metadata

license: other
base_model: nvidia/mit-b0
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: 0.5986
Mean Iou: 0.5110
Mean Accuracy: 0.8118
Overall Accuracy: 0.8081
Accuracy Object1: nan
Accuracy Object2: 0.7529
Accuracy Object3: 0.8707
Iou Object1: 0.0
Iou Object2: 0.7267
Iou Object3: 0.8065

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 Object1	Accuracy Object2	Accuracy Object3	Iou Object2	Iou Object3
0.7244	1.4286	20	0.6924	0.4978	0.8311	0.8263	nan	0.7536	0.9087	0.7153	0.7782
0.7251	2.8571	40	0.6470	0.5105	0.8256	0.8213	nan	0.7572	0.8940	0.7246	0.8069
0.6558	4.2857	60	0.6246	0.5148	0.8243	0.8210	nan	0.7714	0.8772	0.7350	0.8095
0.6463	5.7143	80	0.5954	0.5100	0.8126	0.8098	nan	0.7680	0.8572	0.7295	0.8004
0.63	7.1429	100	0.5892	0.5082	0.8073	0.8043	nan	0.7582	0.8564	0.7254	0.7991
0.5935	8.5714	120	0.5923	0.5134	0.8155	0.8127	nan	0.7694	0.8616	0.7369	0.8031
0.6137	10.0	140	0.5986	0.5110	0.8118	0.8081	nan	0.7529	0.8707	0.7267	0.8065

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1