Clip Vit Base Patch32 Stanford Cars

🚀 Vision Encoder Fine - Tuning Model

This project focuses on fine - tuning the vision encoder of the CLIP model using the Stanford Cars dataset, aiming to improve the accuracy of image recognition.

🚀 Quick Start

Prerequisites

• Ensure you have installed the transformers library.

Loading the Model

from transformers import CLIPVisionModel

vision_model = CLIPVisionModel.from_pretrained('tanganke/clip-vit-base-patch32_stanford-cars')

Substituting the Vision Encoder

from transformers import CLIPModel

clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
clip_model.vision_model.load_state_dict(vision_model.vision_model.state_dict())

✨ Features

• Fine - tune the vision encoder of the CLIP model to improve image recognition accuracy.
• Use the Stanford Cars dataset for training.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import CLIPVisionModel

vision_model = CLIPVisionModel.from_pretrained('tanganke/clip-vit-base-patch32_stanford-cars')

Advanced Usage

from transformers import CLIPModel

clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
clip_model.vision_model.load_state_dict(vision_model.vision_model.state_dict())

📚 Documentation

Model Details

Training Details

The Adam Optimizer was used with a constant learning rate of 1e - 5 for 4000 steps of training (batch_size = 32). Only the vision encoder was fine - tuned.

Evaluation Results