Aller au contenu Studio Créez des images et des vidéos sans vivre dans la chaîne d’outils d’IA.
Un espace de travail local pour transformer les flux de travail ComfyUI en outils que vous pouvez utiliser, comprendre et retrouver.
© 2026 Tea Time Labs
Création locale par IA, bien organisée.
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur. Rendre un workflow lisible. Essayer maintenant ↗
Mask2former Swin Base Apple Dms Run3 | ST Studio
Ressources / Mask2former Swin Base Apple Dms Run3 Mask2former Swin Base Apple Dms Run3 This model is a fine-tuned version of facebook/mask2former-swin-base-ade-semantic on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4055 Mean Accuracy:...
This model is a fine-tuned version of facebook/mask2former-swin-base-ade-semantic on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4055 Mean Accuracy:...
Type Other Modèle de base facebook/mask2former-swin-base-ade-semantic Version Revision fe5f648
Source du modèle
Type Other
Taille du fichier 412 MB
Modèle de base facebook/mask2former-swin-base-ade-semantic
Version vRevision fe5f648
Mis à jour 9 févr. 2026
Téléchargements 5
Tâches Segmentation d'image
Source Hugging Face
mask2former-swin-base-apple-dms-run3
This model is a fine-tuned version of facebook/mask2former-swin-base-ade-semantic on the AllanK24/apple-dms-materials dataset.
It achieves the following results on the evaluation set:
Artefacts du modèle
1 artefact model.safetensors
safetensors · 412 MB · SHA-256 f054b5e7aa2c…a98b · Hugging Face
Télécharger Extraits de sources
2 extraits
Mean Iou: 0.4055
Mean Accuracy: 0.4571
Overall Accuracy: 0.7261
Iou Animal Skin: 0.2844
Accuracy Animal Skin: 0.3396
Iou Bone Teeth Horn: 0.1287
Accuracy Bone Teeth Horn: 0.1353
Iou Brickwork: 0.5506
Accuracy Brickwork: 0.6007
Iou Cardboard: 0.4753
Accuracy Cardboard: 0.5163
Iou Carpet Rug: 0.7248
Accuracy Carpet Rug: 0.7993
Iou Ceiling Tile: 0.7318
Accuracy Ceiling Tile: 0.7822
Iou Ceramic: 0.6421
Accuracy Ceramic: 0.7324
Iou Chalkboard Blackboard: 0.6229
Accuracy Chalkboard Blackboard: 0.6613
Iou Clutter: 0.0
Accuracy Clutter: 0.0
Iou Concrete: 0.2897
Accuracy Concrete: 0.3533
Iou Cork Corkboard: 0.0
Accuracy Cork Corkboard: 0.0
Iou Engineered Stone: 0.0
Accuracy Engineered Stone: 0.0
Iou Fabric Cloth: 0.7774
Accuracy Fabric Cloth: 0.8431
Iou Fiberglass Wool: 0.0
Accuracy Fiberglass Wool: 0.0
Iou Fire: 0.0462
Accuracy Fire: 0.0485
Iou Foliage: 0.8463
Accuracy Foliage: 0.9090
Iou Food: 0.8038
Accuracy Food: 0.8915
Iou Fur: 0.8120
Accuracy Fur: 0.9058
Iou Gemstone Quartz: 0.0
Accuracy Gemstone Quartz: 0.0
Iou Glass: 0.5701
Accuracy Glass: 0.6385
Iou Hair: 0.7468
Accuracy Hair: 0.8342
Iou Ice: 0.0
Accuracy Ice: 0.0
Iou Leather: 0.4000
Accuracy Leather: 0.4492
Iou Liquid Non-water: 0.0044
Accuracy Liquid Non-water: 0.0045
Iou Metal: 0.3217
Accuracy Metal: 0.3957
Iou Mirror: 0.4412
Accuracy Mirror: 0.4830
Iou Paint Plaster Enamel: 0.6995
Accuracy Paint Plaster Enamel: 0.7585
Iou Paper: 0.5897
Accuracy Paper: 0.6750
Iou Pearl: 0.0
Accuracy Pearl: 0.0
Iou Photograph Painting: 0.2360
Accuracy Photograph Painting: 0.2656
Iou Plastic Clear: 0.2166
Accuracy Plastic Clear: 0.2648
Iou Plastic Non-clear: 0.3274
Accuracy Plastic Non-clear: 0.3924
Iou Rubber Latex: 0.2258
Accuracy Rubber Latex: 0.2529
Iou Sand: 0.4271
Accuracy Sand: 0.5089
Iou Skin Lips: 0.7549
Accuracy Skin Lips: 0.8461
Iou Sky: 0.9267
Accuracy Sky: 0.9488
Iou Snow: 0.5493
Accuracy Snow: 0.6568
Iou Soap: 0.0
Accuracy Soap: 0.0
Iou Soil Mud: 0.4185
Accuracy Soil Mud: 0.6073
Iou Sponge: 0.0
Accuracy Sponge: 0.0
Iou Stone Natural: 0.4712
Accuracy Stone Natural: 0.5925
Iou Stone Polished: 0.1409
Accuracy Stone Polished: 0.1469
Iou Styrofoam: 0.0
Accuracy Styrofoam: 0.0
Iou Tile: 0.6098
Accuracy Tile: 0.6803
Iou Wallpaper: 0.4314
Accuracy Wallpaper: 0.5003
Iou Water: 0.8358
Accuracy Water: 0.9263
Iou Wax: 0.5110
Accuracy Wax: 0.5657
Iou Whiteboard: 0.6395
Accuracy Whiteboard: 0.7026
Iou Wicker: 0.4063
Accuracy Wicker: 0.4495
Iou Wood: 0.6898
Accuracy Wood: 0.7487
Iou Wood Tree: 0.3589
Accuracy Wood Tree: 0.4629
Iou Asphalt: 0.4000
Accuracy Asphalt: 0.4936
Loss: 275.7852
Eval Runtime: 36.0974
Eval Samples Per Second: 32.8
Eval Steps Per Second: 8.2
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: 64
eval_batch_size: 32
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 512
total_eval_batch_size: 256
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: 30
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 301.1912 3.4091 150 0.2898 0.3579 0.7339 0.0076 0.0076 0.0377 0.0393 0.3809 0.4826 0.3801 0.4998 0.6153 0.6646 0.7289 0.8201 0.6005 0.7090 0.1974 0.2470 0.0 0.0 0.0980 0.1084
---
library_name: transformers
license: other
base_model: facebook/mask2former-swin-base-ade-semantic
tags:
- vision
- image-segmentation
- mask2former
- material-segmentation
- generated_from_trainer
model-index:
- name: mask2former-swin-base-apple-dms-run3
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-base-apple-dms-run3
This model is a fine-tuned version of [facebook/mask2former-swin-base-ade-semantic](https://huggingface.co/facebook/mask2former-swin-base-ade-semantic) on the AllanK24/apple-dms-materials dataset.
