Hugging Face's logo

Greynar
/
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
Greynar's picture
Greynar
End of training
3ba6271
preview code
|
raw
history blame
9.11 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: 4.1737
  • Mean Iou: 0.0412
  • Mean Accuracy: 0.1197
  • Overall Accuracy: 0.3353
  • Per Category Iou: [0.2401425714267801, 0.034835822859774955, 0.5233226285438033, 0.05315318739919738, 0.3363441411947116, 0.002136415124098476, 0.09670075065121168, 0.0, 0.0, 0.0, nan, nan, 0.498363641748608, 0.25150888487559303, 0.0, 0.0, 0.08397363262672963, 0.0, 0.07671808913771606, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.19346311110638784, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 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, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan]
  • Per Category Accuracy: [0.6895015391262084, 0.3058347775852109, 0.9947227819603158, 0.05414555351492488, 0.4346378378378378, 0.0023242754188375504, 0.12029455130074054, 0.0, 0.0, 0.0, nan, nan, 0.8755609902046232, 0.32841060897331464, 0.0, nan, 0.11352886582952221, 0.0, 0.07671808913771606, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.9129513540621865, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 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, nan, nan, nan, 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, 0.0, nan, nan, nan, nan, 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
4.0917 1.0 20 4.1737 0.0412 0.1197 0.3353 [0.2401425714267801, 0.034835822859774955, 0.5233226285438033, 0.05315318739919738, 0.3363441411947116, 0.002136415124098476, 0.09670075065121168, 0.0, 0.0, 0.0, nan, nan, 0.498363641748608, 0.25150888487559303, 0.0, 0.0, 0.08397363262672963, 0.0, 0.07671808913771606, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.19346311110638784, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 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, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan] [0.6895015391262084, 0.3058347775852109, 0.9947227819603158, 0.05414555351492488, 0.4346378378378378, 0.0023242754188375504, 0.12029455130074054, 0.0, 0.0, 0.0, nan, nan, 0.8755609902046232, 0.32841060897331464, 0.0, nan, 0.11352886582952221, 0.0, 0.07671808913771606, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.9129513540621865, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 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, nan, nan, nan, 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, 0.0, nan, nan, nan, nan, nan]

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1