From 7b19e0daa0a5cd4596c0e9b9de5edc18d456b487 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Mon, 16 Sep 2024 20:47:37 +0200 Subject: [PATCH] Threaded inference docs improvements (#16313) Signed-off-by: UltralyticsAssistant Co-authored-by: UltralyticsAssistant --- README.md | 44 +++++++++----------- README.zh-CN.md | 44 +++++++++----------- docs/en/modes/predict.md | 18 ++++---- docs/en/modes/track.md | 59 +++++++++++---------------- docs/en/yolov5/quickstart_tutorial.md | 4 +- 5 files changed, 72 insertions(+), 97 deletions(-) diff --git a/README.md b/README.md index e13ef56450..704c04b794 100644 --- a/README.md +++ b/README.md @@ -87,14 +87,25 @@ YOLOv8 may also be used directly in a Python environment, and accepts the same [ from ultralytics import YOLO # Load a model -model = YOLO("yolov8n.yaml") # build a new model from scratch -model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training) - -# Use the model -model.train(data="coco8.yaml", epochs=3) # train the model -metrics = model.val() # evaluate model performance on the validation set -results = model("https://ultralytics.com/images/bus.jpg") # predict on an image -path = model.export(format="onnx") # export the model to ONNX format +model = YOLO("yolov8n.pt") + +# Train the model +train_results = model.train( + data="coco8.yaml", # path to dataset YAML + epochs=100, # number of training epochs + imgsz=640, # training image size + device="cpu", # device to run on, i.e. device=0 or device=0,1,2,3 or device=cpu +) + +# Evaluate model performance on the validation set +metrics = model.val() + +# Perform object detection on an image +results = model("path/to/image.jpg") +results[0].show() + +# Export the model to ONNX format +path = model.export(format="onnx") # return path to exported model ``` See YOLOv8 [Python Docs](https://docs.ultralytics.com/usage/python/) for more examples. @@ -139,23 +150,6 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp -
Detection (Open Image V7) - -See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examples with these models trained on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/), which include 600 pre-trained classes. - -| Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | - -- **mAPval** values are for single-model single-scale on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/) dataset.
Reproduce by `yolo val detect data=open-images-v7.yaml device=0` -- **Speed** averaged over Open Image V7 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu` - -
-
Segmentation (COCO) See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage examples with these models trained on [COCO-Seg](https://docs.ultralytics.com/datasets/segment/coco/), which include 80 pre-trained classes. diff --git a/README.zh-CN.md b/README.zh-CN.md index 4319c0dff8..1e7b972762 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -89,14 +89,25 @@ YOLOv8 也可以在 Python 环境中直接使用，并接受与上述 CLI 示例 from ultralytics import YOLO # 加载模型 -model = YOLO("yolov8n.yaml") # 从头开始构建新模型 -model = YOLO("yolov8n.pt") # 加载预训练模型（建议用于训练） - -# 使用模型 -model.train(data="coco8.yaml", epochs=3) # 训练模型 -metrics = model.val() # 在验证集上评估模型性能 -results = model("https://ultralytics.com/images/bus.jpg") # 对图像进行预测 -success = model.export(format="onnx") # 将模型导出为 ONNX 格式 +model = YOLO("yolov8n.pt") + +# 训练模型 +train_results = model.train( + data="coco8.yaml", # 数据配置文件的路径 + epochs=100, # 训练的轮数 + imgsz=640, # 训练图像大小 + device="cpu", # 运行的设备，例如 device=0 或 device=0,1,2,3 或 device=cpu +) + +# 在验证集上评估模型性能 +metrics = model.val() + +# 对图像进行目标检测 +results = model("path/to/image.jpg") +results[0].show() + +# 将模型导出为 ONNX 格式 +path = model.export(format="onnx") # 返回导出的模型路径 ``` 查看 YOLOv8 [Python 文档](https://docs.ultralytics.com/usage/python/)以获取更多示例。 @@ -141,23 +152,6 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
-
检测（Open Image V7） - -查看[检测文档](https://docs.ultralytics.com/tasks/detect/)以获取这些在[Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/)上训练的模型的使用示例，其中包括600个预训练类别。 - -| 模型 | 尺寸
