diff --git a/README.md b/README.md index b26a29ac..18d71f0e 100644 --- a/README.md +++ b/README.md @@ -1,16 +1,16 @@

- - + +

[English](README.md) | [简体中文](README.zh-CN.md)
- CI - Citation - Docker Pulls + YOLOv3 CI + YOLOv3 Citation + Docker Pulls
Run on Gradient Open In Colab @@ -18,12 +18,9 @@

-🚀 is the world's most loved vision AI, representing Ultralytics open-source -research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours -of research and development. +YOLOv3 🚀 is the world's most loved vision AI, representing Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development. -To request an Enterprise License please complete the form at Ultralytics -Licensing. +To request an Enterprise License please complete the form at Ultralytics Licensing.
@@ -70,13 +67,12 @@ pip install ultralytics ##
Documentation
-See the [ 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 -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov3/blob/master/requirements.txt) in a +Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.7.0**](https://www.python.org/) environment, including [**PyTorch>=1.7**](https://pytorch.org/get-started/locally/). @@ -91,17 +87,14 @@ pip install -r requirements.txt # install
Inference -[PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36) -inference. [Models](https://github.com/ultralytics/yolov5/tree/master/models) download automatically from the latest -[release](https://github.com/ultralytics/yolov5/releases). +YOLOv3 [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36) 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 # Model -model = torch.hub.load( - "ultralytics/yolov3", "yolov3" -) # or yolov3-spp, yolov3-tiny, custom +model = torch.hub.load("ultralytics/yolov3", "yolov3") # or yolov5n - yolov5x6, custom # Images img = "https://ultralytics.com/images/zidane.jpg" # or file, Path, PIL, OpenCV, numpy, list @@ -118,9 +111,8 @@ results.print() # or .show(), .save(), .crop(), .pandas(), etc.
Inference with detect.py -`detect.py` runs inference on a variety of sources, -downloading [models](https://github.com/ultralytics/yolov5/tree/master/models) automatically from -the latest [release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`. +`detect.py` runs inference on a variety of sources, downloading [models](https://github.com/ultralytics/yolov5/tree/master/models) automatically from +the latest YOLOv3 [release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`. ```bash python detect.py --weights yolov5s.pt --source 0 # webcam @@ -140,13 +132,13 @@ python detect.py --weights yolov5s.pt --source 0 #
Training -The commands below reproduce [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) +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 -[release](https://github.com/ultralytics/yolov5/releases). Training times for YOLOv5n/s/m/l/x are +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://github.com/ultralytics/yolov5/issues/475) times faster). Use the largest `--batch-size` possible, or pass `--batch-size -1` for -[AutoBatch](https://github.com/ultralytics/yolov5/pull/5092). Batch sizes shown for V100-16GB. +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 @@ -163,8 +155,8 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml -
Tutorials -- [Train Custom Data](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data)🚀 RECOMMENDED -- [Tips for Best Training Results](https://github.com/ultralytics/yolov5/wiki/Tips-for-Best-Training-Results)☘️ +- [Train Custom Data](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data)  🚀 RECOMMENDED +- [Tips for Best Training Results](https://github.com/ultralytics/yolov5/wiki/Tips-for-Best-Training-Results)  ☘️ RECOMMENDED - [Multi-GPU Training](https://github.com/ultralytics/yolov5/issues/475) - [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36) 🌟 NEW @@ -176,9 +168,9 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml - - [Hyperparameter Evolution](https://github.com/ultralytics/yolov5/issues/607) - [Transfer Learning with Frozen Layers](https://github.com/ultralytics/yolov5/issues/1314) - [Architecture Summary](https://github.com/ultralytics/yolov5/issues/6998) 🌟 NEW -- [Roboflow for Datasets, Labeling, and Active Learning](https://github.com/ultralytics/yolov5/issues/4975)🌟 NEW +- [Roboflow for Datasets, Labeling, and Active Learning](https://github.com/ultralytics/yolov5/issues/4975)  🌟 NEW - [ClearML Logging](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/clearml) 🌟 NEW -- [ with Neural Magic's Deepsparse](https://bit.ly/yolov5-neuralmagic) 🌟 NEW +- [YOLOv3 with Neural Magic's Deepsparse](https://bit.ly/yolov5-neuralmagic) 🌟 NEW - [Comet Logging](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/comet) 🌟 NEW
@@ -187,7 +179,7 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml -
- +

@@ -205,38 +197,34 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml -
-| Roboflow | ClearML ⭐ NEW | Comet ⭐ NEW | Neural Magic ⭐ NEW | -| :--------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------: | -| Label and export your custom datasets directly to for training with [Roboflow](https://roboflow.com/?ref=ultralytics) | Automatically track, visualize and even remotely train using [ClearML](https://cutt.ly/yolov5-readme-clearml) (open-source!) | Free forever, [Comet](https://bit.ly/yolov5-readme-comet2) lets you save models, resume training, and interactively visualise and debug predictions | Run inference up to 6x faster with [Neural Magic DeepSparse](https://bit.ly/yolov5-neuralmagic) | +| Roboflow | ClearML ⭐ NEW | Comet ⭐ NEW | Neural Magic ⭐ NEW | +| :--------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------: | +| Label and export your custom datasets directly to YOLOv3 for training with [Roboflow](https://roboflow.com/?ref=ultralytics) | Automatically track, visualize and even remotely train YOLOv3 using [ClearML](https://cutt.ly/yolov5-readme-clearml) (open-source!) | Free forever, [Comet](https://bit.ly/yolov5-readme-comet2) lets you save YOLOv3 models, resume training, and interactively visualise and debug predictions | Run YOLOv3 inference up to 6x faster with [Neural Magic DeepSparse](https://bit.ly/yolov5-neuralmagic) | ##