It achieves the following results on the evaluation set:
- Mean Iou: 0.4055
- Mean Accuracy: 0.4571
- Overall Accuracy: 0.7261
- Iou Animal Skin: 0.2844
- Accuracy Animal Skin: 0.3396
- Iou Bone Teeth Horn: 0.1287
- Accuracy Bone Teeth Horn: 0.1353
- Iou Brickwork: 0.5506
- Accuracy Brickwork: 0.6007
- Iou Cardboard: 0.4753
- Accuracy Cardboard: 0.5163
- Iou Carpet Rug: 0.7248
- Accuracy Carpet Rug: 0.7993
- Iou Ceiling Tile: 0.7318
- Accuracy Ceiling Tile: 0.7822
- Iou Ceramic: 0.6421
- Accuracy Ceramic: 0.7324
- Iou Chalkboard Blackboard: 0.6229
- Accuracy Chalkboard Blackboard: 0.6613
- Iou Clutter: 0.0
- Accuracy Clutter: 0.0
- Iou Concrete: 0.2897
- Accuracy Concrete: 0.3533
- Iou Cork Corkboard: 0.0
- Accuracy Cork Corkboard: 0.0
- Iou Engineered Stone: 0.0
- Accuracy Engineered Stone: 0.0
- Iou Fabric Cloth: 0.7774
- Accuracy Fabric Cloth: 0.8431
- Iou Fiberglass Wool: 0.0
- Accuracy Fiberglass Wool: 0.0
- Iou Fire: 0.0462
- Accuracy Fire: 0.0485
- Iou Foliage: 0.8463
- Accuracy Foliage: 0.9090
- Iou Food: 0.8038
- Accuracy Food: 0.8915
- Iou Fur: 0.8120
- Accuracy Fur: 0.9058
- Iou Gemstone Quartz: 0.0
- Accuracy Gemstone Quartz: 0.0
- Iou Glass: 0.5701
- Accuracy Glass: 0.6385
- Iou Hair: 0.7468
- Accuracy Hair: 0.8342
- Iou Ice: 0.0
- Accuracy Ice: 0.0
- Iou Leather: 0.4000
- Accuracy Leather: 0.4492
- Iou Liquid Non-water: 0.0044
- Accuracy Liquid Non-water: 0.0045
- Iou Metal: 0.3217
- Accuracy Metal: 0.3957
- Iou Mirror: 0.4412
- Accuracy Mirror: 0.4830
- Iou Paint Plaster Enamel: 0.6995
- Accuracy Paint Plaster Enamel: 0.7585
- Iou Paper: 0.5897
- Accuracy Paper: 0.6750
- Iou Pearl: 0.0
- Accuracy Pearl: 0.0
- Iou Photograph Painting: 0.2360
- Accuracy...
Source context: 5 downloads · 0 likes · Pipeline image-segmentation · Library transformers · Repo AllanK24/mask2former-swin-base-apple-dms-run3
Accuracy Chalkboard Blackboard
Accuracy Engineered Stone
Accuracy Liquid Non-water
Accuracy Paint Plaster Enamel
Accuracy Photograph Painting
Accuracy Plastic Non-clear
301.1912 3.4091 150 0.2898 0.3579 0.7339 0.0076 0.0076 0.0377 0.0393 0.3809 0.4826 0.3801 0.4998 0.6153 0.6646 0.7289 0.8201 0.6005 0.7090 0.1974 0.2470 0.0 0.0 0.0980 0.1084 0.0 0.0 0.0 0.0 0.7572 0.8487 0.0 0.0 0.0 0.0 0.8214 0.9371 0.6580 0.8915 0.6749 0.8054 0.0 0.0 0.5515 0.6922 0.6846 0.7658 0.0 0.0 0.1850 0.1962 0.0 0.0 0.1701 0.1861 0.4358 0.4965 0.7083 0.8100 0.5016 0.6030 0.0 0.0 0.2623 0.3442 0.0906 0.1053 0.3206 0.4415 0.1005 0.1111 0.0 0.0 ...