(像素) | mAP验证
50-95 | 速度
CPU ONNX
(毫秒) | 速度
A100 TensorRT
(毫秒) | 参数
(M) | 浮点运算
(B) | -| ----------------------------------------------------------------------------------------- | ------------------- | --------------------- | ------------------------------- | ------------------------------------ | ---------------- | -------------------- | -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | - -- **mAP验证** 值适用于在[Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/)数据集上的单模型单尺度。
通过 `yolo val detect data=open-images-v7.yaml device=0` 以复现。 -- **速度** 在使用[Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/)实例对Open Image V7验证图像进行平均测算。
通过 `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu` 以复现。 - -
-
分割 (COCO) 查看[分割文档](https://docs.ultralytics.com/tasks/segment/)以获取这些在[COCO-Seg](https://docs.ultralytics.com/datasets/segment/coco/)上训练的模型的使用示例，其中包括80个预训练类别。 diff --git a/docs/en/modes/predict.md b/docs/en/modes/predict.md index 3bda0c079b..5ca5dab9d8 100644 --- a/docs/en/modes/predict.md +++ b/docs/en/modes/predict.md @@ -61,7 +61,7 @@ Ultralytics YOLO models return either a Python list of `Results` objects, or a m model = YOLO("yolov8n.pt") # pretrained YOLOv8n model # Run batched inference on a list of images - results = model(["im1.jpg", "im2.jpg"]) # return a list of Results objects + results = model(["image1.jpg", "image2.jpg"]) # return a list of Results objects # Process results list for result in results: @@ -83,7 +83,7 @@ Ultralytics YOLO models return either a Python list of `Results` objects, or a m model = YOLO("yolov8n.pt") # pretrained YOLOv8n model # Run batched inference on a list of images - results = model(["im1.jpg", "im2.jpg"], stream=True) # return a generator of Results objects + results = model(["image1.jpg", "image2.jpg"], stream=True) # return a generator of Results objects # Process results generator for result in results: @@ -109,8 +109,8 @@ YOLOv8 can process different types of input sources for inference, as shown in t | image | `'image.jpg'` | `str` or `Path` | Single image file. | | URL | `'https://ultralytics.com/images/bus.jpg'` | `str` | URL to an image. | | screenshot | `'screen'` | `str` | Capture a screenshot. | -| PIL | `Image.open('im.jpg')` | `PIL.Image` | HWC format with RGB channels. | -| OpenCV | `cv2.imread('im.jpg')` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | +| PIL | `Image.open('image.jpg')` | `PIL.Image` | HWC format with RGB channels. | +| OpenCV | `cv2.imread('image.jpg')` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | | numpy | `np.zeros((640,1280,3))` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | | torch | `torch.zeros(16,3,320,640)` | `torch.Tensor` | BCHW format with RGB channels `float32 (0.0-1.0)`. | | CSV | `'sources.csv'` | `str` or `Path` | CSV file containing paths to images, videos, or directories. | @@ -710,16 +710,16 @@ When using YOLO models in a multi-threaded application, it's important to instan from ultralytics import YOLO - def thread_safe_predict(image_path): + def thread_safe_predict(model, image_path): """Performs thread-safe prediction on an image using a locally instantiated YOLO model.""" - local_model = YOLO("yolov8n.pt") - results = local_model.predict(image_path) + model = YOLO(model) + results = model.predict(image_path) # Process results # Starting threads that each have their own model instance - Thread(target=thread_safe_predict, args=("image1.jpg",)).start() - Thread(target=thread_safe_predict, args=("image2.jpg",)).start() + Thread(target=thread_safe_predict, args=("yolov8n.pt", "image1.jpg")).start() + Thread(target=thread_safe_predict, args=("yolov8n.pt", "image2.jpg")).start() ``` For an in-depth look at thread-safe inference with YOLO models and step-by-step instructions, please refer to our [YOLO Thread-Safe Inference Guide](../guides/yolo-thread-safe-inference.md). This guide will provide you with all the necessary information