Zum Inhalt springen Studio Erstelle Bilder und Videos, ohne in der KI-Toolchain leben zu müssen.
Ein lokal-orientierter Arbeitsbereich, um ComfyUI-Workflows in Werkzeuge zu verwandeln, die Sie nutzen, verstehen und wiederverwenden können.
© 2026 Tea Time Labs
Lokale KI-Kreation, organisiert.
Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation. Workflow verständlich machen. Jetzt ausprobieren ↗
Mask2former Swin Large Apple Dms v2 Run1 | ST Studio
Ressourcen / Mask2former Swin Large Apple Dms v2 Run1 Mask2former Swin Large Apple Dms v2 Run1 This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials-v2 dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4855 Mean...
This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials-v2 dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4855 Mean...
Art Other Basismodell facebook/mask2former-swin-large-ade-semantic Version Revision 78f5089
Modellquelle
Art Other
Dateigröße 826 MB
Basismodell facebook/mask2former-swin-large-ade-semantic
Version vRevision 78f5089
Aktualisiert 27. Sept. 2026
Downloads 9
Aufgaben Bildsegmentierung
Quelle Hugging Face
mask2former-swin-large-apple-dms-v2-run1
This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials-v2 dataset.
It achieves the following results on the evaluation set:
Modellartefakte
1 Artefakt model.safetensors
safetensors · 826 MB · SHA-256 a38848147556…d17c · Hugging Face
Herunterladen
Mean Iou: 0.4855
Mean Accuracy: 0.5513
Overall Accuracy: 0.7373
Iou Animal Skin: 0.5328
Accuracy Animal Skin: 0.6314
Iou Bone Teeth Horn: 0.2991
Accuracy Bone Teeth Horn: 0.3571
Iou Brickwork: 0.6759
Accuracy Brickwork: 0.7193
Iou Cardboard: 0.5948
Accuracy Cardboard: 0.6508
Iou Carpet Rug: 0.7386
Accuracy Carpet Rug: 0.7948
Iou Ceiling Tile: 0.7821
Accuracy Ceiling Tile: 0.8229
Iou Ceramic: 0.6638
Accuracy Ceramic: 0.7241
Iou Chalkboard Blackboard: 0.7407
Accuracy Chalkboard Blackboard: 0.7690
Iou Clutter: 0.1997
Accuracy Clutter: 0.2594
Iou Concrete: 0.3853
Accuracy Concrete: 0.4942
Iou Cork Corkboard: 0.2842
Accuracy Cork Corkboard: 0.4588
Iou Engineered Stone: 0.0910
Accuracy Engineered Stone: 0.1033
Iou Fabric Cloth: 0.8133
Accuracy Fabric Cloth: 0.8586
Iou Fiberglass Wool: 0.0
Accuracy Fiberglass Wool: 0.0
Iou Fire: 0.0801
Accuracy Fire: 0.0821
Iou Foliage: 0.8400
Accuracy Foliage: 0.8883
Iou Food: 0.8122
Accuracy Food: 0.9154
Iou Fur: 0.7918
Accuracy Fur: 0.8221
Iou Gemstone Quartz: 0.2690
Accuracy Gemstone Quartz: 0.4411
Iou Glass: 0.6341
Accuracy Glass: 0.7020
Iou Hair: 0.7792
Accuracy Hair: 0.8541
Iou Ice: 0.3050
Accuracy Ice: 0.3105
Iou Leather: 0.3909
Accuracy Leather: 0.4495
Iou Liquid Non-water: 0.3621
Accuracy Liquid Non-water: 0.3682
Iou Metal: 0.4062
Accuracy Metal: 0.4727
Iou Mirror: 0.5644
Accuracy Mirror: 0.6356
Iou Paint Plaster Enamel: 0.6886
Accuracy Paint Plaster Enamel: 0.7375
Iou Paper: 0.6154
Accuracy Paper: 0.6782
Iou Pearl: 0.0142
Accuracy Pearl: 0.0169
Iou Photograph Painting: 0.2775
Accuracy Photograph Painting: 0.3620
Iou Plastic Clear: 0.3273
Accuracy Plastic Clear: 0.3714
Iou Plastic Non-clear: 0.3883
Accuracy Plastic Non-clear: 0.4610
Iou Rubber Latex: 0.4523
Accuracy Rubber Latex: 0.5250
Iou Sand: 0.4804
Accuracy Sand: 0.7075
Iou Skin Lips: 0.8028
Accuracy Skin Lips: 0.8891
Iou Sky: 0.9423
Accuracy Sky: 0.9647
Iou Snow: 0.6566
Accuracy Snow: 0.9048
Iou Soap: 0.1444
Accuracy Soap: 0.1515
Iou Soil Mud: 0.4532
Accuracy Soil Mud: 0.5978
Iou Sponge: 0.0115
Accuracy Sponge: 0.0123
Iou Stone Natural: 0.6114
Accuracy Stone Natural: 0.7052
Iou Stone Polished: 0.1957
Accuracy Stone Polished: 0.2190
Iou Styrofoam: 0.0
Accuracy Styrofoam: 0.0
Iou Tile: 0.6430
Accuracy Tile: 0.7046
Iou Wallpaper: 0.4538
Accuracy Wallpaper: 0.5733
Iou Water: 0.8473
Accuracy Water: 0.9057
Iou Wax: 0.3548
Accuracy Wax: 0.3821
Iou Whiteboard: 0.7031
Accuracy Whiteboard: 0.7409
Iou Wicker: 0.5431
Accuracy Wicker: 0.5809
Iou Wood: 0.6676
Accuracy Wood: 0.7112
Iou Wood Tree: 0.3676
Accuracy Wood Tree: 0.4725
Iou Asphalt: 0.5654
