Upload 24 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+imgs/webcam_input_demo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,99 @@
----
-title: Yolov8 Object Detection V1.0
-emoji: 🐠
-colorFrom: blue
-colorTo: pink
-sdk: streamlit
-sdk_version: 1.28.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+<div align="center">
+
+# YOLOv8_Object_detection_v1.0_app
+
+  <p>
+    <a align="center" target="_blank">
+      <img width="50%" src="pic_bed/Images_Object_detection_V1.png"></a><br>
+     <a align="center" href="https://ultralytics.com/yolov8" target="_blank">
+      <img width="50%" src="pic_bed/banner-yolov8.png"></a>
+  </p>
+
+<br>
+
+<div>
+   <a href="https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml"><img src="https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml/badge.svg" alt="Ultralytics CI"></a>
+    <a href="https://colab.research.google.com/drive/1shMJ1F6XbzQOBSlxvoEbnkgoJPngVLvs?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+  </div>
+  <br>
+</div>
+
+## Введение / Introduction
+### RUS: 
+- Этот репозиторий предоставляет удобный интерактивный интерфейс для [YOLOv8](https://github.com/ultralytics/ultralytics), и этот интерфейс создан на базе [Streamlit](https://github.com/streamlit/streamlit).<br>
+- В таблицу ниже, помимо стандартных моделей, включены модели, обученные на основе датасетов с [Roboflow](https://universe.roboflow.com/):
+  - Определение автомобильных номеров - [Car plate detection Computer Vision Project](https://universe.roboflow.com/plate-detection-8sa0a/car-plate-detection-vbivf) 
+  - Определение транспортных средств при разном времени суток и погодных условиях - [Smart city cars detection Computer Vision Project](https://universe.roboflow.com/simone-bernabe/smart-city-cars-detection)
+### ENG:
+- This repository supply a user-friendly interactive interface for [YOLOv8](https://github.com/ultralytics/ultralytics) and the interface is powered by [Streamlit](https://github.com/streamlit/streamlit)
+- The table below, in addition to standard models, includes models trained based on datasets from [Roboflow](https://universe.roboflow.com/):
+  - Determination of license plates - [Car plate detection Computer Vision Project](https://universe.roboflow.com/plate-detection-8sa0a/car-plate-detection-vbivf)
+  - Identification vehicles under different times of day and weather conditions - [Smart city cars detection Computer Vision Project](https://universe.roboflow.com/simone-bernabe/smart-city-cars-detection)
+
+## Функции / Features
+### RUS:
+- Доступные типы задачи: Обнаружение транспорта, обнаружение гос.номера автомобиля, сегментация, обнаружения объектов
+- Доступные модели обнаружения/сегментации: `DetlicPl_s` `DetlicPl_l` `Veh_Det` `yolov8n`, `yolov8s`, `yolov8m`, `yolov8l`, `yolov8x` `yolov8n-seg`, `yolov8s-seg`, `yolov8m-seg`, `yolov8l-seg`, `yolov8x-seg`
+- Несколько входных форматов: `Изображение`, `Видео`, `Вебкамера`
+### ENG:
+- Available task types: Vehicle detection, license plate detection, segmentation, object detection.
+- Available detection/segmentation models: `DetlicPl_s` `DetlicPl_l` `Veh_Det` `yolov8n`, `yolov8s`, `yolov8m`, `yolov8l`, `yolov8x` `yolov8n-seg`, `yolov8s-seg`, `yolov8m-seg`, `yolov8l-seg`, `yolov8x-seg`
+- Multiple input formats: Multiple input formats. `Image`, `Video`, `Webcam`
+
+## Интерактивный интерфейс / Interactive Interface
+### Интерфейс ввода изображения / Image Input Interface
+![image_input_demo](https://github.com/yaroslavski88/Yolov8_Object_detection_v1.0_app/blob/main/imgs/image_input_demo.png)<br>
+![image_input_demo](https://github.com/yaroslavski88/Yolov8_Object_detection_v1.0_app/blob/main/imgs/image_input_demo_1.png)
+
+### Интерфейс ввода видео / Video Input Interface
+![video_input_demo](https://github.com/yaroslavski88/Yolov8_Object_detection_v1.0_app/blob/main/imgs/video_input_demo.png)
+
+### Интерфейс ввода веб-камеры / Webcam Input Interface
+![webcam_input_demo](https://github.com/yaroslavski88/Yolov8_Object_detection_v1.0_app/blob/main/imgs/webcam_input_demo.png)
+
+## Установка / Installation
+### Скачать и распаковать репозиторий / Download and unzip repository
+```commandline
+https://github.com/yaroslavski88/Yolov8_Object_detection_v1.0_app
+```
+### Открыть Терминал/ Open Terminal
+```commandline
+https://github.com/yaroslavski88/Yolov8_Object_detection_v1.0_app
+### Установить пакеты / Install packages
+```commandline
+# yolov8 dependencies
+pip install ultralytics
+
+# Streamlit dependencies
+pip install streamlit
+```
+### Загрузите предварительно обученные веса обнаружения YOLOv8 / Download Pre-trained YOLOv8 Detection Weights
+- RUS: Создайте каталог с именем `weights`, создайте подкаталог с именем `detection` и сохраните загруженные веса обнаружения объектов YOLOv8 внутри этого каталога. Файлы весов можно скачать из таблиц ниже.<br>
+- ENG: Create a directory named `weights` and create a subdirectory named `detection` and save the downloaded YOLOv8 object detection weights inside this directory. The weight files can be downloaded from the tables below.
+
+| Обнаружение транспорта, обнаружение гос.номера автомобиля / Vehicle detection, license plate detection models|
+| ------------------------------------------------------------------------------------------------------------ |
+| [DetlicPl_s](https://drive.google.com/drive/folders/1rxSLLwHc9jeHqOM5EAUcq3JxwpczEm5Z?usp=sharing) |
+| [DetlicPl_l](https://drive.google.com/drive/folders/1rxSLLwHc9jeHqOM5EAUcq3JxwpczEm5Z?usp=sharing) |
+| [Veh_Det](https://drive.google.com/drive/folders/1rxSLLwHc9jeHqOM5EAUcq3JxwpczEm5Z?usp=sharing) |
+| Модели Yolov8 (Обнаружение) / Models Yolov8 (Detection)                                  |
+| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) |
+| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) |
+| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) |
+| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) |
+| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) |
+| Модели Yolov8 (Сегментация) / Models Yolov8 (Segmentation)                                  |
+| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) |
+| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) |
+| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) |
+| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) |
+| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) |
+
+## Запуск / Run
+```commandline
+streamlit run app.py
+```
+- RUS: Затем запустится сервер Streamlit и автоматически откроется в веб-браузере страница Streamlit по умолчанию.<br>
+- ENG: Then will start the Streamlit server and open your web browser to the default Streamlit page automatically.
+

