Mobilevit Small 10k Steps

🚀 mobilevit-small-10k-steps

This model is a fine - tuned version of apple/deeplabv3-mobilevit-small on the Efferbach/lane_master2 dataset. It offers a solution for image - segmentation tasks in the vision field, with specific performance metrics on the evaluation set.

📚 Documentation

Model Overview

This model is a fine - tuned version of apple/deeplabv3-mobilevit-small on the Efferbach/lane_master2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0821
• Mean Iou: 0.0
• Mean Accuracy: 0.0
• Overall Accuracy: 0.0
• Accuracy Background: nan
• Accuracy Left: 0.0
• Accuracy Right: 0.0
• Iou Background: 0.0
• Iou Left: 0.0
• Iou Right: 0.0

Training and Evaluation

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 6e - 05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: polynomial
• training_steps: 10000

Training results

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3

📄 License

The model is released under the "other" license.