Upload 5 files

app (2).py

@@ -0,0 +1,67 @@
+import torch
+import torch.nn as nn
+from torchvision import models, transforms
+from PIL import Image
+import gradio as gr
+import os
+
+# 📦 Class names
+class_names = [
+    "accordion",
+    "banjo",
+    "drum",
+    "flute",
+    "guitar",
+    "harmonica",
+    "saxophone",
+    "sitar",
+    "tabla",
+    "violin"
+]
+
+# 📐 Transformations (same as during training)
+transform = transforms.Compose([
+    transforms.Resize(256),
+    transforms.CenterCrop(224),
+    transforms.ToTensor(),
+    transforms.Normalize([0.485, 0.456, 0.406],
+                         [0.229, 0.224, 0.225])
+])
+
+# 🧠 Load model
+def load_model(model_path="music_model.pth"):
+    model = models.resnet18(weights=None)
+    model.fc = nn.Linear(model.fc.in_features, len(class_names))
+    model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
+    model.eval()
+    return model
+
+model = load_model("music_model.pth")
+
+# 🔍 Prediction function
+def predict(image):
+    image = Image.fromarray(image).convert("RGB")
+    img_tensor = transform(image).unsqueeze(0)
+    with torch.no_grad():
+        outputs = model(img_tensor)
+        _, predicted = torch.max(outputs, 1)
+        prediction = class_names[predicted.item()]
+        confidences = torch.nn.functional.softmax(outputs[0], dim=0)
+        confidences_dict = {class_names[i]: float(confidences[i]) for i in range(len(class_names))}
+    return prediction, confidences_dict
+
+# 🎛️ Gradio Interface
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="numpy", label="Upload Instrument Image"),
+    outputs=[
+        gr.Label(label="Predicted Instrument"),
+        gr.Label(label="Confidence Scores")
+    ],
+    title="🎵 Musical Instrument Classifier",
+    description="Upload an image of a musical instrument and get the predicted class (accordion, guitar, etc.)"
+)
+
+# 🚀 Launch the app
+if __name__ == "__main__":
+    interface.launch()

app.py

@@ -0,0 +1,74 @@
+import torch
+import torch.nn as nn
+from torchvision import models, transforms
+from PIL import Image
+import gradio as gr
+
+# 📦 Class names
+class_names = [
+    "accordion",
+    "banjo",
+    "drum",
+    "flute",
+    "guitar",
+    "harmonica",
+    "saxophone",
+    "sitar",
+    "tabla",
+    "violin"
+]
+
+# 📐 Transformations (same as during training)
+transform = transforms.Compose([
+    transforms.Resize(256),
+    transforms.CenterCrop(224),
+    transforms.ToTensor(),
+    transforms.Normalize([0.485, 0.456, 0.406],
+                         [0.229, 0.224, 0.225])
+])
+
+# 🧠 Load model with enhanced FC head
+def load_model(model_path="music_model.pth"):
+    model = models.resnet18(weights=None)
+
+    # ✨ Enhanced classifier head (512 → 256 → 10)
+    model.fc = nn.Sequential(
+        nn.Linear(model.fc.in_features, 256),
+        nn.ReLU(),
+        nn.Dropout(0.4),
+        nn.Linear(256, 10)
+    )
+
+    model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
+    model.eval()
+    return model
+
+model = load_model("music_model.pth")
+
+# 🔍 Prediction function
+def predict(image):
+    image = Image.fromarray(image).convert("RGB")
+    img_tensor = transform(image).unsqueeze(0)
+    with torch.no_grad():
+        outputs = model(img_tensor)
+        _, predicted = torch.max(outputs, 1)
+        prediction = class_names[predicted.item()]
+        confidences = torch.nn.functional.softmax(outputs[0], dim=0)
+        confidences_dict = {class_names[i]: float(confidences[i]) for i in range(10)}
+    return prediction, confidences_dict
+
+# 🎛️ Gradio Interface
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="numpy", label="Upload Instrument Image"),
+    outputs=[
+        gr.Label(label="Predicted Instrument"),
+        gr.Label(label="Confidence Scores")
+    ],
+    title="🎵 Musical Instrument Classifier",
+    description="Upload an image of a musical instrument and get the predicted class (accordion, guitar, etc.)"
+)
+
+# 🚀 Launch the app
+if __name__ == "__main__":
+    interface.launch()

music_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec98307f0073d0f85cfc07741f70c1669d4e875d188c739264cf74f3fbc20a6c
+size 45321530

music_model2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51d1804a88148ea0acfef630517d68c210a5daeb52ea146a3607d3847f8bf51
+size 44805752

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=4.0.0
+torch>=2.0.0
+torchvision>=0.15.0
+Pillow>=9.0.0