Ultralytics HUB
-[Ultralytics HUB](https://bit.ly/ultralytics_hub) is our ⭐ **NEW** no-code solution to visualize datasets, train 🚀 -models, and deploy to the real world in a seamless experience. Get started for **Free** now! +Experience seamless AI with [Ultralytics HUB](https://bit.ly/ultralytics_hub) ⭐, the all-in-one solution for data visualization, YOLO 🚀 model training and deployment, without any coding. Transform images into actionable insights and bring your AI visions to life with ease using our cutting-edge platform and user-friendly [Ultralytics App](https://ultralytics.com/app_install). Start your journey for **Free** now! -##
Why YOLO
+##
Why YOLOv3
-has been designed to be super easy to get started and simple to learn. We prioritize real-world results. +YOLOv3 has been designed to be super easy to get started and simple to learn. We prioritize real-world results.

- YOLOv5-P5 640 Figure + YOLOv3-P5 640 Figure

Figure Notes -- **COCO AP val** denotes mAP@0.5:0.95 metric measured on the 5000-image [COCO val2017](http://cocodataset.org) dataset - over various inference sizes from 256 to 1536. -- **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using - a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100 instance at batch-size 32. +- **COCO AP val** denotes mAP@0.5:0.95 metric measured on the 5000-image [COCO val2017](http://cocodataset.org) dataset over various inference sizes from 256 to 1536. +- **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100 instance at batch-size 32. - **EfficientDet** data from [google/automl](https://github.com/google/automl) at batch size 8. -- **Reproduce** - by `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt` +- **Reproduce** by `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
@@ -259,28 +247,16 @@ has been designed to be super easy to get started and simple to learn. We priori
Table Notes -- 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://github.com/ultralytics/yolov5/issues/303) includes reflection and scale - augmentations.
Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment` +- 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://github.com/ultralytics/yolov5/issues/303) includes reflection and scale augmentations.
Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
##
Segmentation
-Our new YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) instance segmentation models are the -fastest and most accurate in the world, beating all -current [SOTA benchmarks](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco). We've made them -super simple to train, validate and deploy. See full details in -our [Release Notes](https://github.com/ultralytics/yolov5/releases/v7.0) and visit -our [YOLOv5 Segmentation Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) for -quickstart tutorials. +Our new YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) instance segmentation models are the fastest and most accurate in the world, beating all current [SOTA benchmarks](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco). We've made them super simple to train, validate and deploy. See full details in our [Release Notes](https://github.com/ultralytics/yolov5/releases/v7.0) and visit our [YOLOv5 Segmentation Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) for quickstart tutorials.
Segmentation Checkpoints @@ -290,9 +266,7 @@ quickstart tutorials.
-We trained YOLOv5 segmentations models on COCO for 300 epochs at image size 640 using A100 GPUs. We exported all models -to ONNX FP32 for CPU speed tests and to TensorRT FP16 for GPU speed tests. We ran all speed tests on -Google [Colab Pro](https://colab.research.google.com/signup) notebooks for easy reproducibility. +We trained YOLOv5 segmentations models on COCO for 300 epochs at image size 640 using A100 GPUs. We exported all models to ONNX FP32 for CPU speed tests and to TensorRT FP16 for GPU speed tests. We ran all speed tests on Google [Colab Pro](https://colab.research.google.com/signup) notebooks for easy reproducibility. | Model | size
(pixels) | mAPbox
50-95 | mAPmask
50-95 | Train time
300 epochs
A100 (hours) | Speed
ONNX CPU
(ms) | Speed
TRT A100
(ms) | params
(M) | FLOPs
@640 (B) | | ------------------------------------------------------------------------------------------ | --------------------- | -------------------- | --------------------- | --------------------------------------------- | ------------------------------ | ------------------------------ | ------------------ | ---------------------- | @@ -302,15 +276,10 @@ Google [Colab Pro](https://colab.research.google.com/signup) notebooks for easy | [YOLOv5l-seg](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l-seg.pt) | 640 | 49.0 | 39.9 | 66:43 (2x) | 857.4 | 2.9 | 47.9 | 147.7 | | [YOLOv5x-seg](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x-seg.pt) | 640 | **50.7** | **41.4** | 62:56 (3x) | 1579.2 | 4.5 | 88.8 | 265.7 | -- All checkpoints are trained to 300 epochs with SGD optimizer with `lr0=0.01` and `weight_decay=5e-5` at image size 640 - and all default settings.
