import torch
import torch.nn as nn
import torchvision.models as models
import torchvision.transforms as transforms
import os
from PIL import Image

# Define the ResNet-50 model
model = models.resnet50(pretrained=True)

# Remove the classification head (the fully connected layer)
num_features = model.fc.in_features
model.fc = nn.Identity()

# Set the model to evaluation mode
model.eval()

# Define the preprocessing transforms
preprocess = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225]
    )
])

# Define the dictionary to store the feature vectors
features = {}

# Iterate over the images and extract the features
image_dir = 'lfw'
for root, dirs, files in os.walk(image_dir):
    for file in files:
        # Load the image
        image_path = os.path.join(root, file)
        image = Image.open(image_path).convert('RGB')

        # Apply the preprocessing transforms
        input_tensor = preprocess(image)
        input_batch = input_tensor.unsqueeze(0)

        # Extract the features from the penultimate layer
        with torch.no_grad():
            features_tensor = model(input_batch)
            features_vector = torch.squeeze(features_tensor).numpy()

        # Store the feature vector in the dictionary
        features[file] = features_vector