model.py

import torch
import torchvision

from torch import nn
def create_vit_model(num_classes:int=121,
                     seed:int=42):
    """Creates a ViT-B/16 feature extractor model and transforms.

    Args:
        num_classes (int, optional): number of target classes. Defaults to 3.
        seed (int, optional): random seed value for output layer. Defaults to 42.

    Returns:
        model (torch.nn.Module): ViT-B/16 feature extractor model.
        transforms (torchvision.transforms): ViT-B/16 image transforms.
    """
    # Create ViT_B_16 pretrained 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 layers in model
    for param in model.parameters():
        param.requires_grad = False

    # Change classifier head to suit our needs (this will be trainable)
    torch.manual_seed(seed)
    model.heads = nn.Sequential(
    nn.LayerNorm(768),
    nn.Dropout(0.2),  # Try 0.1 or 0.2
    nn.Linear(768, 121)
     )

    return model, transforms