SegFormer_Clean_Set1_240430_V2-Augmented_mit-b5_RGB

This model is a fine-tuned version of nvidia/mit-b5 on the Hasano20/Clean_Set1_240430_V2-Augmented dataset. It achieves the following results on the evaluation set:

• Loss: 0.4812
• Mean Iou: 0.6072
• Mean Accuracy: 0.6905
• Overall Accuracy: 0.8761
• Accuracy Background: 0.8967
• Accuracy Melt: 0.2439
• Accuracy Substrate: 0.9311
• Iou Background: 0.8325
• Iou Melt: 0.1423
• Iou Substrate: 0.8467

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• 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 Background	Accuracy Melt	Accuracy Substrate	Iou Background	Iou Melt	Iou Substrate
0.2826	6.6667	20	0.4812	0.6072	0.6905	0.8761	0.8967	0.2439	0.9311	0.8325	0.1423	0.8467

Framework versions

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