README.md

metadata

library_name: transformers
license: other
base_model: nvidia/mit-b0
tags:
  - vision
  - image-segmentation
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-georeferencing
    results: []

segformer-b0-finetuned-georeferencing

This model is a fine-tuned version of nvidia/mit-b0 on the zhaoqiao0120/georeferencing_2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1456
• Mean Iou: 0.0
• Mean Accuracy: 0.0
• Overall Accuracy: 0.0
• Accuracy Unlabeled: nan
• Accuracy Object: 0.0
• Iou Unlabeled: 0.0
• Iou Object: 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: 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Object	Iou Unlabeled	Iou Object
0.4873	5.0	20	0.5349	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.3815	10.0	40	0.3688	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.3355	15.0	60	0.2834	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.2632	20.0	80	0.2497	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.187	25.0	100	0.2110	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.2059	30.0	120	0.1814	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.1468	35.0	140	0.1703	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.1357	40.0	160	0.1479	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.1443	45.0	180	0.1445	0.0	0.0	0.0	nan	0.0	0.0	0.0
0.1344	50.0	200	0.1456	0.0	0.0	0.0	nan	0.0	0.0	0.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cpu
• Datasets 2.21.0
• Tokenizers 0.19.1