to avoid common pitfalls and ensure that your multi-threaded inference runs smoothly. diff --git a/docs/en/modes/track.md b/docs/en/modes/track.md index cfeb8c9084..c222e592b7 100644 --- a/docs/en/modes/track.md +++ b/docs/en/modes/track.md @@ -290,63 +290,50 @@ Finally, after all threads have completed their task, the windows displaying the from ultralytics import YOLO + # Define model names and video sources + MODEL_NAMES = ["yolov8n.pt", "yolov8n-seg.pt"] + SOURCES = ["path/to/video1.mp4", 0] # local video, 0 for webcam - def run_tracker_in_thread(filename, model, file_index): - """ - Runs a video file or webcam stream concurrently with the YOLOv8 model using threading. - This function captures video frames from a given file or camera source and utilizes the YOLOv8 model for object - tracking. The function runs in its own thread for concurrent processing. + def run_tracker_in_thread(model_name, filename, index): + """ + Runs a video file or webcam stream concurrently with the YOLOv8 model using threading. This function captures video + frames from a given file or camera source and utilizes the YOLOv8 model for object tracking. The function runs in + its own thread for concurrent processing. Args: filename (str): The path to the video file or the identifier for the webcam/external camera source. model (obj): The YOLOv8 model object. - file_index (int): An index to uniquely identify the file being processed, used for display purposes. - - Note: - Press 'q' to quit the video display window. + index (int): An index to uniquely identify the file being processed, used for display purposes. """ - video = cv2.VideoCapture(filename) # Read the video file + model = YOLO(model_name) + video = cv2.VideoCapture(filename) while True: - ret, frame = video.read() # Read the video frames - - # Exit the loop if no more frames in either video + ret, frame = video.read() if not ret: break - # Track objects in frames if available results = model.track(frame, persist=True) res_plotted = results[0].plot() - cv2.imshow(f"Tracking_Stream_{file_index}", res_plotted) + cv2.imshow(f"Tracking_Stream_{index}", res_plotted) - key = cv2.waitKey(1) - if key == ord("q"): + if cv2.waitKey(1) == ord("q"): break - # Release video sources video.release() - # Load the models - model1 = YOLO("yolov8n.pt") - model2 = YOLO("yolov8n-seg.pt") + # Create and start tracker threads using a for loop + tracker_threads = [] + for i, (video_file, model_name) in enumerate(zip(SOURCES, MODEL_NAMES), start=1): + thread = threading.Thread(target=run_tracker_in_thread, args=(model_name, video_file, i), daemon=True) + tracker_threads.append(thread) + thread.start() - # Define the video files for the trackers - video_file1 = "path/to/video1.mp4" # Path to video file, 0 for webcam - video_file2 = 0 # Path to video file, 0 for webcam, 1 for external camera - - # Create the tracker threads - tracker_thread1 = threading.Thread(target=run_tracker_in_thread, args=(video_file1, model1, 1), daemon=True) - tracker_thread2 = threading.Thread(target=run_tracker_in_thread, args=(video_file2, model2, 2), daemon=True) - - # Start the tracker threads - tracker_thread1.start() - tracker_thread2.start() - - # Wait for the tracker threads to finish - tracker_thread1.join() - tracker_thread2.join() + # Wait for all tracker threads to finish + for thread in tracker_threads: + thread.join() # Clean up and close windows cv2.destroyAllWindows() diff --git a/docs/en/yolov5/quickstart_tutorial.md b/docs/en/yolov5/quickstart_tutorial.md index f8cabb9f23..582dfcbda8 100644 --- a/docs/en/yolov5/quickstart_tutorial.md +++ b/docs/en/yolov5/quickstart_tutorial.md @@ -44,8 +44,8 @@ Harness `detect.py` for versatile inference on various sources. It automatically ```bash python detect.py --weights yolov5s.pt --source 0 # webcam - img.jpg # image - vid.mp4 # video + image.jpg # image + video.mp4 # video screen # screenshot path/ # directory list.txt # list of images