Add files via upload

.gitignore

@@ -160,3 +160,4 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+model.pt

README.md

@@ -1 +1,25 @@
-# cat-dog-hug-exp
+---
+title: Demo
+emoji: 🌖
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 3.0.6
+app_file: app.py
+pinned: false
+license: cc
+---
+
+
+[![Sync to Hugging Face hub](https://github.com/nogibjj/hugging-face/actions/workflows/main.yml/badge.svg)](https://github.com/nogibjj/hugging-face/actions/workflows/main.yml)
+
+
+[Try Demo Text Summarization Here](https://huggingface.co/spaces/noahgift/demo)
+
+
+![mlops-hugging-face](https://user-images.githubusercontent.com/58792/170845235-7f00d61c-ea36-4d28-82d0-3a9b8c0f1769.png)
+
+
+## References
+
+[Watch YouTube Walkthrough](https://youtu.be/VYSGjUa5sc4)

app.py

@@ -0,0 +1,68 @@
+import gradio as gr
+import torch
+import torchvision.transforms as transforms
+from PIL import Image
+import os
+
+class CatDogClassifier:
+    def __init__(self, model_path="model.pt"):
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        
+        # Load the traced model
+        self.model = torch.jit.load(model_path)
+        self.model = self.model.to(self.device)
+        self.model.eval()
+
+        # Define the same transforms used during training/testing
+        self.transform = transforms.Compose([
+            transforms.Resize((160, 160)),
+            transforms.ToTensor(),
+            transforms.Normalize(
+                mean=[0.485, 0.456, 0.406],
+                std=[0.229, 0.224, 0.225]
+            )
+        ])
+
+        # Class labels
+        self.labels = ['Dog', 'Cat']
+
+    @torch.no_grad()
+    def predict(self, image):
+        if image is None:
+            return None
+        
+        # Convert to PIL Image if needed
+        if not isinstance(image, Image.Image):
+            image = Image.fromarray(image).convert('RGB')
+        
+        # Preprocess image
+        img_tensor = self.transform(image).unsqueeze(0).to(self.device)
+        
+        # Get prediction
+        output = self.model(img_tensor)
+        probabilities = torch.nn.functional.softmax(output[0], dim=0)
+        
+        # Create prediction dictionary
+        return {
+            self.labels[idx]: float(prob)
+            for idx, prob in enumerate(probabilities)
+        }
+
+# Create classifier instance
+classifier = CatDogClassifier()
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=classifier.predict,
+    inputs=gr.Image(),
+    outputs=gr.Label(num_top_classes=2),
+    title="Cat vs Dog Classifier",
+    description="Upload an image to classify whether it's a cat or a dog",
+    examples=[
+        ["examples/cat.jpg"],
+        ["examples/dog.jpg"]
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch() 

requirements.txt

@@ -0,0 +1,3 @@
+torch
+gradio
+torchvision