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 ↗
Segformer B5 Finetuned Apple Dms Run8 | ST Studio
Ressourcen / Segformer B5 Finetuned Apple Dms Run8 Segformer B5 Finetuned Apple Dms Run8 This model is a fine-tuned version of nvidia/segformer-b5-finetuned-ade-640-640 on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Loss: 1.3158 Mean Iou: 0.3623 Mean...
This model is a fine-tuned version of nvidia/segformer-b5-finetuned-ade-640-640 on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Loss: 1.3158 Mean Iou: 0.3623 Mean...
Art Other Basismodell nvidia/segformer-b5-finetuned-ade-640-640 Version Revision 8c4f3cf
Modellquelle
Art Other
Dateigröße 323 MB
Basismodell nvidia/segformer-b5-finetuned-ade-640-640
Version vRevision 8c4f3cf
Aktualisiert 27. Sept. 2026
Downloads 8
Aufgaben Bildsegmentierung
Quelle Hugging Face
segformer-b5-finetuned-apple-dms-run8
This model is a fine-tuned version of nvidia/segformer-b5-finetuned-ade-640-640 on the AllanK24/apple-dms-materials dataset.
It achieves the following results on the evaluation set:
Modellartefakte
1 Artefakt model.safetensors
safetensors · 323 MB · SHA-256 0a557384cd53…8742 · Hugging Face
Herunterladen
Loss: 1.3158
Mean Iou: 0.3623
Mean Accuracy: 0.4418
Overall Accuracy: 0.7931
Accuracy Animal Skin: 0.0006
Iou Animal Skin: 0.0006
Accuracy Bone Teeth Horn: 0.0
Iou Bone Teeth Horn: 0.0
Accuracy Brickwork: 0.6866
Iou Brickwork: 0.5481
Accuracy Cardboard: 0.5888
Iou Cardboard: 0.4554
Accuracy Carpet Rug: 0.8537
Iou Carpet Rug: 0.7194
Accuracy Ceiling Tile: 0.8663
Iou Ceiling Tile: 0.7477
Accuracy Ceramic: 0.7220
Iou Ceramic: 0.5581
Accuracy Chalkboard Blackboard: 0.5775
Iou Chalkboard Blackboard: 0.5219
Accuracy Clutter: 0.0
Iou Clutter: 0.0
Accuracy Concrete: 0.5451
Iou Concrete: 0.3830
Accuracy Cork Corkboard: 0.0
Iou Cork Corkboard: 0.0
Accuracy Engineered Stone: 0.0
Iou Engineered Stone: 0.0
Accuracy Fabric Cloth: 0.8904
Iou Fabric Cloth: 0.7591
Accuracy Fiberglass Wool: 0.0
Iou Fiberglass Wool: 0.0
Accuracy Fire: 0.0
Iou Fire: 0.0
Accuracy Foliage: 0.9360
Iou Foliage: 0.8185
Accuracy Food: 0.8928
Iou Food: 0.7456
Accuracy Fur: 0.9172
Iou Fur: 0.7602
Accuracy Gemstone Quartz: 0.0
Iou Gemstone Quartz: 0.0
Accuracy Glass: 0.7353
Iou Glass: 0.5745
Accuracy Hair: 0.8039
Iou Hair: 0.6858
Accuracy Ice: 0.0
Iou Ice: 0.0
Accuracy Leather: 0.4730
Iou Leather: 0.3979
Accuracy Liquid Non-water: 0.0
Iou Liquid Non-water: 0.0
Accuracy Metal: 0.3912
Iou Metal: 0.3013
Accuracy Mirror: 0.5493
Iou Mirror: 0.4350
Accuracy Paint Plaster Enamel: 0.8595
Iou Paint Plaster Enamel: 0.7257
Accuracy Paper: 0.7236
Iou Paper: 0.5573
Accuracy Pearl: 0.0
Iou Pearl: 0.0
Accuracy Photograph Painting: 0.4124
Iou Photograph Painting: 0.3168
Accuracy Plastic Clear: 0.1583
Iou Plastic Clear: 0.1403
Accuracy Plastic Non-clear: 0.4829
Iou Plastic Non-clear: 0.3457
Accuracy Rubber Latex: 0.0001
Iou Rubber Latex: 0.0001
Accuracy Sand: 0.1871
Iou Sand: 0.1813
Accuracy Skin Lips: 0.8032
Iou Skin Lips: 0.6802
Accuracy Sky: 0.9700
Iou Sky: 0.9207
Accuracy Snow: 0.4513
Iou Snow: 0.4329
Accuracy Soap: 0.0
Iou Soap: 0.0
Accuracy Soil Mud: 0.5892
Iou Soil Mud: 0.3437
Accuracy Sponge: 0.0
Iou Sponge: 0.0
Accuracy Stone Natural: 0.6717
Iou Stone Natural: 0.4867
Accuracy Stone Polished: 0.1281
Iou Stone Polished: 0.1186
Accuracy Styrofoam: 0.0
Iou Styrofoam: 0.0
Accuracy Tile: 0.8029
Iou Tile: 0.6400
Accuracy Wallpaper: 0.5318
Iou Wallpaper: 0.4360
Accuracy Water: 0.9102
Iou Water: 0.7919
Accuracy Wax: 0.0
Iou Wax: 0.0
Accuracy Whiteboard: 0.7470
Iou Whiteboard: 0.5827
Accuracy Wicker: 0.4441
Iou Wicker: 0.3946
Accuracy Wood: 0.8514
Iou Wood: 0.7134
Accuracy Wood Tree: 0.1826
Iou Wood Tree: 0.1617
Accuracy Asphalt: 0.6368
Iou Asphalt: 0.4573
Model description
Intended uses & limitations
Training and evaluation data
