segformer-b0-finetuned-breastcancer-oct-22

This model is a fine-tuned version of nvidia/mit-b0 on the as-cle-bert/breastcancer-semantic-segmentation dataset. It achieves the following results on the evaluation set:

• Loss: 1.2330
• Mean Iou: 0.3012
• Mean Accuracy: 0.5964
• Overall Accuracy: 0.8331
• Accuracy Background: nan
• Accuracy Benign Breast Cancer: 0.1308
• Accuracy Malignant Breast Cancer: 0.8042
• Accuracy Ignore: 0.8543
• Iou Background: 0.0
• Iou Benign Breast Cancer: 0.0749
• Iou Malignant Breast Cancer: 0.2943
• Iou Ignore: 0.8356

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Benign Breast Cancer	Accuracy Malignant Breast Cancer	Accuracy Ignore	Iou Background	Iou Benign Breast Cancer	Iou Malignant Breast Cancer	Iou Ignore
1.1649	0.625	10	1.2330	0.3012	0.5964	0.8331	nan	0.1308	0.8042	0.8543	0.0	0.0749	0.2943	0.8356

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cpu
• Datasets 3.0.0
• Tokenizers 0.19.1