Upload 9 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/img3.jpg filter=lfs diff=lfs merge=lfs -text
+examples/Screenshot[[:space:]]2025-03-14[[:space:]]at[[:space:]]5.29.03 PM.png filter=lfs diff=lfs merge=lfs -text
+examples/Screenshot[[:space:]]2025-03-14[[:space:]]at[[:space:]]5.29.32 PM.png filter=lfs diff=lfs merge=lfs -text

App.py

@@ -0,0 +1,110 @@
+import os
+import gradio as gr
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchvision.transforms as transforms
+from PIL import Image
+from ResNet_for_CC import CC_model  # Import fixed model
+
+# Set device (CPU/GPU)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load the trained CC_model
+model_path = "CC_net.pt"
+model = CC_model(num_classes=14)  
+
+# Load model weights
+state_dict = torch.load(model_path, map_location=device)
+model.load_state_dict(state_dict, strict=False) 
+model.to(device)
+model.eval()
+
+# Clothing1M Class Labels
+class_labels = [
+    "T-Shirt", "Shirt", "Knitwear", "Chiffon", "Sweater", "Hoodie",
+    "Windbreaker", "Jacket", "Downcoat", "Suit", "Shawl", "Dress",
+    "Vest", "Underwear"
+]
+
+# Define image transformations
+transform = transforms.Compose([
+    transforms.Resize(256),
+    transforms.CenterCrop(224),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+])
+
+# 🔹 **Dynamically Fetch All Example Images (Including .webp)**
+def get_example_images():
+    examples_dir = "examples"
+    if not os.path.exists(examples_dir):
+        print("[WARNING] 'examples/' directory does not exist.")
+        return []
+    
+    # Fetch all image files (including .webp)
+    image_files = sorted([
+        os.path.join(examples_dir, f) for f in os.listdir(examples_dir)
+        if f.lower().endswith((".png", ".jpg", ".jpeg", ".webp"))
+    ])
+    
+    if not image_files:
+        print("[WARNING] No images found in 'examples/' directory.")
+    
+    print(f"[INFO] Found {len(image_files)} images in 'examples/'")
+    return image_files
+
+# 🔹 **Classification Function**
+def classify_image(image):
+    print("\n[DEBUG] Received image for classification.")
+
+    try:
+        image = transform(image).unsqueeze(0).to(device)
+        print("[DEBUG] Image transformed and moved to device.")
+
+        with torch.no_grad():
+            output = model(image)  
+            print(f"[DEBUG] Model output shape: {output.shape}")  
+            print(f"[DEBUG] Model output values: {output}")
+
+            if output.shape[1] != 14:
+                return f"[ERROR] Model output mismatch! Expected 14 but got {output.shape[1]}."
+
+            # Convert logits to probabilities
+            probabilities = F.softmax(output, dim=1)
+            print(f"[DEBUG] Softmax probabilities: {probabilities}")
+
+            # Print class predictions and probabilities
+            for i, prob in enumerate(probabilities[0].tolist()):
+                print(f"[INFO] {class_labels[i]}: {prob * 100:.2f}%")
+
+            # Get predicted class index
+            predicted_class = torch.argmax(probabilities, dim=1).item()
+            print(f"[DEBUG] Predicted class index: {predicted_class} (Class: {class_labels[predicted_class]})")
+
+            # Validate prediction
+            if 0 <= predicted_class < len(class_labels):
+                predicted_label = class_labels[predicted_class]
+                confidence = probabilities[0][predicted_class].item() * 100
+                return f"Predicted Class: {predicted_label} (Confidence: {confidence:.2f}%)"
+            else:
+                return "[ERROR] Model returned an invalid class index."
+
+    except Exception as e:
+        print(f"[ERROR] Exception during classification: {e}")
+        return "Error in classification. Check console for details."
+
+# 🔹 **Create Gradio Interface with Dynamic Examples**
+interface = gr.Interface(
+    fn=classify_image, 
+    inputs=gr.Image(type="pil"), 
+    outputs="text",
+    title="Clothing1M Image Classifier",
+    description="Upload a clothing image, or select an example below to classify it.",
+    examples=get_example_images()  # Dynamically load all images including .webp
+)
+
+# Run the Interface
+if __name__ == "__main__":
+    print("[INFO] Launching Gradio interface...")
+    interface.launch()

CC_net.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61ad39bb8f2872cff371265b3ad4ecbf9c5a201d64225f92d6bcc937d9e112b
+size 95648689

ResNet_for_CC.py

@@ -0,0 +1,47 @@
+import torch
+import torch.nn as nn
+import torchvision.models as models
+
+
+class ResClassifier(nn.Module):
+    def __init__(self, class_num=14):
+        super(ResClassifier, self).__init__()
+        self.fc1 = nn.Sequential(
+            nn.Linear(128, 64),
+            nn.BatchNorm1d(64, affine=True),
+            nn.ReLU(inplace=True),
+            nn.Dropout()
+        )
+        self.fc2 = nn.Sequential(
+            nn.Linear(64, 64),
+            nn.BatchNorm1d(64, affine=True),
+            nn.ReLU(inplace=True),
+            nn.Dropout()
+        )
+        self.fc3 = nn.Linear(64, class_num)
+
+    def forward(self, x):
+        fc1_emb = self.fc1(x)
+        fc2_emb = self.fc2(fc1_emb)
+        logit = self.fc3(fc2_emb)
+        return logit
+
+
+class CC_model(nn.Module):
+    def __init__(self, num_classes=14):
+        super(CC_model, self).__init__()
+        self.num_classes = num_classes
+        self.model_resnet = models.resnet50(weights='ResNet50_Weights.DEFAULT')
+
+        # Modify final layers
+        num_ftrs = self.model_resnet.fc.in_features
+        self.model_resnet.fc = nn.Identity()  # Remove ResNet's default final layer
+        self.classification_fc = nn.Linear(num_ftrs, num_classes)  
+        self.dr = nn.Linear(num_ftrs, 128)  # Feature reduction (for embeddings)
+        self.fc1 = ResClassifier(num_classes)
+        self.fc2 = ResClassifier(num_classes)
+
+    def forward(self, x):
+        feature = self.model_resnet(x)
+        class_logits = self.classification_fc(feature)  # Correct classification output
+        return class_logits  # Ensure output shape is [batch_size, 14]

requirements.txt

@@ -0,0 +1,7 @@
+clip==0.2.0
+numpy==1.23.4
+openai_clip==1.0.1
+Pillow==9.4.0
+torch==2.6.0
+torchvision==0.21.0
+tqdm==4.64.1