Accuracy Asphalt: 0.7091
Loss: 273.8730
Eval Runtime: 18.7903
Eval Samples Per Second: 28.1
Eval Steps Per Second: 14.05
Model description
Intended uses & limitations
Training and evaluation data
Training procedure
Training hyperparameters The following hyperparameters were used during training:
learning_rate: 0.001
train_batch_size: 32
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 256
total_eval_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 40
Training results Training Loss Epoch Step Mean Iou Mean Accuracy Overall Accuracy Iou Animal Skin Accuracy Animal Skin Iou Bone Teeth Horn Accuracy Bone Teeth Horn Iou Brickwork Accuracy Brickwork Iou Cardboard Accuracy Cardboard Iou Carpet Rug Accuracy Carpet Rug Iou Ceiling Tile Accuracy Ceiling Tile Iou Ceramic Accuracy Ceramic Iou Chalkboard Blackboard 285.3377 2.6923 350 0.3212 0.3593 0.7146 0.0193 0.0376 0.0628 0.0639 0.3758 0.4029 0.3987 0.4071 0.4748 0.4935 0.7595 0.7934 0.6011 0.6469 0.5165 0.5798 0.0 0.0 0.1381 0.1494
---
library_name: transformers
license: other
base_model: facebook/mask2former-swin-large-ade-semantic
tags:
- vision
- image-segmentation
- mask2former
- material-segmentation
- generated_from_trainer
model-index:
- name: mask2former-swin-large-apple-dms-v2-run1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mask2former-swin-large-apple-dms-v2-run1
This model is a fine-tuned version of [facebook/mask2former-swin-large-ade-semantic](https://huggingface.co/facebook/mask2former-swin-large-ade-semantic) on the AllanK24/apple-dms-materials-v2 dataset.
It achieves the following results on the evaluation set:
- Mean Iou: 0.4855
- Mean Accuracy: 0.5513
- Overall Accuracy: 0.7373
- Iou Animal Skin: 0.5328
- Accuracy Animal Skin: 0.6314
- Iou Bone Teeth Horn: 0.2991
- Accuracy Bone Teeth Horn: 0.3571
- Iou Brickwork: 0.6759
- Accuracy Brickwork: 0.7193
- Iou Cardboard: 0.5948
- Accuracy Cardboard: 0.6508
- Iou Carpet Rug: 0.7386
- Accuracy Carpet Rug: 0.7948
- Iou Ceiling Tile: 0.7821
- Accuracy Ceiling Tile: 0.8229
- Iou Ceramic: 0.6638
- Accuracy Ceramic: 0.7241
- Iou Chalkboard Blackboard: 0.7407
- Accuracy Chalkboard Blackboard: 0.7690
- Iou Clutter: 0.1997
- Accuracy Clutter: 0.2594
- Iou Concrete: 0.3853
- Accuracy Concrete: 0.4942
- Iou Cork Corkboard: 0.2842
- Accuracy Cork Corkboard: 0.4588
- Iou Engineered Stone: 0.0910
- Accuracy Engineered Stone: 0.1033
- Iou Fabric Cloth: 0.8133
- Accuracy Fabric Cloth: 0.8586
- Iou Fiberglass Wool: 0.0
- Accuracy Fiberglass Wool: 0.0
- Iou Fire: 0.0801
- Accuracy Fire: 0.0821
- Iou Foliage: 0.8400
- Accuracy Foliage: 0.8883
- Iou Food: 0.8122
- Accuracy Food: 0.9154
- Iou Fur: 0.7918
- Accuracy Fur: 0.8221
- Iou Gemstone Quartz: 0.2690
- Accuracy Gemstone Quartz: 0.4411
- Iou Glass: 0.6341
- Accuracy Glass: 0.7020
- Iou Hair: 0.7792
- Accuracy Hair: 0.8541
- Iou Ice: 0.3050
- Accuracy Ice: 0.3105
- Iou Leather: 0.3909
- Accuracy Leather: 0.4495
- Iou Liquid Non-water: 0.3621
- Accuracy Liquid Non-water: 0.3682
- Iou Metal: 0.4062
- Accuracy Metal: 0.4727
- Iou Mirror: 0.5644
- Accuracy Mirror: 0.6356
- Iou Paint Plaster Enamel: 0.6886
- Accuracy Paint Plaster Enamel: 0.7375
- Iou Paper: 0.6154
- Accuracy Paper: 0.6782
- Iou Pearl: 0.0142
- Accuracy Pearl: 0....
Source context: 9 downloads · 0 likes · Pipeline image-segmentation · Library transformers · Repo AllanK24/mask2former-swin-large-apple-dms-v2-run1
Accuracy Chalkboard Blackboard
Accuracy Engineered Stone
Accuracy Liquid Non-water
Accuracy Paint Plaster Enamel
Accuracy Photograph Painting
Accuracy Plastic Non-clear
285.3377 2.6923 350 0.3212 0.3593 0.7146 0.0193 0.0376 0.0628 0.0639 0.3758 0.4029 0.3987 0.4071 0.4748 0.4935 0.7595 0.7934 0.6011 0.6469 0.5165 0.5798 0.0 0.0 0.1381 0.1494 0.0 0.0 0.0 0.0 0.8153 0.8680 0.0 0.0 0.0 0.0 0.7444 0.9378 0.6288 0.8808 0.7131 0.8840 0.0 0.0 0.6072 0.6683 0.7306 0.7897 0.0 0.0 0.2414 0.2487 0.0 0.0 0.2483 0.2644 0.5574 0.6409 0.7410 0.8344 0.5938 0.6661 0.0 0.0 0.2740 0.2913 0.1242 0.1395 0.1268 0.1302 0.1163...
