changes done

app.py

@@ -1,66 +1,66 @@
-### 1. Imports and class names setup ### 
+### 1. Imports and class names setup ###
 import gradio as gr
 import os
 import torch
+import numpy as np
+from PIL import Image
 
 from model import create_vit_model
 from timeit import default_timer as timer
 from typing import Tuple, Dict
+
+# List of 121 food classes
 class_names = ["apple_pie", "baby_back_ribs", "baklava", "beef_carpaccio", "beef_tartare", "beet_salad", "beignets", "bibimbap", "biryani", "bread_pudding", "breakfast_burrito", "bruschetta", "caesar_salad", "cannoli", "caprese_salad", "carrot_cake", "ceviche", "chai", "chapati", "cheese_plate", "cheesecake", "chicken_curry", "chicken_quesadilla", "chicken_wings", "chocolate_cake", "chocolate_mousse", "chole_bhature", "churros", "clam_chowder", "club_sandwich", "crab_cakes", "creme_brulee", "croque_madame", "cup_cakes", "dabeli", "dal", "deviled_eggs", "dhokla", "donuts", "dosa", "dumplings", "edamame", "eggs_benedict", "escargots", "falafel", "filet_mignon", "fish_and_chips", "foie_gras", "french_fries", "french_onion_soup", "french_toast", "fried_calamari", "fried_rice", "frozen_yogurt", "garlic_bread", "gnocchi", "greek_salad", "grilled_cheese_sandwich", "grilled_salmon", "guacamole", "gyoza", "hamburger", "hot_and_sour_soup", "hot_dog", "huevos_rancheros", "hummus", "ice_cream", "idli", "jalebi", "kathi_rolls", "kofta", "kulfi", "lasagna", "lobster_bisque", "lobster_roll_sandwich", "macaroni_and_cheese", "macarons", "miso_soup", "momos", "mussels", "naan", "nachos", "omelette", "onion_rings", "oysters", "pad_thai", "paella", "pakoda", "pancakes", "pani_puri", "panna_cotta", "panner_butter_masala", "pav_bhaji", "peking_duck", "pho", "pizza", "pork_chop", "poutine", "prime_rib", "pulled_pork_sandwich", "ramen", "ravioli", "red_velvet_cake", "risotto", "samosa", "sashimi", "scallops", "seaweed_salad", "shrimp_and_grits", "spaghetti_bolognese", "spaghetti_carbonara", "spring_rolls", "steak", "strawberry_shortcake", "sushi", "tacos", "takoyaki", "tiramisu", "tuna_tartare", "vadapav", "waffles"]
-vit, vit_transforms = create_vit_model(
-    num_classes=121, # len(class_names) would also work
-)
-vit.load_state_dict(
-    torch.load(
-        f="vit_epoch_2.pth",
-        map_location=torch.device("cpu"),  # load to CPU
-    )
-)
-# Create predict function
+
+# Load model and transforms
+vit, vit_transforms = create_vit_model(num_classes=121)
+vit.load_state_dict(torch.load("vit_epoch_2.pth", map_location=torch.device("cpu")))
+
+# Predict function
 def predict(img) -> Tuple[Dict, float]:
-    """Transforms and performs a prediction on img and returns prediction and time taken.
-    """
+    """Transforms and performs a prediction on img and returns prediction and time taken."""
+    # Ensure image is PIL
+    if isinstance(img, np.ndarray):
+        img = Image.fromarray(img)
+
     # Start the timer
     start_time = timer()
-    
-    # Transform the target image and add a batch dimension
-    img = vit_transforms(img).unsqueeze(0)
-    
-    # Put model into evaluation mode and turn on inference mode
+
+    # Transform and predict
+    img = vit_transforms(img).unsqueeze(0)  # Add batch dimension
     vit.eval()
     with torch.inference_mode():
-        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
         pred_probs = torch.softmax(vit(img), dim=1)
-    
-    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
+
+    # Get label:probability dictionary
     pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
-    
-    # Calculate the prediction time
     pred_time = round(timer() - start_time, 5)
-    
-    # Return the prediction dictionary and prediction time 
+
     return pred_labels_and_probs, pred_time
 
 ### 4. Gradio app ###
 
-# Create title, description and article strings
+# App metadata
 title = "VisionBite 🍕🥩🍣"
 description = "A Vision Transformer (ViT-Base-16) model trained to classify images of food into 121 distinct categories. The model uses a transformer-based architecture to extract visual features and achieve accurate classification across diverse food items."
-article = "Model has been trained on Food121 dataset (https://huggingface.co/datasets/ItsNotRohit/Food121) and has an accuracy of 95% on top 5 predictions."
+article = "Model has been trained on the [Food121 dataset](https://huggingface.co/datasets/ItsNotRohit/Food121) and achieves ~95% Top-5 accuracy."
 
 # Create examples list from "examples/" directory
-example_list = [["examples/" + example] for example in os.listdir("examples")]
+example_list = [["examples/" + example] for example in os.listdir("examples") if example.lower().endswith(('.jpg', '.jpeg', '.png'))]
 
-# Create the Gradio demo
-demo = gr.Interface(fn=predict, # mapping function from input to output
-                    inputs=gr.Image(type="pil"), # what are the inputs?
-                    outputs=[gr.Label(num_top_classes=121, label="Predictions"), # what are the outputs?
-                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
-                    # Create examples list from "examples/" directory
-                    examples=example_list, 
-                    title=title,
-                    description=description,
-                    article=article)
+# Gradio demo
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Label(num_top_classes=5, label="Top-5 Predictions"),
+        gr.Number(label="Prediction time (s)")
+    ],
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article
+)
 
-# Launch the demo!
+# Launch app
 demo.launch()