app.py

@@ -0,0 +1,81 @@
+from pathlib import Path
+from PIL import Image
+import streamlit as st
+
+import config
+from utils import load_model, infer_uploaded_image, infer_uploaded_video, infer_uploaded_webcam
+
+st.set_page_config(
+    page_title="Интерактивный интерфейс для YOLOv8",
+    page_icon="🤖",
+    layout="wide",
+    initial_sidebar_state="expanded"
+    )
+
+# заголовок главной страницы
+st.title("Интерактивный интерфейс для YOLOv8")
+
+st.sidebar.header("Настройка модели DL")
+
+# опции модели
+task_type = st.sidebar.selectbox(
+    "Выберите задачу",
+    config.DETECTION_TASK_LIST
+)
+
+
+model_type = None
+if task_type == "Обнаружение транспорта":
+    model_type = st.sidebar.selectbox(
+        "Выберите модель",
+        config.DETECTION_MODEL_CAR_LIST
+    )
+elif task_type == "Обнаружение гос.номера автомобиля":
+      model_type = st.sidebar.selectbox(
+        "Выберите модель",
+        config.DETECTION_MODEL_GN_LIST
+      )
+elif task_type == "Сегментация":
+      model_type = st.sidebar.selectbox(
+        "Выберите модель",
+        config.DETECTION_MODEL_SEG_LIST
+      )
+elif task_type == "Обнаружение объектов":
+      model_type = st.sidebar.selectbox(
+        "Выберите модель",
+        config.DETECTION_MODEL_OTHER_LIST
+      )
+else:
+    st.error("Другие функции пока не реализованы")
+
+confidence = float(st.sidebar.slider(
+    "Выберите уверенность модели", 1, 100, 50)) / 100
+
+model_path = ""
+if model_type:
+    model_path = Path(config.DETECTION_MODEL_DIR, str(model_type))
+else:
+    st.error("Пожалуйста, выберите модель на боковой панели")
+
+# загрузка обученной модели
+try:
+    model = load_model(model_path)
+except Exception as e:
+    st.error(f"Не удалось загрузить модель. Пожалуйста, проверьте указанный путь: {model_path}")
+
+# Настройка изображения/видео
+st.sidebar.header("Настройка изображения/видео")
+source_selectbox = st.sidebar.selectbox(
+    "Выберите источник",
+    config.SOURCES_LIST
+)
+
+source_img = None
+if source_selectbox == config.SOURCES_LIST[0]: # Image
+    infer_uploaded_image(confidence, model)
+elif source_selectbox == config.SOURCES_LIST[1]: # Video
+    infer_uploaded_video(confidence, model)
+elif source_selectbox == config.SOURCES_LIST[2]: # Webcam
+    infer_uploaded_webcam(confidence, model)
+else:
+    st.error("Выберите источник.")

