Hugging Face's logo

IslemTouati
/
segformer-b0-scene-parse-150

Transformers
TensorBoard
Safetensors
segformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
segformer-b0-scene-parse-150 / README.md
IslemTouati's picture
IslemTouati
End of training
2806416 verified
preview code
|
raw
history blame
9.06 kB
metadata
license: other
base_model: nvidia/mit-b0
tags:
  - generated_from_trainer
datasets:
  - scene_parse_150
model-index:
  - name: segformer-b0-scene-parse-150
    results: []

segformer-b0-scene-parse-150

This model is a fine-tuned version of nvidia/mit-b0 on the scene_parse_150 dataset. It achieves the following results on the evaluation set:

  • Loss: 3.6391
  • Mean Iou: 0.0583
  • Mean Accuracy: 0.1172
  • Overall Accuracy: 0.4492
  • Per Category Iou: [0.44041294308583534, nan, nan, 0.6666970930892689, nan, 0.33468836772838806, nan, nan, 0.010483214113553378, nan, 0.09776380089668009, nan, nan, nan, 0.27788378028383004, 0.0, nan, 0.0, 0.0003410360439818898, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.10667274078691827, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.07423709941194892, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.02291795825583798, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.12350896966281581, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan]
  • Per Category Accuracy: [0.6424969817484554, nan, nan, 0.8805785816574676, nan, 0.46181318389743264, nan, nan, 0.01073188993573345, nan, 0.10568203217142234, nan, nan, nan, 0.6834847599119304, 0.0, nan, nan, 0.00041847041847041847, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.23207169236547248, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.551230945262614, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.03717359970502464, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.1452108041255328, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan]

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: 2
  • eval_batch_size: 2
  • 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
3.747 1.0 20 3.6391 0.0583 0.1172 0.4492 [0.44041294308583534, nan, nan, 0.6666970930892689, nan, 0.33468836772838806, nan, nan, 0.010483214113553378, nan, 0.09776380089668009, nan, nan, nan, 0.27788378028383004, 0.0, nan, 0.0, 0.0003410360439818898, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.10667274078691827, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.07423709941194892, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.02291795825583798, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.12350896966281581, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan] [0.6424969817484554, nan, nan, 0.8805785816574676, nan, 0.46181318389743264, nan, nan, 0.01073188993573345, nan, 0.10568203217142234, nan, nan, nan, 0.6834847599119304, 0.0, nan, nan, 0.00041847041847041847, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.23207169236547248, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.551230945262614, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.03717359970502464, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.1452108041255328, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan]

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.2.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1