xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.108 add Meituan YOLOv6 models (#2811)

Browse Source 
Co-authored-by: Michael Currie <mcurrie@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Hicham Talaoubrid <98521878+HichTala@users.noreply.github.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
Co-authored-by: Szymon Mikler <sjmikler@gmail.com>
This commit is contained in:
Glenn Jocher
2023-05-25 00:43:32 +02:00
committed by GitHub
parent 07b57c03c8
commit ffc0e8ccf7
18 changed files with 233 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/models/index.md
View File

@ -11,6 +11,7 @@ In this documentation, we provide information on four major models:
1. [YOLOv3](./yolov3.md): The third iteration of the YOLO model family, known for its efficient real-time object detection capabilities.
2. [YOLOv5](./yolov5.md): An improved version of the YOLO architecture, offering better performance and speed tradeoffs compared to previous versions.
3. [YOLOv6](./yolov6.md): Released by [Meituan](https://about.meituan.com/) in 2022 and is in use in many of the company's autonomous delivery robots.
3. [YOLOv8](./yolov8.md): The latest version of the YOLO family, featuring enhanced capabilities such as instance segmentation, pose/keypoints estimation, and classification.
4. [Segment Anything Model (SAM)](./sam.md): Meta's Segment Anything Model (SAM).
5. [Realtime Detection Transformers (RT-DETR)](./rtdetr.md): Baidu's RT-DETR model.

2
docs/models/sam.md
View File

@ -26,7 +26,7 @@ For more information about the Segment Anything Model and the SA-1B dataset, ple
SAM can be used for a variety of downstream tasks involving object and image distributions beyond its training data. Examples include edge detection, object proposal generation, instance segmentation, and preliminary text-to-mask prediction. By employing prompt engineering, SAM can adapt to new tasks and data distributions in a zero-shot manner, making it a versatile and powerful tool for image segmentation tasks.
```python
from ultralytics.vit import SAM
from ultralytics import SAM
model = SAM('sam_b.pt')
model.info() # display model information

81
docs/models/yolov6.md Normal file
View File

@ -0,0 +1,81 @@
---
comments: true
description: Discover Meituan YOLOv6, a robust real-time object detector. Learn how to utilize pre-trained models with Ultralytics Python API for a variety of tasks.
---
# Meituan YOLOv6
## Overview
[Meituan](https://about.meituan.com/) YOLOv6 is a cutting-edge object detector that offers remarkable balance between speed and accuracy, making it a popular choice for real-time applications. This model introduces several notable enhancements on its architecture and training scheme, including the implementation of a Bi-directional Concatenation (BiC) module, an anchor-aided training (AAT) strategy, and an improved backbone and neck design for state-of-the-art accuracy on the COCO dataset.
![Meituan YOLOv6](https://user-images.githubusercontent.com/26833433/240750495-4da954ce-8b3b-41c4-8afd-ddb74361d3c2.png)
![Model example image](https://user-images.githubusercontent.com/26833433/240750557-3e9ec4f0-0598-49a8-83ea-f33c91eb6d68.png)
**Overview of YOLOv6.** Model architecture diagram showing the redesigned network components and training strategies that have led to significant performance improvements. (a) The neck of YOLOv6 (N and S are shown). Note for M/L, RepBlocks is replaced with CSPStackRep. (b) The
structure of a BiC module. (c) A SimCSPSPPF block. ([source](https://arxiv.org/pdf/2301.05586.pdf)).
### Key Features
- **Bi-directional Concatenation (BiC) Module:** YOLOv6 introduces a BiC module in the neck of the detector, enhancing localization signals and delivering performance gains with negligible speed degradation.
- **Anchor-Aided Training (AAT) Strategy:** This model proposes AAT to enjoy the benefits of both anchor-based and anchor-free paradigms without compromising inference efficiency.
- **Enhanced Backbone and Neck Design:** By deepening YOLOv6 to include another stage in the backbone and neck, this model achieves state-of-the-art performance on the COCO dataset at high-resolution input.
- **Self-Distillation Strategy:** A new self-distillation strategy is implemented to boost the performance of smaller models of YOLOv6, enhancing the auxiliary regression branch during training and removing it at inference to avoid a marked speed decline.
## Pre-trained Models
YOLOv6 provides various pre-trained models with different scales:
- YOLOv6-N: 37.5% AP on COCO val2017 at 1187 FPS with NVIDIA Tesla T4 GPU.
- YOLOv6-S: 45.0% AP at 484 FPS.
- YOLOv6-M: 50.0% AP at 226 FPS.
- YOLOv6-L: 52.8% AP at 116 FPS.
- YOLOv6-L6: State-of-the-art accuracy in real-time.
YOLOv6 also provides quantized models for different precisions and models optimized for mobile platforms.
## Usage
### Python API
```python
from ultralytics import YOLO
model = YOLO("yolov6n.yaml") # build new model from scratch
model.info() # display model information
model.predict("path/to/image.jpg") # predict
```
### Supported Tasks
| Model Type | Pre-trained Weights | Tasks Supported |
|------------|---------------------|------------------|
| YOLOv6-N | `yolov6-n.pt` | Object Detection |
| YOLOv6-S | `yolov6-s.pt` | Object Detection |
| YOLOv6-M | `yolov6-m.pt` | Object Detection |
| YOLOv6-L | `yolov6-l.pt` | Object Detection |
| YOLOv6-L6 | `yolov6-l6.pt` | Object Detection |
## Supported Modes
| Mode | Supported |
|------------|--------------------|
| Inference | :heavy_check_mark: |
| Validation | :heavy_check_mark: |
| Training | :heavy_check_mark: |
## Citations and Acknowledgements
We would like to acknowledge the authors for their significant contributions in the field of real-time object detection:
```bibtex
@misc{li2023yolov6,
title={YOLOv6 v3.0: A Full-Scale Reloading},
author={Chuyi Li and Lulu Li and Yifei Geng and Hongliang Jiang and Meng Cheng and Bo Zhang and Zaidan Ke and Xiaoming Xu and Xiangxiang Chu},
year={2023},
eprint={2301.05586},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
The original YOLOv6 paper can be found on [arXiv](https://arxiv.org/abs/2301.05586). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/meituan/YOLOv6). We appreciate their efforts in advancing the field and making their work accessible to the broader community.