Runs logged to https://wandb.ai/glenn-jocher/YOLOv5_v70_official -- **Accuracy** values are for single-model single-scale on COCO dataset.
Reproduce - by `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt` -- **Speed** averaged over 100 inference images using a [Colab Pro](https://colab.research.google.com/signup) A100 - High-RAM instance. Values indicate inference speed only (NMS adds about 1ms per image).
Reproduce - by `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt --batch 1` -- **Export** to ONNX at FP32 and TensorRT at FP16 done with `export.py`.
Reproduce - by `python export.py --weights yolov5s-seg.pt --include engine --device 0 --half` +- All checkpoints are trained to 300 epochs with SGD optimizer with `lr0=0.01` and `weight_decay=5e-5` at image size 640 and all default settings.
Runs logged to https://wandb.ai/glenn-jocher/YOLOv5_v70_official +- **Accuracy** values are for single-model single-scale on COCO dataset.
Reproduce by `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt` +- **Speed** averaged over 100 inference images using a [Colab Pro](https://colab.research.google.com/signup) A100 High-RAM instance. Values indicate inference speed only (NMS adds about 1ms per image).
Reproduce by `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt --batch 1` +- **Export** to ONNX at FP32 and TensorRT at FP16 done with `export.py`.
Reproduce by `python export.py --weights yolov5s-seg.pt --include engine --device 0 --half` @@ -319,9 +288,7 @@ Google [Colab Pro](https://colab.research.google.com/signup) notebooks for easy ### Train -YOLOv5 segmentation training supports auto-download COCO128-seg segmentation dataset with `--data coco128-seg.yaml` -argument and manual download of COCO-segments dataset with `bash data/scripts/get_coco.sh --train --val --segments` and -then `python train.py --data coco.yaml`. +YOLOv5 segmentation training supports auto-download COCO128-seg segmentation dataset with `--data coco128-seg.yaml` argument and manual download of COCO-segments dataset with `bash data/scripts/get_coco.sh --train --val --segments` and then `python train.py --data coco.yaml`. ```bash # Single-GPU @@ -369,21 +336,14 @@ python export.py --weights yolov5s-seg.pt --include onnx engine --img 640 --devi ##
Classification
-YOLOv5 [release v6.2](https://github.com/ultralytics/yolov5/releases) brings support for classification model training, -validation and deployment! See full details in our [Release Notes](https://github.com/ultralytics/yolov5/releases/v6.2) -and visit -our [YOLOv5 Classification Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb) -for quickstart tutorials. +YOLOv5 [release v6.2](https://github.com/ultralytics/yolov5/releases) brings support for classification model training, validation and deployment! See full details in our [Release Notes](https://github.com/ultralytics/yolov5/releases/v6.2) and visit our [YOLOv5 Classification Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb) for quickstart tutorials.
Classification Checkpoints
-We trained YOLOv5-cls classification models on ImageNet for 90 epochs using a 4xA100 instance, and we trained ResNet and -EfficientNet models alongside with the same default training settings to compare. We exported all models to ONNX FP32 -for CPU speed tests and to TensorRT FP16 for GPU speed tests. We ran all speed tests on -Google [Colab Pro](https://colab.research.google.com/signup) for easy reproducibility. +We trained YOLOv5-cls classification models on ImageNet for 90 epochs using a 4xA100 instance, and we trained ResNet and EfficientNet models alongside with the same default training settings to compare. We exported all models to ONNX FP32 for CPU speed tests and to TensorRT FP16 for GPU speed tests. We ran all speed tests on Google [Colab Pro](https://colab.research.google.com/signup) for easy reproducibility. | Model | size
(pixels) | acc
top1 | acc
top5 | Training
90 epochs
4xA100 (hours) | Speed
ONNX CPU
(ms) | Speed
TensorRT V100
(ms) | params
(M) | FLOPs
@224 (B) | | -------------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | -------------------------------------------- | ------------------------------ | ----------------------------------- | ------------------ | ---------------------- | @@ -406,14 +366,10 @@ Google [Colab Pro](https://colab.research.google.com/signup) for easy reproducib
Table Notes (click to expand) -- All checkpoints are trained to 90 epochs with SGD optimizer with `lr0=0.001` and `weight_decay=5e-5` at image size 224 - and all default settings.
