Update README.md

README.md

@@ -68,12 +68,24 @@ You can use this model with the `transformers` and `torch` libraries.
 
 ```python
 import torch
+from huggingface_hub import hf_hub_download
 from torchvision import transforms
 from PIL import Image
 import requests
 
-# Load the model from Hugging Face Hub
-model = torch.hub.load('huggingface/pytorch', 'resnet18_pneumonia_classifier')
+# Download the model weights from Hugging Face Hub
+model_path = hf_hub_download(repo_id="izeeek/resnet18_pneumonia_classifier", filename="resnet18_pneumonia_classifier.pth")
+
+# Load the model architecture (ResNet18)
+model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet18', pretrained=False)
+
+# Adjust the final layer for binary classification (if necessary)
+model.fc = torch.nn.Linear(model.fc.in_features, 2)
+
+# Load the downloaded weights
+model.load_state_dict(torch.load(model_path))
+
+# Set the model to evaluation mode
 model.eval()
 
 # Image preprocessing
@@ -84,7 +96,7 @@ transform = transforms.Compose([
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
 ])
 
-# Sample Image (replace with your own image)
+# Sample Image (replace with your own image URL)
 url = 'https://storage.googleapis.com/kagglesdsdata/datasets/17810/23812/chest_xray/test/NORMAL/IM-0005-0001.jpeg?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=databundle-worker-v2%40kaggle-161607.iam.gserviceaccount.com%2F20240913%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240913T014624Z&X-Goog-Expires=345600&X-Goog-SignedHeaders=host&X-Goog-Signature=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'
 img = Image.open(requests.get(url, stream=True).raw)
 
@@ -95,6 +107,7 @@ input_img = transform(img).unsqueeze(0)
 with torch.no_grad():
     output = model(input_img)
     _, predicted = torch.max(output, 1)
-    
+
+# Labels for classification
 labels = {0: 'Pneumonia', 1: 'Normal'}
-print(f'Predicted label: {labels[predicted.item()]}')
+print(f'Predicted label: {labels[predicted.item()]}')