README.md

metadata

base_model: nvidia/mit-b0
license: other
tags:
  - vision
  - image-segmentation
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-SixrayKnife8-19-2024
    results: []

segformer-b0-finetuned-segments-SixrayKnife8-19-2024

This model is a fine-tuned version of nvidia/mit-b0 on the saad7489/SixraygunTest dataset. It achieves the following results on the evaluation set:

• Loss: 0.9038
• Mean Iou: 0.4486
• Mean Accuracy: 0.8693
• Overall Accuracy: 0.8708
• Accuracy Bkg: 0.8709
• Accuracy Gun: 0.8680
• Accuracy Knife: 0.8689
• Iou Bkg: 0.8700
• Iou Gun: 0.1670
• Iou Knife: 0.3088

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: 1e-05
• train_batch_size: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Bkg	Accuracy Gun	Accuracy Knife	Iou Bkg	Iou Gun	Iou Knife
1.0919	1.4286	20	1.1033	0.1925	0.6509	0.3960	0.3783	0.8281	0.7462	0.3783	0.0314	0.1677
1.0576	2.8571	40	1.0473	0.3242	0.7738	0.6681	0.6608	0.8826	0.7781	0.6607	0.0600	0.2518
0.9844	4.2857	60	0.9913	0.3823	0.8265	0.7783	0.7750	0.8873	0.8171	0.7748	0.0928	0.2793
0.9604	5.7143	80	0.9385	0.4206	0.8552	0.8396	0.8386	0.8813	0.8457	0.8381	0.1334	0.2902
0.9418	7.1429	100	0.9073	0.4389	0.8651	0.8592	0.8588	0.8795	0.8570	0.8581	0.1520	0.3065
0.9029	8.5714	120	0.8989	0.4474	0.8672	0.8683	0.8684	0.8712	0.8620	0.8677	0.1621	0.3123
0.9277	10.0	140	0.9038	0.4486	0.8693	0.8708	0.8709	0.8680	0.8689	0.8700	0.1670	0.3088

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1