Runs logged to https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2 -- **Accuracy** values are for single-model single-scale on [ImageNet-1k](https://www.image-net.org/index.php) - dataset.
Reproduce by `python classify/val.py --data ../datasets/imagenet --img 224` -- **Speed** averaged over 100 inference images using a Google [Colab Pro](https://colab.research.google.com/signup) V100 - High-RAM instance.
Reproduce by `python classify/val.py --data ../datasets/imagenet --img 224 --batch 1` -- **Export** to ONNX at FP32 and TensorRT at FP16 done with `export.py`.
Reproduce - by `python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224` +- All checkpoints are trained to 90 epochs with SGD optimizer with `lr0=0.001` and `weight_decay=5e-5` at image size 224 and all default settings.
Runs logged to https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2 +- **Accuracy** values are for single-model single-scale on [ImageNet-1k](https://www.image-net.org/index.php) dataset.
Reproduce by `python classify/val.py --data ../datasets/imagenet --img 224` +- **Speed** averaged over 100 inference images using a Google [Colab Pro](https://colab.research.google.com/signup) V100 High-RAM instance.
Reproduce by `python classify/val.py --data ../datasets/imagenet --img 224 --batch 1` +- **Export** to ONNX at FP32 and TensorRT at FP16 done with `export.py`.
Reproduce by `python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224`
@@ -423,8 +379,7 @@ Google [Colab Pro](https://colab.research.google.com/signup) for easy reproducib ### Train -YOLOv5 classification training supports auto-download of MNIST, Fashion-MNIST, CIFAR10, CIFAR100, Imagenette, Imagewoof, -and ImageNet datasets with the `--data` argument. To start training on MNIST for example use `--data mnist`. +YOLOv5 classification training supports auto-download of MNIST, Fashion-MNIST, CIFAR10, CIFAR100, Imagenette, Imagewoof, and ImageNet datasets with the `--data` argument. To start training on MNIST for example use `--data mnist`. ```bash # Single-GPU @@ -481,7 +436,7 @@ Get started in seconds with our verified environments. Click each icon below for - + @@ -493,10 +448,7 @@ Get started in seconds with our verified environments. Click each icon below for ##
Contribute
-We love your input! We want to make contributing to as easy and transparent as possible. Please see -our [Contributing Guide](CONTRIBUTING.md) to get started, and fill out -the [ Survey](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey) to send us -feedback on your experiences. Thank you to all our contributors! +We love your input! We want to make contributing to YOLOv3 as easy and transparent as possible. Please see our [Contributing Guide](CONTRIBUTING.md) to get started, and fill out the [YOLOv3 Survey](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey) to send us feedback on your experiences. Thank you to all our contributors! @@ -505,17 +457,14 @@ feedback on your experiences. Thank you to all our contributors! ##
License
-is available under two different licenses: +YOLOv3 is available under two different licenses: - **GPL-3.0 License**: See [LICENSE](https://github.com/ultralytics/yolov5/blob/master/LICENSE) file for details. -- **Enterprise License**: Provides greater flexibility for commercial product development without the open-source - requirements of GPL-3.0. Typical use cases are embedding Ultralytics software and AI models in commercial products and - applications. Request an Enterprise License at [Ultralytics Licensing](https://ultralytics.com/license). +- **Enterprise License**: Provides greater flexibility for commercial product development without the open-source requirements of GPL-3.0. Typical use cases are embedding Ultralytics software and AI models in commercial products and applications. Request an Enterprise License at [Ultralytics Licensing](https://ultralytics.com/license). ##
Contact
-For bug reports and feature requests please visit [GitHub Issues](https://github.com/ultralytics/yolov3/issues) or -the [Ultralytics Community Forum](https://community.ultralytics.com/). +For YOLOv3 bug reports and feature requests please visit [GitHub Issues](https://github.com/ultralytics/yolov5/issues) or the [Ultralytics Community Forum](https://community.ultralytics.com/).
