From 7c2031969a946a49960e166934dfbf48fa1f3dfa Mon Sep 17 00:00:00 2001 From: Ultralytics Assistant <135830346+UltralyticsAssistant@users.noreply.github.com> Date: Sat, 5 Oct 2024 14:10:25 +0200 Subject: [PATCH] Ultralytics Code Refactor https://ultralytics.com/actions (#2289) Refactor code for speed and clarity --- README.md | 40 ++++++++++++++++++++-------------------- README.zh-CN.md | 40 ++++++++++++++++++++-------------------- 2 files changed, 40 insertions(+), 40 deletions(-) diff --git a/README.md b/README.md index 01bd24d056..f197aba42c 100644 --- a/README.md +++ b/README.md @@ -46,7 +46,7 @@ To request an Enterprise License please complete the form at [Ultralytics Licens We are thrilled to announce the launch of Ultralytics YOLOv8 🚀, our NEW cutting-edge, state-of-the-art (SOTA) model released at **[https://github.com/ultralytics/ultralytics](https://github.com/ultralytics/ultralytics)**. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection, image segmentation and image classification tasks. -See the [YOLOv8 Docs](https://docs.ultralytics.com) for details and get started with: +See the [YOLOv8 Docs](https://docs.ultralytics.com/) for details and get started with: [![PyPI version](https://badge.fury.io/py/ultralytics.svg)](https://badge.fury.io/py/ultralytics) [![Downloads](https://static.pepy.tech/badge/ultralytics)](https://pepy.tech/project/ultralytics) @@ -61,7 +61,7 @@ pip install ultralytics ##
Documentation
-See the [YOLOv3 Docs](https://docs.ultralytics.com) for full documentation on training, testing and deployment. See below for quickstart examples. +See the [YOLOv3 Docs](https://docs.ultralytics.com/) for full documentation on training, testing and deployment. See below for quickstart examples.
Install @@ -79,7 +79,7 @@ pip install -r requirements.txt # install
Inference -YOLOv3 [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading) inference. [Models](https://github.com/ultralytics/yolov5/tree/master/models) download automatically from the latest YOLOv3 [release](https://github.com/ultralytics/yolov5/releases). +YOLOv3 [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading/) inference. [Models](https://github.com/ultralytics/yolov5/tree/master/models) download automatically from the latest YOLOv3 [release](https://github.com/ultralytics/yolov5/releases). ```python import torch @@ -122,7 +122,7 @@ python detect.py --weights yolov5s.pt --source 0 #
Training -The commands below reproduce YOLOv3 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) results. [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv3 [release](https://github.com/ultralytics/yolov5/releases). Training times for YOLOv5n/s/m/l/x are 1/2/4/6/8 days on a V100 GPU ([Multi-GPU](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training) times faster). Use the largest `--batch-size` possible, or pass `--batch-size -1` for YOLOv3 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092). Batch sizes shown for V100-16GB. +The commands below reproduce YOLOv3 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) results. [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv3 [release](https://github.com/ultralytics/yolov5/releases). Training times for YOLOv5n/s/m/l/x are 1/2/4/6/8 days on a V100 GPU ([Multi-GPU](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/) times faster). Use the largest `--batch-size` possible, or pass `--batch-size -1` for YOLOv3 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092). Batch sizes shown for V100-16GB. ```bash python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml --batch-size 128 @@ -139,22 +139,22 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml -
Tutorials -- [Train Custom Data](https://docs.ultralytics.com/yolov5/tutorials/train_custom_data) 🚀 RECOMMENDED +- [Train Custom Data](https://docs.ultralytics.com/yolov5/tutorials/train_custom_data/) 🚀 RECOMMENDED - [Tips for Best Training Results](https://docs.ultralytics.com/guides/model-training-tips/) ☘️ -- [Multi-GPU Training](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training) -- [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading) 🌟 NEW -- [TFLite, ONNX, CoreML, TensorRT Export](https://docs.ultralytics.com/yolov5/tutorials/model_export) 🚀 -- [NVIDIA Jetson platform Deployment](https://docs.ultralytics.com/yolov5/tutorials/running_on_jetson_nano) 🌟 NEW -- [Test-Time Augmentation (TTA)](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation) -- [Model