Swin Tiny Patch4 Window7 224 Finetuned Eurosat

🚀 swin-tiny-patch4-window7-224-finetuned-eurosat

This model is a fine - tuned version of microsoft/swin-tiny-patch4-window7-224 on the image_folder dataset, achieving high accuracy in image classification.

🚀 Quick Start

This model is a fine - tuned version of microsoft/swin-tiny-patch4-window7-224 on the image_folder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0767
• Accuracy: 0.9726

✨ Features

• High Accuracy: Achieves an accuracy of 0.9726 on the evaluation set.
• Fine - Tuned: Based on the pre - trained microsoft/swin-tiny-patch4-window7-224 model.

📚 Documentation

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: 5e - 05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1

📄 License

This model is licensed under the Apache - 2.0 license.