diff --git a/README.zh-CN.md b/README.zh-CN.md index 5bd5a83d..6620131c 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -1,15 +1,15 @@

- - + +

[英文](README.md)|[简体中文](README.zh-CN.md)
- CI - Citation - Docker Pulls + YOLOv3 CI + YOLOv3 Citation + Docker Pulls
Run on Gradient Open In Colab @@ -17,8 +17,7 @@

-🚀 是世界上最受欢迎的视觉 AI，代表 Ultralytics 对未来视觉 AI -方法的开源研究，结合在数千小时的研究和开发中积累的经验教训和最佳实践。 +YOLOv3 🚀 是世界上最受欢迎的视觉 AI，代表 Ultralytics 对未来视觉 AI 方法的开源研究，结合在数千小时的研究和开发中积累的经验教训和最佳实践。 如果要申请企业许可证，请填写表格Ultralytics 许可. @@ -66,14 +65,12 @@ pip install ultralytics ##
文档
-有关训练、测试和部署的完整文档见[YOLOv5 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 -克隆 repo，并要求在 [**Python>=3.7.0**](https://www.python.org/) -环境中安装 [requirements.txt](https://github.com/ultralytics/yolov3/blob/master/requirements.txt) ，且要求 [**PyTorch> -=1.7**](https://pytorch.org/get-started/locally/) 。 +克隆 repo，并要求在 [**Python>=3.7.0**](https://www.python.org/) 环境中安装 [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) ，且要求 [**PyTorch>=1.7**](https://pytorch.org/get-started/locally/) 。 ```bash git clone https://github.com/ultralytics/yolov3 # clone @@ -86,17 +83,14 @@ pip install -r requirements.txt # install
推理 -使用 YOLOv5 [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36) -推理。最新 [模型](https://github.com/ultralytics/yolov5/tree/master/models) 将自动的从 -YOLOv5 [release](https://github.com/ultralytics/yolov5/releases) 中下载。 +使用 YOLOv3 [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36) 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 # Model -model = torch.hub.load( - "ultralytics/yolov3", "yolov3" -) # or yolov3-spp, yolov3-tiny, custom +model = torch.hub.load("ultralytics/yolov5", "yolov3") # or yolov5n - yolov5x6, custom # Images img = "https://ultralytics.com/images/zidane.jpg" # or file, Path, PIL, OpenCV, numpy, list @@ -134,14 +128,12 @@ python detect.py --weights yolov5s.pt --source 0 #
训练 -下面的命令重现 YOLOv5 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 YOLOv5 [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://github.com/ultralytics/yolov5/issues/475) -训练速度更快）。 +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://github.com/ultralytics/yolov5/issues/475) 训练速度更快）。 尽可能使用更大的 `--batch-size` ，或通过 `--batch-size -1` 实现 -YOLOv5 [自动批处理](https://github.com/ultralytics/yolov5/pull/5092) 。下方显示的 batchsize 适用于 V100-16GB。 +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 @@ -181,7 +173,7 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml -
- +

@@ -201,19 +193,18 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml - | Roboflow | ClearML ⭐ 新 | Comet ⭐ 新 | Neural Magic ⭐ 新 | | :--------------------------------------------------------------------------------: | :-------------------------------------------------------------------------: | :-------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------: | -| 将您的自定义数据集进行标注并直接导出到 YOLOv5 以进行训练 [Roboflow](https://roboflow.com/?ref=ultralytics) | 自动跟踪、可视化甚至远程训练 YOLOv5 [ClearML](https://cutt.ly/yolov5-readme-clearml)（开源！） | 永远免费，[Comet](https://bit.ly/yolov5-readme-comet)可让您保存 YOLOv5 模型、恢复训练以及交互式可视化和调试预测 | 使用 [Neural Magic DeepSparse](https://bit.ly/yolov5-neuralmagic)，运行 YOLOv5 推理的速度最高可提高6倍 | +| 将您的自定义数据集进行标注并直接导出到 YOLOv3 以进行训练 [Roboflow](https://roboflow.com/?ref=ultralytics) | 自动跟踪、可视化甚至远程训练 YOLOv3 [ClearML](https://cutt.ly/yolov5-readme-clearml)（开源！） | 永远免费，[Comet](https://bit.ly/yolov5-readme-comet)可让您保存 YOLOv3 模型、恢复训练以及交互式可视化和调试预测 | 使用 [Neural Magic DeepSparse](https://bit.ly/yolov5-neuralmagic)，运行 YOLOv3 推理的速度最高可提高6倍 | ##
Ultralytics HUB
-[Ultralytics HUB](https://bit.ly/ultralytics_hub) 是我们的⭐**新的**用于可视化数据集、训练 YOLOv5 🚀 -模型并以无缝体验部署到现实世界的无代码解决方案。现在开始 **免费** 使用他！ +[Ultralytics HUB](https://bit.ly/ultralytics_hub) 是我们的⭐**新的**用于可视化数据集、训练 YOLOv3 🚀 模型并以无缝体验部署到现实世界的无代码解决方案。现在开始 **免费** 使用他！ -##
为什么选择 YOLOv5
+##
为什么选择 YOLOv3
-YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结果。 +YOLOv3 超级容易上手，简单易学。我们优先考虑现实世界的结果。