config.py

@@ -0,0 +1,57 @@
+from pathlib import Path
+import sys
+
+file_path = Path(__file__).resolve()
+
+root_path = file_path.parent
+
+if root_path not in sys.path:
+    sys.path.append(str(root_path))
+
+ROOT = root_path.relative_to(Path.cwd())
+
+
+SOURCES_LIST = ["Изображение", "Видео", "Вебкамера"]
+
+DETECTION_MODEL_DIR = ROOT / 'weights' / 'detection'
+DetLicPL_s = DETECTION_MODEL_DIR / "DetLicPL_s.pt"
+DetLicPL_l = DETECTION_MODEL_DIR / "DetLicPL_l.pt"
+VehDet = DETECTION_MODEL_DIR / "VehDet.pt"
+YOLOv8n = DETECTION_MODEL_DIR / "yolov8n.pt"
+YOLOv8s = DETECTION_MODEL_DIR / "yolov8s.pt"
+YOLOv8m = DETECTION_MODEL_DIR / "yolov8m.pt"
+YOLOv8l = DETECTION_MODEL_DIR / "yolov8l.pt"
+YOLOv8x = DETECTION_MODEL_DIR / "yolov8x.pt"
+YOLOv8n_seg = DETECTION_MODEL_DIR / "yolov8n-seg.pt"
+YOLOv8s_seg = DETECTION_MODEL_DIR / "yolov8s-seg.pt"
+YOLOv8m_seg = DETECTION_MODEL_DIR / "yolov8m-seg.pt"
+YOLOv8l_seg = DETECTION_MODEL_DIR / "yolov8l-seg.pt"
+YOLOv8x_seg = DETECTION_MODEL_DIR / "yolov8x-seg.pt"
+
+DETECTION_MODEL_CAR_LIST = [
+    "VehDet.pt"]
+
+DETECTION_MODEL_GN_LIST = [
+    "DetLicPL_s.pt",
+    "DetLicPL_l.pt"]
+
+DETECTION_MODEL_SEG_LIST = [
+    "yolov8n-seg.pt",
+    "yolov8s-seg.pt",
+    "yolov8m-seg.pt",
+    "yolov8l-seg.pt",
+    "yolov8x-seg.pt"]
+
+DETECTION_MODEL_OTHER_LIST = [
+    "yolov8n.pt",
+    "yolov8s.pt",
+    "yolov8m.pt",
+    "yolov8l.pt",
+    "yolov8x.pt"]
+
+DETECTION_TASK_LIST = [
+    "Обнаружение транспорта",
+    "Обнаружение гос.номера автомобиля",
+    "Сегментация",
+    "Обнаружение объектов"]
+

requirements.txt

@@ -0,0 +1,6 @@
+streamlit==1.28.0
+ultralytics==8.0.202
+
+opencv-python==4.8.1.78
+# opencv-python-headless==4.8.1.78
+Pillow==10.1.0

