Segformer B0 Finetuned Segments Water 2

🚀 segformer-b0-finetuned-segments-water-2

This model is a fine - tuned version of nvidia/mit-b0 on the imadd/water_dataset dataset. It's designed for image segmentation tasks, offering potential solutions for water - related image analysis.

🚀 Quick Start

This section will provide a quick overview of the model's basic information and performance.

📚 Documentation

Model Overview

This model is a fine - tuned version of nvidia/mit-b0 on the imadd/water_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.5845
• Mean Iou: nan
• Mean Accuracy: nan
• Overall Accuracy: nan
• Per Category Iou: [nan, nan]
• Per Category Accuracy: [nan, nan]

Training and Evaluation

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: 10

Training Results

Framework Versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1

📄 License

This model is licensed under the Apache - 2.0 license.