@@ -224,13 +215,10 @@ YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结
图表笔记 -- **COCO AP val** 表示 mAP@0.5:0.95 指标，在 [COCO val2017](http://cocodataset.org) 数据集的 5000 张图像上测得， 图像包含 - 256 到 1536 各种推理大小。 -- **显卡推理速度** 为在 [COCO val2017](http://cocodataset.org) - 数据集上的平均推理时间，使用 [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100实例，batchsize 为 32 。 +- **COCO AP val** 表示 mAP@0.5:0.95 指标，在 [COCO val2017](http://cocodataset.org) 数据集的 5000 张图像上测得， 图像包含 256 到 1536 各种推理大小。 +- **显卡推理速度** 为在 [COCO val2017](http://cocodataset.org) 数据集上的平均推理时间，使用 [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100实例，batchsize 为 32 。 - **EfficientDet** 数据来自 [google/automl](https://github.com/google/automl) ， batchsize 为32。 -- **复现命令** - 为 `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt` +- **复现命令** 为 `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
@@ -253,25 +241,16 @@ YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结
笔记 -- 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://github.com/ultralytics/yolov5/issues/303) 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` +- 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://github.com/ultralytics/yolov5/issues/303) 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`
-##
实例分割模型 ⭐ 新
+##
实例分割模型 ⭐ 新
-我们新的 YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) -实例分割模型是世界上最快和最准确的模型，击败所有当前 [SOTA 基准](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco) -。我们使它非常易于训练、验证和部署。更多细节请查看 [发行说明](https://github.com/ultralytics/yolov5/releases/v7.0) -或访问我们的 [YOLOv5 分割 Colab 笔记本](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) 以快速入门。 +我们新的 YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) 实例分割模型是世界上最快和最准确的模型，击败所有当前 [SOTA 基准](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco)。我们使它非常易于训练、验证和部署。更多细节请查看 [发行说明](https://github.com/ultralytics/yolov5/releases/v7.0) 或访问我们的 [YOLOv5 分割 Colab 笔记本](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) 以快速入门。
实例分割模型列表 @@ -283,9 +262,7 @@ YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结
-我们使用 A100 GPU 在 COCO 上以 640 图像大小训练了 300 epochs 得到 YOLOv5 分割模型。我们将所有模型导出到 ONNX FP32 以进行 -CPU 速度测试，并导出到 TensorRT FP16 以进行 GPU 速度测试。为了便于再现，我们在 -Google [Colab Pro](https://colab.research.google.com/signup) 上进行了所有速度测试。 +我们使用 A100 GPU 在 COCO 上以 640 图像大小训练了 300 epochs 得到 YOLOv5 分割模型。我们将所有模型导出到 ONNX FP32 以进行 CPU 速度测试，并导出到 TensorRT FP16 以进行 GPU 速度测试。为了便于再现，我们在 Google [Colab Pro](https://colab.research.google.com/signup) 上进行了所有速度测试。 | 模型 | 尺寸
（像素） | mAPbox
50-95 | mAPmask
50-95 | 训练时长
300 epochs
A100 GPU（小时） | 推理速度
ONNX CPU
（ms） | 推理速度
TRT A100
（ms） | 参数量
(M) | FLOPs
@640 (B) | | ------------------------------------------------------------------------------------------ | --------------- | -------------------- | --------------------- | --------------------------------------- | ----------------------------- | ----------------------------- | --------------- | ---------------------- | @@ -295,15 +272,10 @@ Google [Colab Pro](https://colab.research.google.com/signup) 上进行了所有 | [YOLOv5l-seg](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l-seg.pt) | 640 | 49.0 | 39.9 | 66:43 (2x) | 857.4 | 2.9 | 47.9 | 147.7 | | [YOLOv5x-seg](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x-seg.pt) | 640 | **50.7** | **41.4** | 62:56 (3x) | 1579.2 | 4.5 | 88.8 | 265.7 | -- 所有模型使用 SGD 优化器训练， 都使用 `lr0=0.01` 和 `weight_decay=5e-5` 参数， 图像大小为 640 。
训练 log - 可以查看 https://wandb.ai/glenn-jocher/YOLOv5_v70_official -- **准确性**结果都在 COCO 数据集上，使用单模型单尺度测试得到。
- 复现命令 `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt` -- **推理速度**是使用 100 张图像推理时间进行平均得到，测试环境使用 [Colab Pro](https://colab.research.google.com/signup) 上 - A100 高 RAM 实例。结果仅表示推理速度（NMS 每张图像增加约 1 毫秒）。
- 复现命令 `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt --batch 1` -- **模型转换**到 FP32 的 ONNX 和 FP16 的 TensorRT 脚本为 `export.py`.
