 11694620

semantic_kitti/semseg-ptv3_dino-L/model/model_best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5d5cb30a974f775cf29837a3c406a30e40a1654dffca3cf64dd8504d0d3764
+size 560860208

semantic_kitti/semseg-ptv3_dino-L/model/model_last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5d5cb30a974f775cf29837a3c406a30e40a1654dffca3cf64dd8504d0d3764
+size 560860208

semantic_kitti/semseg-ptv3_dino-L/train.log

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ba267cb2d092f3f6d1f39b5206b247775809179cd5cf8709b8501ee3da32f2
+size 28774255