Ensembling](https://docs.ultralytics.com/yolov5/tutorials/model_ensembling) -- [Model Pruning/Sparsity](https://docs.ultralytics.com/yolov5/tutorials/model_pruning_and_sparsity) -- [Hyperparameter Evolution](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution) -- [Transfer Learning with Frozen Layers](https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers) -- [Architecture Summary](https://docs.ultralytics.com/yolov5/tutorials/architecture_description) 🌟 NEW -- [Roboflow for Datasets, Labeling, and Active Learning](https://docs.ultralytics.com/yolov5/tutorials/roboflow_datasets_integration) -- [ClearML Logging](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration) 🌟 NEW -- [YOLOv5 with Neural Magic's Deepsparse](https://docs.ultralytics.com/yolov5/tutorials/neural_magic_pruning_quantization) 🌟 NEW -- [Comet Logging](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration) 🌟 NEW +- [Multi-GPU Training](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/) +- [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading/) 🌟 NEW +- [TFLite, ONNX, CoreML, TensorRT Export](https://docs.ultralytics.com/yolov5/tutorials/model_export/) 🚀 +- [NVIDIA Jetson platform Deployment](https://docs.ultralytics.com/yolov5/tutorials/running_on_jetson_nano/) 🌟 NEW +- [Test-Time Augmentation (TTA)](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) +- [Model Ensembling](https://docs.ultralytics.com/yolov5/tutorials/model_ensembling/) +- [Model Pruning/Sparsity](https://docs.ultralytics.com/yolov5/tutorials/model_pruning_and_sparsity/) +- [Hyperparameter Evolution](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution/) +- [Transfer Learning with Frozen Layers](https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers/) +- [Architecture Summary](https://docs.ultralytics.com/yolov5/tutorials/architecture_description/) 🌟 NEW +- [Roboflow for Datasets, Labeling, and Active Learning](https://docs.ultralytics.com/yolov5/tutorials/roboflow_datasets_integration/) +- [ClearML Logging](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration/) 🌟 NEW +- [YOLOv5 with Neural Magic's Deepsparse](https://docs.ultralytics.com/yolov5/tutorials/neural_magic_pruning_quantization/) 🌟 NEW +- [Comet Logging](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration/) 🌟 NEW
@@ -233,7 +233,7 @@ YOLOv3 has been designed to be super easy to get started and simple to learn. We - All checkpoints are trained to 300 epochs with default settings. Nano and Small models use [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) hyps, all others use [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml). - **mAPval** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset.
Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` - **Speed** averaged over COCO val images using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) instance. NMS times (~1 ms/img) not included.
Reproduce by `python val.py --data coco.yaml --img 640 --task speed --batch 1` -- **TTA** [Test Time Augmentation](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation) includes reflection and scale augmentations.
Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment` +- **TTA** [Test Time Augmentation](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) includes reflection and scale augmentations.
Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
diff --git a/README.zh-CN.md b/README.zh-CN.md index f8121080ec..04c5d9b99d 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -46,7 +46,7 @@ YOLOv3 🚀 是世界上最受欢迎的视觉 AI，代表文档 -有关训练、测试和部署的完整文档见[YOLOv3 文档](https://docs.ultralytics.com)。请参阅下面的快速入门示例。 +有关训练、测试和部署的完整文档见[YOLOv3 文档](https://docs.ultralytics.com/)。请参阅下面的快速入门示例。
安装 @@ -79,7 +79,7 @@ pip install -r requirements.txt # install
推理 -使用 YOLOv3 [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading) 推理。最新 [模型](https://github.com/ultralytics/yolov5/tree/master/models) 将自动的从 YOLOv3 [release](https://github.com/ultralytics/yolov5/releases) 中下载。 +使用 YOLOv3 [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading/) 推理。最新 [模型](https://github.com/ultralytics/yolov5/tree/master/models) 将自动的从 YOLOv3 [release](https://github.com/ultralytics/yolov5/releases) 中下载。 ```python import torch @@ -122,7 +122,7 @@ python detect.py --weights yolov5s.pt --source 0 #
