import torch
import torchvision

def create_effnet_b2_model(num_classes:int = 3):
    """Creates an EfficientNetB2 feature extractor model and transforms
    
    Args: 
        num_classes (int, optional): number of classes in the classifier head. Defaults to 3.

    Returns:
        model (torch.nn.Module): EfficientNetB2 feature extractor model
        transforms (torchvision.transforms): EfficientNetB2 image transforms.
    """

    # Get pretrained weights and use them for model, get transforms from them
    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
    transforms = weights.transforms()
    model = torchvision.models.efficientnet_b2(weights=weights)

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

    # Change classifier head
    model.classifier = torch.nn.Sequential(
        torch.nn.Dropout(p = 0.3, inplace= True),
        torch.nn.Linear(in_features=1408, out_features=num_classes)
    )

    return model, transforms