Update New_file.txt

New_file.txt

@@ -1,14 +1,15 @@
 import torch
-from transformers import SwinTransformer, SwinTransformerTokenizer
 import torchvision.transforms as transforms
 from PIL import Image
 import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
+from torchvision.models import resnet50
+from torchvision.datasets import ImageFolder
+from torch.utils.data import DataLoader
 
-# Load the pre-trained Swin Transformer model and tokenizer
-model_name = "microsoft/Swin-Transformer-base-patch4-in22k"
-model = SwinTransformer.from_pretrained(model_name)
-tokenizer = SwinTransformerTokenizer.from_pretrained(model_name)
+# Load a pre-trained ResNet-50 model
+model = resnet50(pretrained=True)
+model.eval()
 
 # Define a function to preprocess images
 def preprocess_image(image_path):
@@ -22,29 +23,27 @@ def preprocess_image(image_path):
     return image
 
 # Load your ideal subset of images
-ideal_image_paths = ["ideal_image1.jpg", "ideal_image2.jpg", "ideal_image3.jpg"]  # Replace with your ideal image file paths
+ideal_image_paths = ["/content/trunck.jpg", "t4.jpg"]  # Replace with your ideal image file paths
 ideal_embeddings = []
 
 for image_path in ideal_image_paths:
     image = preprocess_image(image_path)
     with torch.no_grad():
-        input_ids = tokenizer(image_path, return_tensors="pt").input_ids
-        embedding = model.pixel_values(input_ids).numpy()
+        embedding = model(image).squeeze().numpy()
         ideal_embeddings.append(embedding)
 
 # Load a set of candidate images
-candidate_image_paths = ["candidate_image1.jpg", "candidate_image2.jpg", "candidate_image3.jpg"]  # Replace with your candidate image file paths
+candidate_image_paths = ["/content/trunck2.jpg", "t3.jpg", "car.jpg",]  # Replace with your candidate image file paths
 candidate_embeddings = []
 
 for image_path in candidate_image_paths:
     image = preprocess_image(image_path)
     with torch.no_grad():
-        input_ids = tokenizer(image_path, return_tensors="pt").input_ids
-        embedding = model.pixel_values(input_ids).numpy()
+        embedding = model(image).squeeze().numpy()
         candidate_embeddings.append(embedding)
 
 # Calculate similarities between ideal and candidate images using cosine similarity
 similarities = cosine_similarity(ideal_embeddings, candidate_embeddings)
 
 # Print the similarity matrix
-print(similarities)
+print(similarities)