Test-SegFormer_Mixed_Set2_788images_mit-b5_RGB

• Loss: 0.1661
• Mean Iou: 0.7900
• Mean Accuracy: 0.8412
• Overall Accuracy: 0.9471
• Accuracy Background: 0.9799
• Accuracy Melt: 0.5677
• Accuracy Substrate: 0.9760
• Iou Background: 0.9430
• Iou Melt: 0.4987
• Iou Substrate: 0.9285

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Framework versions

• Transformers 4.41.2
• Pytorch 2.0.1+cu117
• Datasets 2.19.2
• Tokenizers 0.19.1