metadata

license: other
base_model: nvidia/mit-b0
tags:
  - vision
  - image-segmentation
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-SixrayKnife8-21-2024_saad5
    results: []

segformer-b0-finetuned-segments-SixrayKnife8-21-2024_saad5

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: 0.2923
Mean Iou: 0.8066
Mean Accuracy: 0.9078
Overall Accuracy: 0.9857
Accuracy Bkg: 0.9917
Accuracy Knife: 0.8251
Accuracy Gun: 0.9065
Iou Bkg: 0.9869
Iou Knife: 0.7133
Iou Gun: 0.7196

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: 20
eval_batch_size: 20
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 Bkg	Accuracy Knife	Accuracy Gun	Iou Bkg	Iou Knife	Iou Gun
0.8263	5.0	20	0.9552	0.5735	0.8760	0.9414	0.9464	0.8112	0.8703	0.9424	0.4242	0.3540
0.6154	10.0	40	0.6184	0.6297	0.7711	0.9652	0.9800	0.6061	0.7272	0.9657	0.4854	0.4379
0.5165	15.0	60	0.5098	0.6805	0.8233	0.9714	0.9826	0.7375	0.7498	0.9720	0.5691	0.5003
0.4503	20.0	80	0.4561	0.7103	0.8818	0.9735	0.9805	0.7960	0.8690	0.9742	0.5898	0.5670
0.4154	25.0	100	0.3958	0.7526	0.8997	0.9791	0.9852	0.8206	0.8934	0.9800	0.6237	0.6540
0.3659	30.0	120	0.3529	0.7810	0.8969	0.9832	0.9899	0.7932	0.9076	0.9844	0.6814	0.6773
0.3616	35.0	140	0.3253	0.7949	0.8937	0.9848	0.9918	0.8004	0.8889	0.9858	0.6954	0.7035
0.3666	40.0	160	0.3110	0.8018	0.9085	0.9852	0.9911	0.8255	0.9087	0.9863	0.7079	0.7112
0.3082	45.0	180	0.2983	0.8011	0.9037	0.9852	0.9914	0.8195	0.9002	0.9863	0.6982	0.7189
0.3097	50.0	200	0.2923	0.8066	0.9078	0.9857	0.9917	0.8251	0.9065	0.9869	0.7133	0.7196

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1