Vit Base Cats Vs Dogs

🚀 vit-base-cats-vs-dogs

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) on the cats_vs_dogs dataset, achieving high accuracy in image classification.

🚀 Quick Start

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) on the cats_vs_dogs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0369
• Accuracy: 0.9883

💻 Usage Examples

Basic Usage

from transformers import ViTFeatureExtractor, ViTModel
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
model = ViTModel.from_pretrained('akahana/vit-base-cats-vs-dogs')
inputs = feature_extractor(images=image, return_tensors="pt")

outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• 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: linear
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.12.5
• Pytorch 1.10.0+cu111
• Datasets 1.16.1
• Tokenizers 0.10.3

📄 License

This model is licensed under the Apache - 2.0 license.

📋 Model Information