训练 -下面的命令重现 YOLOv3 在 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) 数据集上的结果。 最新的 [模型](https://github.com/ultralytics/yolov5/tree/master/models) 和 [数据集](https://github.com/ultralytics/yolov5/tree/master/data) 将自动的从 YOLOv3 [release](https://github.com/ultralytics/yolov5/releases) 中下载。 YOLOv5n/s/m/l/x 在 V100 GPU 的训练时间为 1/2/4/6/8 天（ [多GPU](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training) 训练速度更快）。 尽可能使用更大的 `--batch-size` ，或通过 `--batch-size -1` 实现 YOLOv3 [自动批处理](https://github.com/ultralytics/yolov5/pull/5092) 。下方显示的 batchsize 适用于 V100-16GB。 +下面的命令重现 YOLOv3 在 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) 数据集上的结果。 最新的 [模型](https://github.com/ultralytics/yolov5/tree/master/models) 和 [数据集](https://github.com/ultralytics/yolov5/tree/master/data) 将自动的从 YOLOv3 [release](https://github.com/ultralytics/yolov5/releases) 中下载。 YOLOv5n/s/m/l/x 在 V100 GPU 的训练时间为 1/2/4/6/8 天（ [多GPU](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/) 训练速度更快）。 尽可能使用更大的 `--batch-size` ，或通过 `--batch-size -1` 实现 YOLOv3 [自动批处理](https://github.com/ultralytics/yolov5/pull/5092) 。下方显示的 batchsize 适用于 V100-16GB。 ```bash python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml --batch-size 128 @@ -139,22 +139,22 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml -
教程 -- [训练自定义数据](https://docs.ultralytics.com/yolov5/tutorials/train_custom_data) 🚀 推荐 +- [训练自定义数据](https://docs.ultralytics.com/yolov5/tutorials/train_custom_data/) 🚀 推荐 - [获得最佳训练结果的技巧](https://docs.ultralytics.com/guides/model-training-tips/) ☘️ -- [多GPU训练](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training) -- [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading) 🌟 新 -- [TFLite，ONNX，CoreML，TensorRT导出](https://docs.ultralytics.com/yolov5/tutorials/model_export) 🚀 -- [NVIDIA Jetson平台部署](https://docs.ultralytics.com/yolov5/tutorials/running_on_jetson_nano) 🌟 新 -- [测试时增强 (TTA)](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation) -- [模型集成](https://docs.ultralytics.com/yolov5/tutorials/model_ensembling) -- [模型剪枝/稀疏](https://docs.ultralytics.com/yolov5/tutorials/model_pruning_and_sparsity) -- [超参数进化](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution) -- [冻结层的迁移学习](https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers) -- [架构概述](https://docs.ultralytics.com/yolov5/tutorials/architecture_description) 🌟 新 -- [Roboflow用于数据集、标注和主动学习](https://docs.ultralytics.com/yolov5/tutorials/roboflow_datasets_integration) -- [ClearML日志记录](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration) 🌟 新 -- [使用Neural Magic的Deepsparse的YOLOv5](https://docs.ultralytics.com/yolov5/tutorials/neural_magic_pruning_quantization) 🌟 新 -- [Comet日志记录](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration) 🌟 新 +- [多GPU训练](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/) +- [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading/) 🌟 新 +- [TFLite，ONNX，CoreML，TensorRT导出](https://docs.ultralytics.com/yolov5/tutorials/model_export/) 🚀 +- [NVIDIA Jetson平台部署](https://docs.ultralytics.com/yolov5/tutorials/running_on_jetson_nano/) 🌟 新 +- [测试时增强 (TTA)](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) +- [模型集成](https://docs.ultralytics.com/yolov5/tutorials/model_ensembling/) +- [模型剪枝/稀疏](https://docs.ultralytics.com/yolov5/tutorials/model_pruning_and_sparsity/) +- [超参数进化](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution/) +- [冻结层的迁移学习](https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers/) +- [架构概述](https://docs.ultralytics.com/yolov5/tutorials/architecture_description/) 🌟 新 +- [Roboflow用于数据集、标注和主动学习](https://docs.ultralytics.com/yolov5/tutorials/roboflow_datasets_integration/) +- [ClearML日志记录](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration/) 🌟 新 +- [使用Neural Magic的Deepsparse的YOLOv5](https://docs.ultralytics.com/yolov5/tutorials/neural_magic_pruning_quantization/) 🌟 新 +- [Comet日志记录](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration/) 🌟 新
@@ -233,7 +233,7 @@ YOLOv3 超级容易上手，简单易学。我们优先考虑现实世界的结 - 所有模型都使用默认配置，训练 300 epochs。n和s模型使用 [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) ，其他模型都使用 [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml) 。 - \*\*mAPval\*\*在单模型单尺度上计算，数据集使用 [COCO val2017](http://cocodataset.org) 。
复现命令 `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` - **推理速度**在 COCO val 图像总体时间上进行平均得到，测试环境使用[AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/)实例。 NMS 时间 (大约 1 ms/img) 不包括在内。
复现命令 `python val.py --data coco.yaml --img 640 --task speed --batch 1` -- **TTA** [测试时数据增强](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation) 包括反射和尺度变换。
复现命令 `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment` +- **TTA** [测试时数据增强](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) 包括反射和尺度变换。
复现命令 `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`