model.py

import torch
import torchvision

from torch import nn

def create_vit_model(num_classes: int = 3,
                     seed: int = 42):
    # Create ViT_B_16 pre-trained weights, transforms and model
    weights = torchvision.models.ViT_B_16_Weights.DEFAULT
    transforms = weights.transforms()
    model = torchvision.models.vit_b_16(weights = weights)

    # Freeze all of the base layers
    for param in model.parameters():
        param.requires_grad = False

    # Change classifier head to suit our needs
    torch.manual_seed(seed)
    model.heads = nn.Sequential(nn.Linear(in_features = 768,
                                          out_features = num_classes))

    return model, transforms