- 运行命令 `python export.py --weights yolov5s-seg.pt --include engine --device 0 --half` +- 所有模型使用 SGD 优化器训练， 都使用 `lr0=0.01` 和 `weight_decay=5e-5` 参数， 图像大小为 640 。
训练 log 可以查看 https://wandb.ai/glenn-jocher/YOLOv5_v70_official +- **准确性**结果都在 COCO 数据集上，使用单模型单尺度测试得到。
复现命令 `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt` +- **推理速度**是使用 100 张图像推理时间进行平均得到，测试环境使用 [Colab Pro](https://colab.research.google.com/signup) 上 A100 高 RAM 实例。结果仅表示推理速度（NMS 每张图像增加约 1 毫秒）。
复现命令 `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt --batch 1` +- **模型转换**到 FP32 的 ONNX 和 FP16 的 TensorRT 脚本为 `export.py`.
运行命令 `python export.py --weights yolov5s-seg.pt --include engine --device 0 --half` @@ -312,9 +284,7 @@ Google [Colab Pro](https://colab.research.google.com/signup) 上进行了所有 ### 训练 -YOLOv5分割训练支持自动下载 COCO128-seg 分割数据集，用户仅需在启动指令中包含 `--data coco128-seg.yaml` 参数。 -若要手动下载，使用命令 `bash data/scripts/get_coco.sh --train --val --segments`， -在下载完毕后，使用命令 `python train.py --data coco.yaml` 开启训练。 +YOLOv5分割训练支持自动下载 COCO128-seg 分割数据集，用户仅需在启动指令中包含 `--data coco128-seg.yaml` 参数。 若要手动下载，使用命令 `bash data/scripts/get_coco.sh --train --val --segments`， 在下载完毕后，使用命令 `python train.py --data coco.yaml` 开启训练。 ```bash # 单 GPU @@ -362,19 +332,14 @@ python export.py --weights yolov5s-seg.pt --include onnx engine --img 640 --devi ##
分类网络 ⭐ 新
-YOLOv5 [release v6.2](https://github.com/ultralytics/yolov5/releases) -带来对分类模型训练、验证和部署的支持！详情请查看 [发行说明](https://github.com/ultralytics/yolov5/releases/v6.2) -或访问我们的 [YOLOv5 分类 Colab 笔记本](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb) -以快速入门。 +YOLOv5 [release v6.2](https://github.com/ultralytics/yolov5/releases) 带来对分类模型训练、验证和部署的支持！详情请查看 [发行说明](https://github.com/ultralytics/yolov5/releases/v6.2) 或访问我们的 [YOLOv5 分类 Colab 笔记本](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb) 以快速入门。
分类网络模型
-我们使用 4xA100 实例在 ImageNet 上训练了 90 个 epochs 得到 YOLOv5-cls 分类模型，我们训练了 ResNet 和 EfficientNet -模型以及相同的默认训练设置以进行比较。我们将所有模型导出到 ONNX FP32 以进行 CPU 速度测试，并导出到 TensorRT FP16 以进行 -GPU 速度测试。为了便于重现，我们在 Google 上进行了所有速度测试 [Colab Pro](https://colab.research.google.com/signup) 。 +我们使用 4xA100 实例在 ImageNet 上训练了 90 个 epochs 得到 YOLOv5-cls 分类模型，我们训练了 ResNet 和 EfficientNet 模型以及相同的默认训练设置以进行比较。我们将所有模型导出到 ONNX FP32 以进行 CPU 速度测试，并导出到 TensorRT FP16 以进行 GPU 速度测试。为了便于重现，我们在 Google 上进行了所有速度测试 [Colab Pro](https://colab.research.google.com/signup) 。 | 模型 | 尺寸
（像素） | acc
top1 | acc
top5 | 训练时长
90 epochs
4xA100（小时） | 推理速度
ONNX CPU
（ms） | 推理速度
TensorRT V100
（ms） | 参数
(M) | FLOPs
@640 (B) | | -------------------------------------------------------------------------------------------------- | --------------- | ---------------- | ---------------- | ------------------------------------ | ----------------------------- | ---------------------------------- | -------------- | ---------------------- | @@ -397,14 +362,10 @@ GPU 速度测试。为了便于重现，我们在 Google 上进行了所有速
Table Notes (点击以展开) -- 所有模型都使用 SGD 优化器训练 90 个 epochs，都使用 `lr0=0.001` 和 `weight_decay=5e-5` 参数， 图像大小为 224 - ，且都使用默认设置。
训练 log 可以查看 https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2 -- **准确性**都在单模型单尺度上计算，数据集使用 [ImageNet-1k](https://www.image-net.org/index.php) 。
