deployment_push

.gitattributes

@@ -0,0 +1,4 @@
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

classifier.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7ab0a6e5dcbf38a8c33b960996a55a3b4300b36a018c4545801de3a3c8bde0
+size 18582189

main.py

@@ -0,0 +1,77 @@
+import cv2
+import os
+import mediapipe as mp
+
+# --- Initialize MediaPipe Image Classifier ---
+BaseOptions = mp.tasks.BaseOptions
+ImageClassifier = mp.tasks.vision.ImageClassifier
+ImageClassifierOptions = mp.tasks.vision.ImageClassifierOptions
+VisionRunningMode = mp.tasks.vision.RunningMode
+
+# ✅ Load model
+model_path = "classifier.tflite"
+# model_path = "2.tflite"
+# https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt
+
+options = ImageClassifierOptions(
+    base_options=BaseOptions(model_asset_path=model_path),
+    max_results=3
+)
+classifier = ImageClassifier.create_from_options(options)
+
+# --- Load images from folder ---
+folder = r"C:\Users\R c\PycharmProjects\BG_Remover\images"
+images = [os.path.join(folder, f) for f in os.listdir(folder)
+          if f.lower().endswith(('.png', '.jpg', '.jpeg'))]
+
+if not images:
+    print("❌ No images found in folder.")
+    exit()
+
+index = 0
+
+# --- Main Loop ---
+while True:
+    image_path = images[index]
+    frame = cv2.imread(image_path)
+
+    if frame is None:
+        print(f"⚠️ Skipping unreadable image: {image_path}")
+        index = (index + 1) % len(images)
+        continue
+
+    # ✅ Scale down image (20% of original size)
+    frame = cv2.resize(frame, None, fx=0.5, fy=0.5, interpolation=cv2.INTER_AREA)
+
+    # Convert to RGB for MediaPipe
+    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+    mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=rgb)
+
+    # Classify the image
+    result = classifier.classify(mp_image)
+
+    # --- Get top label and score ---
+    if result.classifications:
+        category = result.classifications[0].categories[0]
+        label = category.category_name
+        score = category.score
+        text = f"{label} ({score:.2f})"
+    else:
+        text = "No classification"
+
+    # Draw label on image
+    cv2.putText(frame, text, (20, 40),
+                cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+
+    cv2.imshow("E-Commerce Image Classification", frame)
+
+    key = cv2.waitKey(0) & 0xFF
+    if key == 27:  # ESC → exit
+        break
+    elif key == 32:  # SPACE → next image
+        index = (index + 1) % len(images)
+
+cv2.destroyAllWindows()
+
+
+# put this as deafult address r"C:\Users\R c\PycharmProjects\BG_Remover\images"

mobilenet_v2_1.0_224.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3bc29e38e90842a852bfed957dbf5e36f2d97a91dd17736b1e5c0aca8d3303
+size 13978596

