Deit Base Patch16 224 Plant Seedling Classification

🚀 weeds_hfclass16

This model is fine - tuned on the imagefolder dataset and can be used for image classification tasks, achieving high accuracy.

🚀 Quick Start

This model, weeds_hfclass16, is trained on a balanced dataset with 250 samples per class, split into 0.8 for training, 0.1 for validation, and 0.1 for testing. The images are resized to 224x224.

Dataset: https://www.kaggle.com/datasets/vbookshelf/v2-plant-seedlings-dataset

This model is a fine - tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.1597
• Accuracy: 0.9467

📚 Documentation

Model Information

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training Results

Framework Versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.10.1
• Tokenizers 0.13.2

📄 License

This model is licensed under the Apache 2.0 license.