- 复现命令 `python classify/val.py --data ../datasets/imagenet --img 224` -- **推理速度**是使用 100 个推理图像进行平均得到，测试环境使用谷歌 [Colab Pro](https://colab.research.google.com/signup) - V100 高 RAM 实例。
复现命令 `python classify/val.py --data ../datasets/imagenet --img 224 --batch 1` -- **模型导出**到 FP32 的 ONNX 和 FP16 的 TensorRT 使用 `export.py` 。
- 复现命令 `python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224` +- 所有模型都使用 SGD 优化器训练 90 个 epochs，都使用 `lr0=0.001` 和 `weight_decay=5e-5` 参数， 图像大小为 224 ，且都使用默认设置。
训练 log 可以查看 https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2 +- **准确性**都在单模型单尺度上计算，数据集使用 [ImageNet-1k](https://www.image-net.org/index.php) 。
复现命令 `python classify/val.py --data ../datasets/imagenet --img 224` +- **推理速度**是使用 100 个推理图像进行平均得到，测试环境使用谷歌 [Colab Pro](https://colab.research.google.com/signup) V100 高 RAM 实例。
复现命令 `python classify/val.py --data ../datasets/imagenet --img 224 --batch 1` +- **模型导出**到 FP32 的 ONNX 和 FP16 的 TensorRT 使用 `export.py` 。
复现命令 `python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224`
@@ -413,8 +374,7 @@ GPU 速度测试。为了便于重现，我们在 Google 上进行了所有速 ### 训练 -YOLOv5 分类训练支持自动下载 MNIST、Fashion-MNIST、CIFAR10、CIFAR100、Imagenette、Imagewoof 和 ImageNet -数据集，命令中使用 `--data` 即可。 MNIST 示例 `--data mnist` 。 +YOLOv5 分类训练支持自动下载 MNIST、Fashion-MNIST、CIFAR10、CIFAR100、Imagenette、Imagewoof 和 ImageNet 数据集，命令中使用 `--data` 即可。 MNIST 示例 `--data mnist` 。 ```bash # 单 GPU @@ -459,7 +419,7 @@ python export.py --weights yolov5s-cls.pt resnet50.pt efficientnet_b0.pt --inclu ##
环境
-使用下面我们经过验证的环境，在几秒钟内开始使用 YOLOv5 。单击下面的图标了解详细信息。 +使用下面我们经过验证的环境，在几秒钟内开始使用 YOLOv3 。单击下面的图标了解详细信息。
@@ -471,7 +431,7 @@ python export.py --weights yolov5s-cls.pt resnet50.pt efficientnet_b0.pt --inclu - + @@ -483,9 +443,7 @@ python export.py --weights yolov5s-cls.pt resnet50.pt efficientnet_b0.pt --inclu ##
贡献
-我们喜欢您的意见或建议！我们希望尽可能简单和透明地为 YOLOv5 做出贡献。请看我们的 [投稿指南](CONTRIBUTING.md) -，并填写 [YOLOv5调查](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey) -向我们发送您的体验反馈。感谢我们所有的贡献者！ +我们喜欢您的意见或建议！我们希望尽可能简单和透明地为 YOLOv3 做出贡献。请看我们的 [投稿指南](CONTRIBUTING.md)，并填写 [YOLOv5调查](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey) 向我们发送您的体验反馈。感谢我们所有的贡献者！ @@ -494,16 +452,14 @@ python export.py --weights yolov5s-cls.pt resnet50.pt efficientnet_b0.pt --inclu ##
License
-YOLOv5 在两种不同的 License 下可用： +YOLOv3 在两种不同的 License 下可用： - **GPL-3.0 License**： 查看 [License](https://github.com/ultralytics/yolov5/blob/master/LICENSE) 文件的详细信息。 -- **企业License**：在没有 GPL-3.0 开源要求的情况下为商业产品开发提供更大的灵活性。典型用例是将 Ultralytics 软件和 AI - 模型嵌入到商业产品和应用程序中。在以下位置申请企业许可证 [Ultralytics 许可](https://ultralytics.com/license) 。 +- **企业License**：在没有 GPL-3.0 开源要求的情况下为商业产品开发提供更大的灵活性。典型用例是将 Ultralytics 软件和 AI 模型嵌入到商业产品和应用程序中。在以下位置申请企业许可证 [Ultralytics 许可](https://ultralytics.com/license) 。 ##
联系我们
-请访问 [GitHub Issues](https://github.com/ultralytics/yolov3/issues) -或 [Ultralytics Community Forum](https://community.ultralytis.com) 以报告 YOLOv5 错误和请求功能。 +请访问 [GitHub Issues](https://github.com/ultralytics/yolov5/issues) 或 [Ultralytics Community Forum](https://community.ultralytis.com) 以报告 YOLOv3 错误和请求功能。