16
docs/usage/hyperparameter_tuning.md
View File

@ -50,14 +50,14 @@ To install the required packages, run:
The `tune()` method in YOLOv8 provides an easy-to-use interface for hyperparameter tuning with Ray Tune. It accepts several arguments that allow you to customize the tuning process. Below is a detailed explanation of each parameter:
| Parameter | Type | Description | Default Value |
|-----------------|----------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
| `data` | str | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and validation data paths, as well as other dataset-specific settings. | |
| `space` | dict, optional | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | |
| `grace_period` | int, optional | The grace period in epochs for the [ASHA scheduler](https://docs.ray.io/en/latest/tune/api_docs/schedulers.html#asha-tune-schedulers-asha) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 |
| `gpu_per_trial` | int, optional | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None |
| `max_samples` | int, optional | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 |
| `train_args` | dict, optional | A dictionary of additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, batch size, and other training-specific configurations. | {} |
| Parameter | Type | Description | Default Value |
|-----------------|----------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
| `data` | str | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and validation data paths, as well as other dataset-specific settings. | |
| `space` | dict, optional | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | |
| `grace_period` | int, optional | The grace period in epochs for the [ASHA scheduler]https://docs.ray.io/en/latest/tune/api/schedulers.html) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 |
| `gpu_per_trial` | int, optional | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None |
| `max_samples` | int, optional | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 |
| `train_args` | dict, optional | A dictionary of additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, batch size, and other training-specific configurations. | {} |
By customizing these parameters, you can fine-tune the hyperparameter optimization process to suit your specific needs and available computational resources.