---
license: mit
pipeline_tag: image-classification
tags:
- Deep-Learnign
- FoundationModel
- MedicalImaging
- BrainMRI
---
# BrainIAC Model

This is the official implementation of the BrainIAC model, a 3D ResNet50-based architecture designed for brain MRI analysis.

## Model Description

BrainIAC is built on a modified ResNet50 architecture that processes 3D brain imaging data. The model has been adapted to handle volumetric inputs through 3D convolutions and produces feature vectors that capture relevant brain imaging characteristics.

## Model Architecture
- Base Architecture: ResNet50 (modified for 3D)
- Input: 3D brain volumes [batch_size, 1, H, W, D]
- Output: Feature vector of dimension 2048
- First layer: 3D convolution (1 channel input)
- Final layer: Identity (returns features directly)

## Usage

```python
import brainiac
from transformers import AutoModel
import torch

# Load model
model = AutoModel.from_pretrained("Divytak/brainiac")
model.eval()


# dummy input
batch_size = 1
H, W, D = 128, 128, 128  
input_tensor = torch.randn(batch_size, 1, H, W, D)

# Get features
with torch.no_grad():
    features = model(input_tensor)

print(f"Output feature shape: {features.shape}")  # Should be [batch_size, 2048]
```

## Requirements
```
torch>=2.0.0
monai
transformers
brainiac-model
```