streamlit_app.py

@@ -0,0 +1,196 @@
+import streamlit as st
+import cv2
+import mediapipe as mp
+import numpy as np
+import os
+from PIL import Image
+
+# -------------------------------
+# MediaPipe Classifier Setup
+# -------------------------------
+BaseOptions = mp.tasks.BaseOptions
+ImageClassifier = mp.tasks.vision.ImageClassifier
+ImageClassifierOptions = mp.tasks.vision.ImageClassifierOptions
+
+model_path = "classifier.tflite"
+options = ImageClassifierOptions(
+    base_options=BaseOptions(model_asset_path=model_path),
+    max_results=5
+)
+classifier = ImageClassifier.create_from_options(options)
+
+# -------------------------------
+# Streamlit UI Setup
+# -------------------------------
+st.set_page_config(page_title="Image Classifier", layout="wide", page_icon="🛒")
+
+# Compact layout fix — title fully visible
+st.markdown(
+    """
+    <style>
+    div.block-container {
+        padding-top: 1.5rem;
+        padding-bottom: 0.5rem;
+        max-width: 100%;
+    }
+    h1, h2, h3, h4, h5 {font-size: 1rem;}
+    img {max-width: 100%; height: auto;}
+    .stSlider {margin-top: 0.2rem;}
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+st.title("E-Commerce Image Classifier")
+st.write(
+    "Try uploading an image or a folder to see automatic classification results. "
+    "You can navigate between images using the arrow buttons below. "
+    "This project is open source — check it out on [GitHub](https://github.com/travelmateen/ImageClassifier). 🚀"
+)
+st.markdown("<style> div[data-testid='stStatusWidget']{display:none}</style>", unsafe_allow_html=True)
+
+# ✅ Sidebar uploader and controls
+with st.sidebar:
+    st.title("User Configuration")
+
+    num_classes = st.number_input(
+        "Number of classes to display",
+        min_value=1,
+        max_value=5,
+        value=3,
+        help="Choose how many classification results to show (1-5)"
+    )
+
+    # Selection mode (Images or Directory)
+    selection_mode = st.radio(
+        "Choose upload type:",
+        ["Directory", "Select Images"],
+        index=0,
+        horizontal=True,
+    )
+
+    st.header("Upload Your Files")
+
+    if selection_mode == "Directory":
+        uploaded_files = st.file_uploader(
+            "Upload images from directory",
+            accept_multiple_files="directory",
+            type=["jpg", "jpeg", "png"],
+        )
+    else:
+        uploaded_files = st.file_uploader(
+            "Select individual images",
+            type=["jpg", "jpeg", "png"],
+            accept_multiple_files=True
+        )
+
+    with st.sidebar.expander("⚠️ Limitations & Tips"):
+        st.write("""
+        **Known Limitations:**
+        - Pre-trained MediaPipe general classifier
+        - 1000 ImageNet categories only
+        - Not customized for specific domains
+        - Max 10MB per image
+
+        **For Best Results:**
+        - Clear, single-subject images
+        - Common objects and scenes
+        - Good lighting and focus
+        - Avoid ambiguous or complex scenes
+        """)
+
+# -------------------------------
+# Default folder handling
+# -------------------------------
+if not uploaded_files:
+    default_folder = "images"
+    if os.path.exists(default_folder):
+        image_files = [
+            os.path.join(default_folder, f)
+            for f in os.listdir(default_folder)
+            if f.lower().endswith((".jpg", ".jpeg", ".png"))
+        ]
+        if image_files:
+            uploaded_files = [open(img, "rb") for img in image_files]
+
+# -------------------------------
+# Classification Logic
+# -------------------------------
+if uploaded_files:
+    total_images = len(uploaded_files)
+
+    if 'foo' not in st.session_state:
+        st.session_state['foo'] = 0
+
+    current_index = st.session_state['foo']
+    # Prevent out-of-range errors
+    if current_index >= len(uploaded_files):
+        current_index = len(uploaded_files) - 1
+        st.session_state['foo'] = current_index
+    elif current_index < 0:
+        current_index = 0
+        st.session_state['foo'] = 0
+
+    current_image = uploaded_files[current_index]
+
+    # --- Read image ---
+    file_bytes = np.asarray(bytearray(current_image.read()), dtype=np.uint8)
+    frame = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+    if frame is None:
+        st.error("⚠️ Unable to read image.")
+        st.stop()
+
+    # --- Fixed smaller image for full window fit ---
+    display_width = 450
+    display_height = 300
+    frame = cv2.resize(frame, (display_width, display_height))
+    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+    # --- Classify image ---
+    mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=rgb)
+    result = classifier.classify(mp_image)
+
+    # --- Layout: image + classification ---
+    col1, col2 = st.columns([1, 1])
+
+    with col1:
+        st.subheader("Original Image")
+        st.image(rgb, width=display_width)
+
+        nav_col1, nav_col2, nav_col3 = st.columns([3, 4, 1], gap="small")
+        with nav_col1:
+            st.markdown("<div style='text-align:left; margin-top:2px;'>", unsafe_allow_html=True)
+            if st.button("⬅️", key="prev") and current_index > 0:
+                st.session_state['foo'] = current_index - 1
+                st.rerun()
+            st.markdown("</div>", unsafe_allow_html=True)
+        with nav_col2:
+            st.caption(f"🖼️ Image {current_index + 1} of {total_images}")
+        with nav_col3:
+            st.markdown("<div style='text-align:right; margin-top:2px;'>", unsafe_allow_html=True)
+            if st.button("➡️", key="next") and current_index < total_images - 1:
+                st.session_state['foo'] = current_index + 1
+                st.rerun()
+            st.markdown("</div>", unsafe_allow_html=True)
+
+    with col2:
+        st.subheader("Classification Results")
+        if result.classifications:
+            categories = result.classifications[0].categories
+            for cat in categories[:num_classes]:
+                st.write(f"**{cat.category_name}** ({cat.score:.2f})")
+                st.progress(float(cat.score))
+        else:
+            st.write("No classification detected.")
+else:
+    st.info("📂 Please upload images using the sidebar to begin classification, or place images in the 'images' folder.")
+
+# -------------------------------
+# Footer
+# -------------------------------
+st.markdown("""
+<hr style="border:0;border-top:1px solid #e6eef8;margin:8px 0 4px 0;">
+<div style='text-align:center;color:#111F68;margin:0;padding:0;'>
+  <p style="margin:0;">Made by <a href='https://techtics.ai' target='_blank' style='color:#042AFF;text-decoration:none;font-weight:700;'>Techtics.ai</a></p>
+</div>
+""", unsafe_allow_html=True)