DaViT Model

This repository contains the implementation of the DaViT (Dual-Attention Vision Transformer) model for image classification tasks. The model leverages dual attention mechanisms to improve performance on various image datasets.

Model Description

DaViT (Dual-Attention Vision Transformer) is designed to handle image classification tasks effectively. It combines spatial and channel attention mechanisms to capture intricate details in images. The model has multiple stages, each with convolutional embeddings and attention blocks.

Example

Here is an example of how to use the DaViT model for image classification:

import torch
from transformers import AutoModel, AutoConfig

# Load the configuration and model
config = AutoConfig.from_pretrained("your-username/DaViT")
model = AutoModel.from_pretrained("your-username/DaViT")

# Generate a random sample input tensor with shape (batch_size, channels, height, width)
batch_size = 2
channels = 3
height = 224
width = 224
sample_input = torch.randn(batch_size, channels, height, width)

# Pass the sample input through the model
output = model(sample_input)

# Print the output shape
print(f"Output shape: {output.shape}")

Files

configuration_davit.py: Contains the DaViTConfig class.
modeling_davit.py: Contains the DaViTModel class.
test_davit_model.py: Script to test the model.
config.json: Configuration file for the model.
model.safetensors: Pretrained weights of the DaViT model.

Credits

This model is inspired by and builds upon the ideas presented in the Florence-2-large model by Microsoft.