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 Run5 | ST Studio
Ressourcen / Mask2former Swin Large Apple Dms Run5 Mask2former Swin Large Apple Dms Run5 This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4092 Mean Accuracy:...
This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4092 Mean Accuracy:...
Art Other Basismodell facebook/mask2former-swin-large-ade-semantic Version Revision b0fa169
Modellquelle
Art Other
Dateigröße 826 MB
Basismodell facebook/mask2former-swin-large-ade-semantic
Version vRevision b0fa169
Aktualisiert 27. Sept. 2026
Downloads 12
Aufgaben Bildsegmentierung
Quelle Hugging Face
mask2former-swin-large-apple-dms-run5
This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials dataset.
It achieves the following results on the evaluation set:
Modellartefakte
1 Artefakt model.safetensors
safetensors · 826 MB · SHA-256 5b6d0b80e737…7ea8 · Hugging Face
Herunterladen
Mean Iou: 0.4092
Mean Accuracy: 0.4515
Overall Accuracy: 0.7668
Iou Animal Skin: 0.1578
Accuracy Animal Skin: 0.1806
Iou Bone Teeth Horn: 0.0798
Accuracy Bone Teeth Horn: 0.0820
Iou Brickwork: 0.6137
Accuracy Brickwork: 0.6665
Iou Cardboard: 0.5351
Accuracy Cardboard: 0.5757
Iou Carpet Rug: 0.7736
Accuracy Carpet Rug: 0.8370
Iou Ceiling Tile: 0.7898
Accuracy Ceiling Tile: 0.8378
Iou Ceramic: 0.7090
Accuracy Ceramic: 0.7849
Iou Chalkboard Blackboard: 0.6888
Accuracy Chalkboard Blackboard: 0.7112
Iou Clutter: 0.0
Accuracy Clutter: 0.0
Iou Concrete: 0.2113
Accuracy Concrete: 0.2368
Iou Cork Corkboard: 0.0
Accuracy Cork Corkboard: 0.0
Iou Engineered Stone: 0.0
Accuracy Engineered Stone: 0.0
Iou Fabric Cloth: 0.8276
Accuracy Fabric Cloth: 0.8849
Iou Fiberglass Wool: 0.0
Accuracy Fiberglass Wool: 0.0
Iou Fire: 0.0577
Accuracy Fire: 0.0579
Iou Foliage: 0.8600
Accuracy Foliage: 0.9181
Iou Food: 0.8337
Accuracy Food: 0.9197
Iou Fur: 0.8343
Accuracy Fur: 0.9423
Iou Gemstone Quartz: 0.0
Accuracy Gemstone Quartz: 0.0
Iou Glass: 0.6482
Accuracy Glass: 0.7210
Iou Hair: 0.7722
Accuracy Hair: 0.8626
Iou Ice: 0.0
Accuracy Ice: 0.0
Iou Leather: 0.4223
Accuracy Leather: 0.4549
Iou Liquid Non-water: 0.0
Accuracy Liquid Non-water: 0.0
Iou Metal: 0.3931
Accuracy Metal: 0.4598
Iou Mirror: 0.6222
Accuracy Mirror: 0.6854
Iou Paint Plaster Enamel: 0.7474
Accuracy Paint Plaster Enamel: 0.8087
Iou Paper: 0.6602
Accuracy Paper: 0.7341
Iou Pearl: 0.0
Accuracy Pearl: 0.0
Iou Photograph Painting: 0.2659
Accuracy Photograph Painting: 0.2848
Iou Plastic Clear: 0.2922
Accuracy Plastic Clear: 0.3171
Iou Plastic Non-clear: 0.3641
Accuracy Plastic Non-clear: 0.4142
Iou Rubber Latex: 0.2416
Accuracy Rubber Latex: 0.2620
Iou Sand: 0.0
Accuracy Sand: 0.0
Iou Skin Lips: 0.7869
Accuracy Skin Lips: 0.8730
Iou Sky: 0.9294
Accuracy Sky: 0.9489
Iou Snow: 0.3728
Accuracy Snow: 0.3952
Iou Soap: 0.0
Accuracy Soap: 0.0
Iou Soil Mud: 0.3733
Accuracy Soil Mud: 0.6259
Iou Sponge: 0.0
Accuracy Sponge: 0.0
Iou Stone Natural: 0.5063
Accuracy Stone Natural: 0.5774
Iou Stone Polished: 0.0582
Accuracy Stone Polished: 0.0584
Iou Styrofoam: 0.0
Accuracy Styrofoam: 0.0
Iou Tile: 0.6665
Accuracy Tile: 0.7335
Iou Wallpaper: 0.4923
Accuracy Wallpaper: 0.5730
Iou Water: 0.8294
Accuracy Water: 0.9135
Iou Wax: 0.1683
Accuracy Wax: 0.1785
Iou Whiteboard: 0.7212
Accuracy Whiteboard: 0.7607
Iou Wicker: 0.3975
Accuracy Wicker: 0.4169
Iou Wood: 0.7545
Accuracy Wood: 0.8255
Iou Wood Tree: 0.4079
Accuracy Wood Tree: 0.4684
Iou Asphalt: 0.4139
Accuracy Asphalt: 0.4880
Loss: 240.7806
Eval Runtime: 35.2182
Eval Samples Per Second: 33.619
Eval Steps Per Second: 16.809
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: 20
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 280.1148 1.7045 150 0.2157 0.2402 0.6236 0.0 0.0 0.0124 0.0125 0.2288 0.2549 0.0043 0.0043 0.3092 0.3173 0.7319 0.7978 0.2896 0.3020 0.1502 0.1502 0.0 0.0 0.0000 0.0000
---
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-run5
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-run5
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 dataset.
