Create App.py

App.py

@@ -0,0 +1,120 @@
+import gradio as gr
+from PIL import Image
+import torch
+import torch.nn as nn
+import torchvision.transforms as transforms
+import torchvision.models as models
+import numpy as np
+
+# Set device
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Load the main classifier (Main_Classifier_best_model.pth)
+main_model = models.resnet18(pretrained=False)
+num_ftrs = main_model.fc.in_features
+main_model.fc = nn.Linear(num_ftrs, 3)  # 3 classes: Soda drinks, Clothing, Mobile Phones
+main_model.load_state_dict(torch.load('Main_Classifier_best_model.pth', map_location=device))
+main_model = main_model.to(device)
+main_model.eval()
+
+# Define class names for the main classifier based on folder structure
+main_class_names = ['Clothing', 'Mobile Phones', 'Soda drinks']
+
+# Sub-classifier models
+def load_soda_drinks_model():
+    model = models.resnet18(pretrained=False)
+    num_ftrs = model.fc.in_features
+    model.fc = nn.Linear(num_ftrs, 3)  # 3 classes: Miranda, Pepsi, Seven Up
+    model.load_state_dict(torch.load('Soda_drinks_best_model.pth', map_location=device))
+    model = model.to(device)
+    model.eval()
+    return model
+
+def load_clothing_model():
+    model = models.resnet18(pretrained=False)
+    num_ftrs = model.fc.in_features
+    model.fc = nn.Linear(num_ftrs, 2)  # 2 classes: Pants, T-Shirt
+    model.load_state_dict(torch.load('Clothes_best_model.pth', map_location=device))
+    model = model.to(device)
+    model.eval()
+    return model
+
+def load_mobile_phones_model():
+    model = models.resnet18(pretrained=False)
+    num_ftrs = model.fc.in_features
+    model.fc = nn.Linear(num_ftrs, 2)  # 2 classes: Apple, Samsung
+    model.load_state_dict(torch.load('Phone_best_model.pth', map_location=device))
+    model = model.to(device)
+    model.eval()
+    return model
+
+def convert_to_rgb(image):
+    """
+    Converts 'P' mode images with transparency to 'RGBA', and then to 'RGB'.
+    This is to avoid transparency issues during model training.
+    """
+    if image.mode in ('P', 'RGBA'):
+        return image.convert('RGB')
+    return image
+
+# Define preprocessing transformations (same used during training)
+preprocess = transforms.Compose([
+    transforms.Lambda(convert_to_rgb),
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  # ImageNet normalization
+])
+
+def classify_image(image):
+    # Open the image using PIL
+    image = Image.fromarray(image)
+
+    # Preprocess the image
+    input_image = preprocess(image).unsqueeze(0).to(device)
+
+    # Perform inference with the main classifier
+    with torch.no_grad():
+        output = main_model(input_image)
+        probabilities = torch.nn.functional.softmax(output[0], dim=0)
+        confidence, predicted_class = torch.max(probabilities, 0)
+
+    # Main classifier result
+    main_prediction = main_class_names[predicted_class]
+    main_confidence = confidence.item()
+
+    # Load and apply the sub-classifier based on the main classification
+    if main_prediction == 'Soda drinks':
+        soda_model = load_soda_drinks_model()
+        sub_class_names = ['Miranda', 'Pepsi', 'Seven Up']
+        with torch.no_grad():
+            sub_output = soda_model(input_image)
+    elif main_prediction == 'Clothing':
+        clothing_model = load_clothing_model()
+        sub_class_names = ['Pants', 'T-Shirt']
+        with torch.no_grad():
+            sub_output = clothing_model(input_image)
+    elif main_prediction == 'Mobile Phones':
+        phones_model = load_mobile_phones_model()
+        sub_class_names = ['Apple', 'Samsung']
+        with torch.no_grad():
+            sub_output = phones_model(input_image)
+
+    # Perform inference with the sub-classifier
+    sub_probabilities = torch.nn.functional.softmax(sub_output[0], dim=0)
+    sub_confidence, sub_predicted_class = torch.max(sub_probabilities, 0)
+
+    sub_prediction = sub_class_names[sub_predicted_class]
+    sub_confidence = sub_confidence.item()
+
+    return f"Main Predicted Class: {main_prediction} (Confidence: {main_confidence:.4f})", \
+           f"Sub Predicted Class: {sub_prediction} (Confidence: {sub_confidence:.4f})"
+
+
+# Gradio interface
+image_input = gr.inputs.Image(shape=(224, 224), image_mode="RGB")
+output_text = gr.outputs.Textbox()
+
+gr.Interface(fn=classify_image, inputs=image_input, outputs=output_text, 
+             title="Main and Sub-Classifier System",
+             description="Upload an image to classify whether it belongs to Clothing, Mobile Phones, or Soda Drinks. Based on the prediction, it will further classify within the subcategory.",
+             theme="default").launch()