import torch
import torchvision

from torch import nn

def create_transformer_model(num_classes:int=325, # default output classes = 3 (pizza, steak, sushi)
                          seed:int=42):
  # 1, 2, 3 Create EffNetB2 pretrained weights, transforms and model
  weights = torchvision.models.ViT_B_16_Weights.DEFAULT
  transforms = weights.transforms()
  model = torchvision.models.vit_b_16(weights=weights)

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

  # 5. Change classifier head with random seed for reproducibility
  torch.manual_seed(seed)
  model.classifier = nn.Sequential(
      nn.Dropout(p=0.3, inplace=True),
      nn.Linear(in_features=768, out_features=num_classes)
  )

  return model, transforms