--- license: other tags: - generated_from_trainer model-index: - name: segformer-b0-DeepCrack results: [] --- # segformer-b0-DeepCrack This model is a fine-tuned version of [nvidia/mit-b4](https://huggingface.co/nvidia/mit-b4) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4264 - Mean Iou: 0.1964 - Mean Accuracy: 0.3929 - Overall Accuracy: 0.3929 - Accuracy Background: nan - Accuracy Cracked: 0.3929 - Iou Background: 0.0 - Iou Cracked: 0.3929 ## 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 Cracked | Iou Background | Iou Cracked | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:----------------:|:--------------:|:-----------:| | 0.5096 | 1.0 | 20 | 0.4264 | 0.1964 | 0.3929 | 0.3929 | nan | 0.3929 | 0.0 | 0.3929 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3