utils.py

@@ -0,0 +1,116 @@
+from ultralytics import YOLO
+import streamlit as st
+import cv2
+from PIL import Image
+import tempfile
+
+def _display_detected_frames(conf, model, st_frame, image):
+ 
+    res = model.predict(image, conf=conf)
+
+    res_plotted = res[0].plot()
+    st_frame.image(res_plotted,
+                   caption='Detected Video',
+                   channels="BGR",
+                   use_column_width=True
+                   )
+
+@st.cache_resource
+def load_model(model_path):
+    model = YOLO(model_path)
+    return model
+
+
+def infer_uploaded_image(conf, model):
+    source_img = st.sidebar.file_uploader(
+        label="Выберите изображение...",
+        type=("jpg", "jpeg", "png", 'bmp', 'webp')
+    )
+
+    col1, col2 = st.columns(2)
+
+    with col1:
+        if source_img:
+            uploaded_image = Image.open(source_img)
+            st.image(
+                image=source_img,
+                caption="Загруженное изображение",
+                use_column_width=True
+            )
+
+    if source_img:
+        if st.button("Старт"):
+            with st.spinner("Запускается..."):
+                res = model.predict(uploaded_image,
+                                    conf=conf)
+                boxes = res[0].boxes
+                res_plotted = res[0].plot()[:, :, ::-1]
+
+                with col2:
+                    st.image(res_plotted,
+                             caption="Обработанное изображение",
+                             use_column_width=True)
+                    try:
+                        with st.expander("Результаты обнаружения"):
+                            for box in boxes:
+                                st.write(box.xywh)
+                    except Exception as ex:
+                        st.write("Изображение не загружено")
+                        st.write(ex)
+
+
+def infer_uploaded_video(conf, model):
+
+    source_video = st.sidebar.file_uploader(
+        label="Выберите видео..."
+    )
+
+    if source_video:
+        st.video(source_video)
+
+    if source_video:
+        if st.button("Старт"):
+            with st.spinner("Запускается..."):
+                try:
+                    tfile = tempfile.NamedTemporaryFile()
+                    tfile.write(source_video.read())
+                    vid_cap = cv2.VideoCapture(
+                        tfile.name)
+                    st_frame = st.empty()
+                    while (vid_cap.isOpened()):
+                        success, image = vid_cap.read()
+                        if success:
+                            _display_detected_frames(conf,
+                                                     model,
+                                                     st_frame,
+                                                     image
+                                                     )
+                        else:
+                            vid_cap.release()
+                            break
+                except Exception as e:
+                    st.error(f"Ошибка загрузки видео: {e}")
+
+
+def infer_uploaded_webcam(conf, model):
+
+    try:
+        flag = st.button(
+            label="Остановить"
+        )
+        vid_cap = cv2.VideoCapture(0)
+        st_frame = st.empty()
+        while not flag:
+            success, image = vid_cap.read()
+            if success:
+                _display_detected_frames(
+                    conf,
+                    model,
+                    st_frame,
+                    image
+                )
+            else:
+                vid_cap.release()
+                break
+    except Exception as e:
+        st.error(f"Ошибка загрузки видео: {str(e)}")

weights/detection/DetLicPL_l.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a892f06265665e955a46e9f49abf270eea4a8c25093ae2d24543d6919d8676d9
+size 87670451

weights/detection/DetLicPL_s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2b7770f243f33a7337eeedcc109661dfd518aaf2627db720e539888ff64492
+size 22540707

weights/detection/VehDet.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77518fbebfa269255c68b7da291dfcf38def1988c1f95e6ebd2da5c48bda3265
+size 22543075

weights/detection/yolov8l-seg.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa891dab47031c12ac82cb1b883af4ab9efbc732118cc04604bfbf107f9dfa8
+size 92391859

weights/detection/yolov8l.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18218ea4798da042d9862e6029ca9531adbd40ace19b6c9a75e2e28f1adf30cc
+size 87769683

weights/detection/yolov8m-seg.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fc740ca0824e14b44681d491dc601efa664ec6ecea9a870acf876053826448
+size 54899779

weights/detection/yolov8m.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c25b0b63b1a433843f06d821a9ac1deb8d5805f74f0f38772c7308c5adc55a5
+size 52117635

weights/detection/yolov8n-seg.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39e867b2c3a5dbc1aa764411544b475cb14727bf6af1ec46c238f8bb1351ab9
+size 7054355

weights/detection/yolov8n.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e20dde3def09e2cf938c7be6fe23d9150bbbe503982af13345706515f2ef95
+size 6534387

weights/detection/yolov8s-seg.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c035c6c5f9c48ee962518ef648854c2cc5e60fa404fac443e17d306fdda16543
+size 23897299

weights/detection/yolov8s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268e5bb54c640c96c3510224833bc2eeacab4135c6deb41502156e39986b562d
+size 22573363

weights/detection/yolov8x-seg.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63cbfa5764867c0066bedfa43cf2dcd90a412a1de44b2e238c43978a9d28ea6
+size 144076467

weights/detection/yolov8x.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d5a3f000d771762f03fc8b57ebd0aae324aeaefdd6e68492a9c4470f2d1e8b
+size 136867539