It achieves the following results on the evaluation set:
- Mean Iou: 0.4092
- Mean Accuracy: 0.4515
- Overall Accuracy: 0.7668
- Iou Animal Skin: 0.1578
- Accuracy Animal Skin: 0.1806
- Iou Bone Teeth Horn: 0.0798
- Accuracy Bone Teeth Horn: 0.0820
- Iou Brickwork: 0.6137
- Accuracy Brickwork: 0.6665
- Iou Cardboard: 0.5351
- Accuracy Cardboard: 0.5757
- Iou Carpet Rug: 0.7736
- Accuracy Carpet Rug: 0.8370
- Iou Ceiling Tile: 0.7898
- Accuracy Ceiling Tile: 0.8378
- Iou Ceramic: 0.7090
- Accuracy Ceramic: 0.7849
- Iou Chalkboard Blackboard: 0.6888
- Accuracy Chalkboard Blackboard: 0.7112
- Iou Clutter: 0.0
- Accuracy Clutter: 0.0
- Iou Concrete: 0.2113
- Accuracy Concrete: 0.2368
- Iou Cork Corkboard: 0.0
- Accuracy Cork Corkboard: 0.0
- Iou Engineered Stone: 0.0
- Accuracy Engineered Stone: 0.0
- Iou Fabric Cloth: 0.8276
- Accuracy Fabric Cloth: 0.8849
- Iou Fiberglass Wool: 0.0
- Accuracy Fiberglass Wool: 0.0
- Iou Fire: 0.0577
- Accuracy Fire: 0.0579
- Iou Foliage: 0.8600
- Accuracy Foliage: 0.9181
- Iou Food: 0.8337
- Accuracy Food: 0.9197
- Iou Fur: 0.8343
- Accuracy Fur: 0.9423
- Iou Gemstone Quartz: 0.0
- Accuracy Gemstone Quartz: 0.0
- Iou Glass: 0.6482
- Accuracy Glass: 0.7210
- Iou Hair: 0.7722
- Accuracy Hair: 0.8626
- Iou Ice: 0.0
- Accuracy Ice: 0.0
- Iou Leather: 0.4223
- Accuracy Leather: 0.4549
- Iou Liquid Non-water: 0.0
- Accuracy Liquid Non-water: 0.0
- Iou Metal: 0.3931
- Accuracy Metal: 0.4598
- Iou Mirror: 0.6222
- Accuracy Mirror: 0.6854
- Iou Paint Plaster Enamel: 0.7474
- Accuracy Paint Plaster Enamel: 0.8087
- Iou Paper: 0.6602
- Accuracy Paper: 0.7341
- Iou Pearl: 0.0
- Accuracy Pearl: 0.0
- Iou Photograph Painting: 0.2659
- Accuracy P...
Source context: 12 downloads · 0 likes · Pipeline image-segmentation · Library transformers · Repo AllanK24/mask2former-swin-large-apple-dms-run5
Accuracy Chalkboard Blackboard
Accuracy Engineered Stone
Accuracy Liquid Non-water
Accuracy Paint Plaster Enamel
Accuracy Photograph Painting
Accuracy Plastic Non-clear
280.1148 1.7045 150 0.2157 0.2402 0.6236 0.0 0.0 0.0124 0.0125 0.2288 0.2549 0.0043 0.0043 0.3092 0.3173 0.7319 0.7978 0.2896 0.3020 0.1502 0.1502 0.0 0.0 0.0000 0.0000 0.0 0.0 0.0 0.0 0.7812 0.8493 0.0 0.0 0.0 0.0 0.7985 0.8420 0.5168 0.7449 0.2533 0.2651 0.0 0.0 0.5540 0.6777 0.7199 0.7991 0.0 0.0 0.0481 0.0507 0.0 0.0 0.1376 0.1439 0.4760 0.5132 0.6778 0.7475 0.5443 0.6549 0.0 0.0 0.0714 0.0743 0.1016 0.1283 0.1456 0.1534 0.0065 0.0066 0.0 0.0 ...
