Hugging Face's logo

pablojrios
/
segformer-b0-finetuned-segments-sidewalk-2

Transformers
PyTorch
segformer
vision
semantic-segmentation
Generated from Trainer
Inference Endpoints
Model card Files Community
segformer-b0-finetuned-segments-sidewalk-2 / README.md
pablojrios's picture
pablojrios
update model card README.md
794eddc
preview code
|
raw
history blame
5.05 kB
metadata
license: other
tags:
  - vision
  - semantic-segmentation
  - generated_from_trainer
datasets:
  - ds_tag1
  - ds_tag2
model-index:
  - name: segformer-b0-finetuned-segments-sidewalk-2
    results: []

segformer-b0-finetuned-segments-sidewalk-2

This model is a fine-tuned version of nvidia/mit-b0 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6449
  • Mean Iou: 0.1548
  • Mean Accuracy: 0.2076
  • Overall Accuracy: 0.7095
  • Per Category Iou: [nan, 0.5140599138533896, 0.7174504614949924, 0.0, 0.2891488100731331, 0.0017519579090739337, nan, 2.896471421964715e-05, 0.0, 0.0, 0.572608873148249, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.5022343403146414, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.7363557838688449, 0.5136205023614682, 0.7964013451546083, 0.0, 0.0, 0.0, 0.0]
  • Per Category Accuracy: [nan, 0.8064241561480351, 0.9062036975406429, 0.0, 0.30153947289328054, 0.0017733699866858271, nan, 2.8972126882463944e-05, 0.0, 0.0, 0.8850507869466231, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.8639780836322506, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.9144389240012535, 0.668388685537115, 0.8810818896148822, 0.0, 0.0, 0.0, 0.0]

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 6e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Per Category Iou Per Category Accuracy
1.9382 0.5 100 1.8048 0.1339 0.1853 0.6789 [nan, 0.4752344017185758, 0.694067134540047, 0.0, 0.12409993164299513, 0.0008311245506368295, nan, 0.0013254481219605065, 0.0, 0.0, 0.5409277406718473, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.4841581403327513, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.690024139245331, 0.2320795469313362, 0.7749690806204844, 0.0, 0.0, 0.0, 0.0] [nan, 0.7639758158865736, 0.8976245985998512, 0.0, 0.12474373026419283, 0.0008415168706412761, nan, 0.0013278891487795974, 0.0, 0.0, 0.880573362170307, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.8526119656818829, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.9393214014210579, 0.26355731572405905, 0.8357039981550286, 0.0, 0.0, 0.0, 0.0]
1.5173 1.0 200 1.6449 0.1548 0.2076 0.7095 [nan, 0.5140599138533896, 0.7174504614949924, 0.0, 0.2891488100731331, 0.0017519579090739337, nan, 2.896471421964715e-05, 0.0, 0.0, 0.572608873148249, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.5022343403146414, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.7363557838688449, 0.5136205023614682, 0.7964013451546083, 0.0, 0.0, 0.0, 0.0] [nan, 0.8064241561480351, 0.9062036975406429, 0.0, 0.30153947289328054, 0.0017733699866858271, nan, 2.8972126882463944e-05, 0.0, 0.0, 0.8850507869466231, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.8639780836322506, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.9144389240012535, 0.668388685537115, 0.8810818896148822, 0.0, 0.0, 0.0, 0.0]

Framework versions

  • Transformers 4.21.1
  • Pytorch 1.12.1
  • Datasets 2.4.0
  • Tokenizers 0.12.1