Add files via upload

annotation_convertion.ipynb

@@ -0,0 +1,143 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "73f058fb-154c-482e-97c7-31475291bdf7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "4f002fe0-7cbb-42ec-9821-bf78e81a60ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "coco_ann_file = \"C:/infosys internship/coco2017_subset/annotation_subset/instances_val2017_subset.json\"\n",
+    "output_dir = \"C:/infosys internship/coco2017_subset/val2017_labels\"\n",
+    "\n",
+    "os.makedirs(output_dir, exist_ok=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f7b471a6-137c-4305-b664-465ca5e350eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load COCO annotations\n",
+    "with open(coco_ann_file, 'r') as f:\n",
+    "    coco_data = json.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "f2165d89-6d9e-4123-9cdc-6b16abc127b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create mapping: COCO category id -> new id (0-based contiguous indices)\n",
+    "# For example, if valid categories are 1, 2, 3, 5, 6, ... then you might have:\n",
+    "coco_categories = sorted([cat['id'] for cat in coco_data['categories']])\n",
+    "id_mapping = {orig_id: new_id for new_id, orig_id in enumerate(coco_categories)}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "8f38b511-f624-4f5f-80a9-8f0308897e41",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Build a mapping from image_id to image info\n",
+    "img_info = {img['id']: img for img in coco_data['images']}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "9ed5f07a-08ee-4573-ae8c-8256bd95c422",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Process annotations per image\n",
+    "annotations_by_image = {}\n",
+    "for ann in coco_data['annotations']:\n",
+    "    img_id = ann['image_id']\n",
+    "    img = img_info[img_id]\n",
+    "    img_width, img_height = img['width'], img['height']\n",
+    "\n",
+    "    x, y, w, h = ann['bbox']\n",
+    "    # Convert COCO bbox [x, y, w, h] to YOLO format [x_center, y_center, width, height] normalized\n",
+    "    x_center = (x + w / 2) / img_width\n",
+    "    y_center = (y + h / 2) / img_height\n",
+    "    norm_w = w / img_width\n",
+    "    norm_h = h / img_height\n",
+    "\n",
+    "    # Remap the category id\n",
+    "    orig_cat = ann['category_id']\n",
+    "    if orig_cat not in id_mapping:\n",
+    "        continue  # skip if the category is not in the mapping\n",
+    "    new_cat = id_mapping[orig_cat]\n",
+    "\n",
+    "    if img_id not in annotations_by_image:\n",
+    "        annotations_by_image[img_id] = []\n",
+    "    annotations_by_image[img_id].append(f\"{new_cat} {x_center:.6f} {y_center:.6f} {norm_w:.6f} {norm_h:.6f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "d420d94a-3e54-4893-a800-28292749d233",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Write YOLO label files for each image\n",
+    "for img_id, ann_list in annotations_by_image.items():\n",
+    "    file_name = img_info[img_id]['file_name']\n",
+    "    base_name = os.path.splitext(file_name)[0]\n",
+    "    # Save the label file in the same directory as your images, or wherever you prefer\n",
+    "    out_file = os.path.join(output_dir, base_name + '.txt')\n",
+    "    with open(out_file, 'w') as f:\n",
+    "        for line in ann_list:\n",
+    "            f.write(line + '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d56b0b41-9890-40fe-8dfa-30b0feda93e3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -0,0 +1,81 @@
+import streamlit as st
+import cv2
+import numpy as np
+import tempfile
+import time
+from ultralytics import YOLO
+
+# Load the YOLO model (adjust the path as needed)
+model = YOLO(r"C:\Users\jerin\yolo11n.pt")
+
+# Sidebar configuration for confidence threshold and mode selection
+confidence_threshold = st.sidebar.slider("Confidence Threshold", 0.0, 1.0, 0.5, 0.05)
+mode = st.sidebar.selectbox("Select Mode", ["Image", "Video", "Webcam"])
+
+st.title("YOLO Object Detection with Streamlit")
+
+if mode == "Image":
+    st.header("Image Detection")
+    uploaded_image = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"])
+    if uploaded_image is not None:
+        # Convert the uploaded image to a NumPy array
+        file_bytes = np.asarray(bytearray(uploaded_image.read()), dtype=np.uint8)
+        image = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+        st.image(image, channels="BGR", caption="Original Image")
+        # Run YOLO detection on the image
+        results = model.predict(source=image, conf=confidence_threshold, show=False)
+        annotated_image = results[0].plot()  # Annotated image with detections
+        st.image(annotated_image, channels="BGR", caption="Detection Result")
+
+elif mode == "Video":
+    st.header("Video Detection")
+    uploaded_video = st.file_uploader("Upload a Video", type=["mp4", "mov", "avi"])
+    if uploaded_video is not None:
+        # Save the uploaded video to a temporary file
+        tfile = tempfile.NamedTemporaryFile(delete=False)
+        tfile.write(uploaded_video.read())
+        cap = cv2.VideoCapture(tfile.name)
+        stframe = st.empty()  # Placeholder to update video frames
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+            # Run YOLO detection on the current frame
+            results = model.predict(source=frame, conf=confidence_threshold, show=False)
+            annotated_frame = results[0].plot()
+            stframe.image(annotated_frame, channels="BGR")
+            time.sleep(0.03)  # Small delay to control frame rate
+        cap.release()
+
+elif mode == "Webcam":
+    st.header("Webcam Live Detection (OpenCV Method)")
+
+    # Initialize webcam run state in session state
+    if "run_webcam" not in st.session_state:
+        st.session_state.run_webcam = False
+
+    # Buttons to start and stop webcam capture
+    start_button = st.button("Start Webcam")
+    stop_button = st.button("Stop Webcam")
+    if start_button:
+        st.session_state.run_webcam = True
+    if stop_button:
+        st.session_state.run_webcam = False
+
+    webcam_placeholder = st.empty()  # Placeholder for webcam frames
+
+    if st.session_state.run_webcam:
+        cap = cv2.VideoCapture(0)  # Open default webcam
+        st.write("Starting webcam...")
+        while st.session_state.run_webcam and cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                st.write("Failed to grab frame")
+                break
+            # Run YOLO detection on the current webcam frame
+            results = model.predict(source=frame, conf=confidence_threshold, show=False)
+            annotated_frame = results[0].plot()
+            webcam_placeholder.image(annotated_frame, channels="BGR")
+            time.sleep(0.03)  # Small delay to control frame rate
+        cap.release()
+        st.write("Webcam stopped.")

