metadata

license: other
base_model: nvidia/mit-b0
tags:
  - image-segmentation
  - vision
  - generated_from_trainer
model-index:
  - name: segformer-finetuned-sidewalk-10k-steps
    results: []

segformer-finetuned-sidewalk-10k-steps

This model is a fine-tuned version of nvidia/mit-b0 on the Manduzamzam/practice2 dataset. It achieves the following results on the evaluation set:

Loss: 0.6829
Mean Iou: 0.0140
Mean Accuracy: 0.0279
Overall Accuracy: 0.0279
Accuracy Background: nan
Accuracy Object: 0.0279
Iou Background: 0.0
Iou Object: 0.0279

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: 8
eval_batch_size: 8
seed: 1337
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Object	Iou Background	Iou Object
No log	0.71	10	0.6829	0.0140	0.0279	0.0279	nan	0.0279	0.0	0.0279

Framework versions

Transformers 4.34.0.dev0
Pytorch 1.13.1+cu116
Datasets 2.14.5
Tokenizers 0.14.0