Saltar al contenido Studio Crea imágenes y vídeo sin vivir dentro de la cadena de herramientas de IA.
Un espacio local para convertir flujos de ComfyUI en herramientas que puedas usar, entender y retomar.
© 2026 Tea Time Labs
Creación con IA local, organizada.
¿Tienes un flujo de trabajo de ComfyUI? Obtén un Workflow Doc legible en tu navegador. Haz legible un flujo de trabajo. Pruébalo ahora ↗
Segformer B0 Finetuned Segments Sidewalk 2 | ST Studio
Recursos / Segformer B0 Finetuned Segments Sidewalk 2 Segformer B0 Finetuned Segments Sidewalk 2 This model is a fine-tuned version of segformer-b0-finetuned-segments-sidewalk-2 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set: Loss: 0.6763 Mean Iou: 0.2315 Mean...
This model is a fine-tuned version of segformer-b0-finetuned-segments-sidewalk-2 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set: Loss: 0.6763 Mean Iou: 0.2315 Mean...
Tipo Other Modelo base segformer-b0-finetuned-segments-sidewalk-2 Versión Revision ccf6ab1
Fuente del modelo
Tipo Other
Tamaño del archivo 14,2 MB
Modelo base segformer-b0-finetuned-segments-sidewalk-2
Versión vRevision ccf6ab1
Actualizado 15 sept 2026
Descargas 2
Fuente Hugging Face
segformer-b0-finetuned-segments-sidewalk-2
This model is a fine-tuned version of segformer-b0-finetuned-segments-sidewalk-2 on the segments/sidewalk-semantic dataset.
It achieves the following results on the evaluation set:
Artefactos del modelo
1 artefacto model.safetensors
safetensors · 14,2 MB · SHA-256 3f2009f77599…c6b0 · Hugging Face
Descargar Extractos de fuentes
2 extractos
Loss: 0.6763
Mean Iou: 0.2315
Mean Accuracy: 0.2798
Overall Accuracy: 0.8133
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.8064
Accuracy Flat-sidewalk: 0.9354
Accuracy Flat-crosswalk: 0.0398
Accuracy Flat-cyclinglane: 0.7199
Accuracy Flat-parkingdriveway: 0.4433
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.4324
Accuracy Human-person: 0.2896
Accuracy Human-rider: 0.0
Accuracy Vehicle-car: 0.9299
Accuracy Vehicle-truck: 0.0
Accuracy Vehicle-bus: 0.0
Accuracy Vehicle-tramtrain: nan
Accuracy Vehicle-motorcycle: 0.0
Accuracy Vehicle-bicycle: 0.0
Accuracy Vehicle-caravan: 0.0
Accuracy Vehicle-cartrailer: 0.0
Accuracy Construction-building: 0.9033
Accuracy Construction-door: 0.0
Accuracy Construction-wall: 0.5104
Accuracy Construction-fenceguardrail: 0.0
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: 0.0
Accuracy Construction-stairs: 0.0
Accuracy Object-pole: 0.0262
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.0
Accuracy Nature-vegetation: 0.9487
Accuracy Nature-terrain: 0.8937
Accuracy Sky: 0.9543
Accuracy Void-ground: 0.0
Accuracy Void-dynamic: 0.0
Accuracy Void-static: 0.1203
Accuracy Void-unclear: 0.0
Iou Unlabeled: nan
Iou Flat-road: 0.6265
Iou Flat-sidewalk: 0.8232
Iou Flat-crosswalk: 0.0398
Iou Flat-cyclinglane: 0.5825
Iou Flat-parkingdriveway: 0.3360
Iou Flat-railtrack: nan
Iou Flat-curb: 0.3409
Iou Human-person: 0.2742
Iou Human-rider: 0.0
Iou Vehicle-car: 0.7473
Iou Vehicle-truck: 0.0
Iou Vehicle-bus: 0.0
Iou Vehicle-tramtrain: nan
Iou Vehicle-motorcycle: 0.0
Iou Vehicle-bicycle: 0.0
Iou Vehicle-caravan: 0.0
Iou Vehicle-cartrailer: 0.0
Iou Construction-building: 0.7214
Iou Construction-door: 0.0
Iou Construction-wall: 0.3282
Iou Construction-fenceguardrail: 0.0
Iou Construction-bridge: 0.0
Iou Construction-tunnel: 0.0
Iou Construction-stairs: 0.0
Iou Object-pole: 0.0260
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0
Iou Nature-vegetation: 0.8246
Iou Nature-terrain: 0.7455
Iou Sky: 0.8968
Iou Void-ground: 0.0
Iou Void-dynamic: 0.0
Iou Void-static: 0.0936
Iou Void-unclear: 0.0
Model description
Intended uses & limitations
Training and evaluation data
Training procedure
Training hyperparameters The following hyperparameters were used during training:
learning_rate: 6e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
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: linear
num_epochs: 1