classes_train&val.ipynb

@@ -0,0 +1,83 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "21a45fde-b895-4915-982e-bb3751c3539f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of Classes: 80\n",
+      "Class IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79]\n",
+      "Class IDs saved to 'classes.txt'\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Paths to label folders (update if necessary)\n",
+    "train_label_path = r\"C:/infosys internship/coco2017_subset/train2017_labels\"\n",
+    "val_label_path = r\"C:/infosys internship/coco2017_subset/val2017_labels\"\n",
+    "\n",
+    "# Store unique class IDs\n",
+    "unique_classes = set()\n",
+    "\n",
+    "# Function to process label files in a folder\n",
+    "def extract_classes(label_path):\n",
+    "    for file in os.listdir(label_path):\n",
+    "        if file.endswith(\".txt\"):\n",
+    "            with open(os.path.join(label_path, file), \"r\") as f:\n",
+    "                for line in f:\n",
+    "                    class_id = int(line.split()[0])  # Extract class ID\n",
+    "                    unique_classes.add(class_id)\n",
+    "\n",
+    "# Process both train and val folders\n",
+    "extract_classes(train_label_path)\n",
+    "extract_classes(val_label_path)\n",
+    "\n",
+    "# Print results\n",
+    "print(f\"Number of Classes: {len(unique_classes)}\")\n",
+    "print(f\"Class IDs: {sorted(unique_classes)}\")\n",
+    "\n",
+    "# (Optional) Save to a text file\n",
+    "with open(\"classes.txt\", \"w\") as f:\n",
+    "    f.write(\"\\n\".join(map(str, sorted(unique_classes))))\n",
+    "\n",
+    "print(\"Class IDs saved to 'classes.txt'\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d43cb6f-bff8-432a-a4c9-96ebe029c96c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}