🚀 Initial upload of my app

.gitattributes

@@ -33,3 +33,5 @@ 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
+demo/demo.mp4 filter=lfs diff=lfs merge=lfs -text
+demo/demo.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,29 @@
+# app.py
+
+import streamlit as st
+from PIL import Image
+import torch
+from utils import load_model, predict_image
+from ui import render_ui
+
+# Set device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load model
+@st.cache_resource
+def load():
+    return load_model("./models/model.pth", device)
+
+model = load()
+
+# Render UI and handle prediction
+uploaded_file = render_ui()
+
+if uploaded_file:
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    with st.spinner("Classifying..."):
+        prediction = predict_image(model, image, device)
+
+    st.success(f"🔍 Predicted Class: **{prediction}**")

demo/demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36de6774a567fa088c53675ee9cb72b86ea888df51fcfc13eee3ff0e568dce4d
+size 1390824

models/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d25a97a2a404cde92fdbdcf99e51764875356538a46d1460a087cf0809db65
+size 98577378

ui.py

@@ -0,0 +1,10 @@
+# ui.py
+
+import streamlit as st
+
+def render_ui():
+    st.title("🗑️ Garbage Classifier")
+    st.subheader("Upload an image to classify it into one of 10 garbage types.")
+
+    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+    return uploaded_file

utils.py

@@ -0,0 +1,35 @@
+# utils.py
+
+import torch
+from torchvision import transforms
+from PIL import Image
+
+IMG_SIZE = 224  # Or your desired size
+
+class_names = ['battery', 'biological', 'cardboard', 'clothes', 'glass',
+               'metal', 'paper', 'platic', 'shoes', 'trash']
+
+# Transformation same as your test transform
+test_transform = transforms.Compose([
+    transforms.Resize((IMG_SIZE, IMG_SIZE)),
+    transforms.ToTensor(),
+])
+
+def load_model(weights_path, device):
+
+
+
+    model = torch.load(weights_path, map_location=device, weights_only=False)
+    model.to(device)
+    model.eval()
+    return model
+
+def predict_image(model, image, device):
+    image = image.convert("RGB")
+    input_tensor = test_transform(image).unsqueeze(0).to(device)
+
+    with torch.no_grad():
+        outputs = model(input_tensor)
+        _, predicted = torch.max(outputs, 1)
+        class_index = predicted.item()
+        return class_names[class_index]