Training results Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Unlabeled Accuracy Flat-road Accuracy Flat-sidewalk Accuracy Flat-crosswalk Accuracy Flat-cyclinglane Accuracy Flat-parkingdriveway Accuracy Flat-railtrack Accuracy Flat-curb Accuracy Human-person Accuracy Human-rider Accuracy Vehicle-car Accuracy Vehicle-truck Accuracy Vehicle-bus Accuracy Vehicle-tramtrain 1.1481 0.05 20 0.8073 0.1984 0.2411 0.7874 nan 0.7279 0.9629 0.0 0.6244 0.1980 nan 0.2204 0.0125 0.0 0.9295 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8887
---
library_name: transformers
base_model: segformer-b0-finetuned-segments-sidewalk-2
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformer-b0-finetuned-segments-sidewalk-2
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-b0-finetuned-segments-sidewalk-2
This model is a fine-tuned version of [segformer-b0-finetuned-segments-sidewalk-2](https://huggingface.co/segformer-b0-finetuned-segments-sidewalk-2) on the segments/sidewalk-semantic dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6763
- Mean Iou: 0.2315
- Mean Accuracy: 0.2798
- Overall Accuracy: 0.8133
- Accuracy Unlabeled: nan
- Accuracy Flat-road: 0.8064
- Accuracy Flat-sidewalk: 0.9354
- Accuracy Flat-crosswalk: 0.0398
- Accuracy Flat-cyclinglane: 0.7199
- Accuracy Flat-parkingdriveway: 0.4433
- Accuracy Flat-railtrack: nan
- Accuracy Flat-curb: 0.4324
- Accuracy Human-person: 0.2896
- Accuracy Human-rider: 0.0
- Accuracy Vehicle-car: 0.9299
- Accuracy Vehicle-truck: 0.0
- Accuracy Vehicle-bus: 0.0
- Accuracy Vehicle-tramtrain: nan
- Accuracy Vehicle-motorcycle: 0.0
- Accuracy Vehicle-bicycle: 0.0
- Accuracy Vehicle-caravan: 0.0
- Accuracy Vehicle-cartrailer: 0.0
- Accuracy Construction-building: 0.9033
- Accuracy Construction-door: 0.0
- Accuracy Construction-wall: 0.5104
- Accuracy Construction-fenceguardrail: 0.0
- Accuracy Construction-bridge: 0.0
- Accuracy Construction-tunnel: 0.0
- Accuracy Construction-stairs: 0.0
- Accuracy Object-pole: 0.0262
- Accuracy Object-trafficsign: 0.0
- Accuracy Object-trafficlight: 0.0
- Accuracy Nature-vegetation: 0.9487
- Accuracy Nature-terrain: 0.8937
- Accuracy Sky: 0.9543
- Accuracy Void-ground: 0.0
- Accuracy Void-dynamic: 0.0
- Accuracy Void-static: 0.1203
- Accuracy Void-unclear: 0.0
- Iou Unlabeled: nan
- Iou Flat-road: 0.6265
- Iou Flat-sidewalk: 0.8232
- Iou Flat-crosswalk: 0.0398
- Iou Flat-cyclinglane: 0.5825
- Iou Flat-parkingdriveway: 0.3360
- Iou Flat-railtrack: nan
- Iou Flat-curb: 0.3409
- Iou Human-person: 0.2742
- Iou Human-rider: 0.0
- Iou Vehicle-car: 0.7473
- Iou Vehicle-truck: 0.0
- Iou Vehicle-bus: 0.0
- Iou Vehicle-tramtrain: nan
- Iou Vehicle-motorcycle: 0.0
- Iou Vehicle-bicycle: 0.0
- Iou Vehicle-carav...
Source context: 2 downloads · 0 likes · Pipeline image-segmentation · Library transformers · Repo gilcx/segformer-b0-finetuned-segments-sidewalk-2
Accuracy Vehicle-motorcycle
Accuracy Vehicle-cartrailer
Accuracy Construction-building
Accuracy Construction-door
Accuracy Construction-wall
Accuracy Construction-fenceguardrail
Accuracy Construction-bridge
Accuracy Construction-tunnel
Accuracy Construction-stairs
Accuracy Object-trafficsign
Accuracy Object-trafficlight
Accuracy Nature-vegetation
Iou Construction-building
Iou Construction-fenceguardrail
0.7058 0.1 40 0.7656 0.2103 0.2558 0.7984 nan 0.8705 0.9184 0.0 0.5946 0.3402 nan 0.3315 0.1077 0.0 0.9105 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9097 0.0 0.3762 0.0001 0.0 0.0 0.0 0.0058 0.0 0.0 0.9531 0.8913 0.9384 0.0 0.0 0.0379 0.0 nan 0.5951 0.8128 0.0 0.5103 0.2786 nan 0.2719 0.1061 0.0 0.7367 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7021 0.0 0.2680 0.0001 0.0 0.0 0.0 0.0058 0.0 0.0 0.8104 0.7135 0.8867 0.0 0.0 0.0332 0.0
0.8220 0.15 60 0.7662 0.2063 0.2492 0.7933 nan 0.7001 0.9570 0.0048 0.6193 0.3344 nan 0.3458 0.0415 0.0 0.9398 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9151 0.0 0.3421 0.0001 0.0 0.0 0.0 0.0045 0.0 0.0 0.9547 0.8523 0.9412 0.0 0.0 0.0205 0.0 nan 0.5909 0.7803 0.0048 0.5455 0.2652 nan 0.2549 0.0408 0.0 0.7019 0.0 0.0 nan 0.0 0.0 0.0...