Training procedure
Training hyperparameters The following hyperparameters were used during training:
learning_rate: 0.0001
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
label_smoothing_factor: 0.1
Training results Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Animal Skin Iou Animal Skin Accuracy Bone Teeth Horn Iou Bone Teeth Horn Accuracy Brickwork Iou Brickwork Accuracy Cardboard Iou Cardboard Accuracy Carpet Rug Iou Carpet Rug Accuracy Ceiling Tile Iou Ceiling Tile Accuracy Ceramic Iou Ceramic Accuracy Chalkboard Blackboard 3.5688 1.7045 150 2.6137 0.0684 0.0998 0.5339 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.3088 0.2399 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
---
library_name: transformers
license: other
base_model: nvidia/segformer-b5-finetuned-ade-640-640
tags:
- vision
- image-segmentation
- segformer
- material-segmentation
- generated_from_trainer
model-index:
- name: segformer-b5-finetuned-apple-dms-run8
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. -->
# segformer-b5-finetuned-apple-dms-run8
This model is a fine-tuned version of [nvidia/segformer-b5-finetuned-ade-640-640](https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640) on the AllanK24/apple-dms-materials dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3158
- Mean Iou: 0.3623
- Mean Accuracy: 0.4418
- Overall Accuracy: 0.7931
- Accuracy Animal Skin: 0.0006
- Iou Animal Skin: 0.0006
- Accuracy Bone Teeth Horn: 0.0
- Iou Bone Teeth Horn: 0.0
- Accuracy Brickwork: 0.6866
- Iou Brickwork: 0.5481
- Accuracy Cardboard: 0.5888
- Iou Cardboard: 0.4554
- Accuracy Carpet Rug: 0.8537
- Iou Carpet Rug: 0.7194
- Accuracy Ceiling Tile: 0.8663
- Iou Ceiling Tile: 0.7477
- Accuracy Ceramic: 0.7220
- Iou Ceramic: 0.5581
- Accuracy Chalkboard Blackboard: 0.5775
- Iou Chalkboard Blackboard: 0.5219
- Accuracy Clutter: 0.0
- Iou Clutter: 0.0
- Accuracy Concrete: 0.5451
- Iou Concrete: 0.3830
- Accuracy Cork Corkboard: 0.0
- Iou Cork Corkboard: 0.0
- Accuracy Engineered Stone: 0.0
- Iou Engineered Stone: 0.0
- Accuracy Fabric Cloth: 0.8904
- Iou Fabric Cloth: 0.7591
- Accuracy Fiberglass Wool: 0.0
- Iou Fiberglass Wool: 0.0
- Accuracy Fire: 0.0
- Iou Fire: 0.0
- Accuracy Foliage: 0.9360
- Iou Foliage: 0.8185
- Accuracy Food: 0.8928
- Iou Food: 0.7456
- Accuracy Fur: 0.9172
- Iou Fur: 0.7602
- Accuracy Gemstone Quartz: 0.0
- Iou Gemstone Quartz: 0.0
- Accuracy Glass: 0.7353
- Iou Glass: 0.5745
- Accuracy Hair: 0.8039
- Iou Hair: 0.6858
- Accuracy Ice: 0.0
- Iou Ice: 0.0
- Accuracy Leather: 0.4730
- Iou Leather: 0.3979
- Accuracy Liquid Non-water: 0.0
- Iou Liquid Non-water: 0.0
- Accuracy Metal: 0.3912
- Iou Metal: 0.3013
- Accuracy Mirror: 0.5493
- Iou Mirror: 0.4350
- Accuracy Paint Plaster Enamel: 0.8595
- Iou Paint Plaster Enamel: 0.7257
- Accuracy Paper: 0.7236
- Iou Paper: 0.5573
- Accuracy Pearl: 0.0
- Iou Pearl: 0.0
- Accuracy Photograph Painting: 0.4124
- Iou Photograp...
Source context: 8 downloads · 0 likes · Pipeline image-segmentation · Library transformers · Repo AllanK24/segformer-b5-finetuned-apple-dms-run8
Iou Chalkboard Blackboard
Accuracy Engineered Stone
Accuracy Liquid Non-water
Accuracy Paint Plaster Enamel
Accuracy Photograph Painting
Accuracy Plastic Non-clear
1.9211 3.4091 300 1.6497 0.1718 0.2221 0.7026 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.7838 0.5890 0.7946 0.6866 0.0131 0.0130 0.0 0.0 0.0 0.0 0.0537 0.0525 0.0 0.0 0.0 0.0 0.8937 0.6446 0.0 0.0 0.0 0.0 0.9330 0.6310 0.8090 0.6758 0.0000 0.0000 0.0 0.0 0.6752 0.4690 0.4928 0.4514 0.0 0.0 0.0 0.0 0.0 0.0 0.0434 0.0413 0.0046 0.0046 0.8531 0.6583 0.6791 0.4309 0.0 0.0 0.0 0.0 0.0 0.0 0.3271 0.2328 0.0 0.0 0.0 0.0 0.4968 0.3999 0.9584 0.9021 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.2658 0.2160 0.0 0.0...
