首页下载资源网络技术论文实现 - YOLOv7：可训练的免费包为实时物体检测器树立了新标杆

ZIP论文实现 - YOLOv7：可训练的免费包为实时物体检测器树立了新标杆

2301_8048821439.37MB需要积分:1

资源文件列表:

yolov7.zip 大约有128个文件
  1. yolov7/
  2. yolov7/.gitignore 3.97KB
  3. yolov7/LICENSE.md 34.33KB
  4. yolov7/README.md 14.4KB
  5. yolov7/cfg/
  6. yolov7/cfg/baseline/
  7. yolov7/cfg/baseline/r50-csp.yaml 1.39KB
  8. yolov7/cfg/baseline/x50-csp.yaml 1.4KB
  9. yolov7/cfg/baseline/yolor-csp-x.yaml 1.56KB
  10. yolov7/cfg/baseline/yolor-csp.yaml 1.56KB
  11. yolov7/cfg/baseline/yolor-d6.yaml 1.96KB
  12. yolov7/cfg/baseline/yolor-e6.yaml 1.95KB
  13. yolov7/cfg/baseline/yolor-p6.yaml 1.99KB
  14. yolov7/cfg/baseline/yolor-w6.yaml 1.99KB
  15. yolov7/cfg/baseline/yolov3-spp.yaml 1.5KB
  16. yolov7/cfg/baseline/yolov3.yaml 1.49KB
  17. yolov7/cfg/baseline/yolov4-csp.yaml 1.56KB
  18. yolov7/cfg/deploy/
  19. yolov7/cfg/deploy/yolov7-d6.yaml 5.96KB
  20. yolov7/cfg/deploy/yolov7-e6.yaml 5.22KB
  21. yolov7/cfg/deploy/yolov7-e6e.yaml 9.27KB
  22. yolov7/cfg/deploy/yolov7-tiny-silu.yaml 2.97KB
  23. yolov7/cfg/deploy/yolov7-tiny.yaml 4.51KB
  24. yolov7/cfg/deploy/yolov7-w6.yaml 4.54KB
  25. yolov7/cfg/deploy/yolov7.yaml 3.9KB
  26. yolov7/cfg/deploy/yolov7x.yaml 4.39KB
  27. yolov7/cfg/training/
  28. yolov7/cfg/training/yolov7-d6.yaml 6.1KB
  29. yolov7/cfg/training/yolov7-e6.yaml 5.36KB
  30. yolov7/cfg/training/yolov7-e6e.yaml 9.41KB
  31. yolov7/cfg/training/yolov7-tiny.yaml 4.51KB
  32. yolov7/cfg/training/yolov7-w6.yaml 4.67KB
  33. yolov7/cfg/training/yolov7.yaml 3.91KB
  34. yolov7/cfg/training/yolov7x.yaml 4.38KB
  35. yolov7/data/
  36. yolov7/data/coco.yaml 1.39KB
  37. yolov7/data/hyp.scratch.custom.yaml 1.47KB
  38. yolov7/data/hyp.scratch.p5.yaml 1.47KB
  39. yolov7/data/hyp.scratch.p6.yaml 1.47KB
  40. yolov7/data/hyp.scratch.tiny.yaml 1.47KB
  41. yolov7/deploy/
  42. yolov7/deploy/triton-inference-server/
  43. yolov7/deploy/triton-inference-server/README.md 7.12KB
  44. yolov7/deploy/triton-inference-server/boundingbox.py 960B
  45. yolov7/deploy/triton-inference-server/client.py 14.03KB
  46. yolov7/deploy/triton-inference-server/data/
  47. yolov7/deploy/triton-inference-server/data/dog.jpg 159.92KB
  48. yolov7/deploy/triton-inference-server/data/dog_result.jpg 179.94KB
  49. yolov7/deploy/triton-inference-server/labels.py 1.35KB
  50. yolov7/deploy/triton-inference-server/processing.py 2.06KB
  51. yolov7/deploy/triton-inference-server/render.py 3.1KB
  52. yolov7/detect.py 9.11KB
  53. yolov7/export.py 8.95KB
  54. yolov7/figure/
  55. yolov7/figure/horses_prediction.jpg 151.45KB
  56. yolov7/figure/mask.png 101.6KB
  57. yolov7/figure/performance.png 164.53KB
  58. yolov7/figure/pose.png 347.06KB
  59. yolov7/figure/tennis.jpg 6.77KB
  60. yolov7/figure/tennis_caption.png 18.64KB
  61. yolov7/figure/tennis_panoptic.png 8.05KB
  62. yolov7/figure/tennis_semantic.jpg 4.43KB
  63. yolov7/figure/yolov7_3d.jpg 1.26MB
  64. yolov7/figure/yolov7_city.jpg 2.22MB
  65. yolov7/figure/yolov7_lidar.jpg 935.87KB
  66. yolov7/figure/yolov7_road.jpg 1.03MB
  67. yolov7/hubconf.py 3.5KB
  68. yolov7/inference/
  69. yolov7/inference/images/
  70. yolov7/inference/images/bus.jpg 476.01KB
  71. yolov7/inference/images/horses.jpg 130.37KB
  72. yolov7/inference/images/image1.jpg 78.85KB
  73. yolov7/inference/images/image2.jpg 140.26KB
  74. yolov7/inference/images/image3.jpg 114.89KB
  75. yolov7/inference/images/zidane.jpg 164.99KB
  76. yolov7/models/
  77. yolov7/models/__init__.py 6B
  78. yolov7/models/common.py 82.41KB
  79. yolov7/models/experimental.py 10.64KB
  80. yolov7/models/yolo.py 39.09KB
  81. yolov7/paper/
  82. yolov7/paper/yolov7.pdf 5.85MB
  83. yolov7/requirements.txt 958B
  84. yolov7/scripts/
  85. yolov7/scripts/get_coco.sh 820B
  86. yolov7/test.py 16.88KB
  87. yolov7/tools/
  88. yolov7/tools/YOLOv7-Dynamic-Batch-ONNXRUNTIME.ipynb 5.66MB
  89. yolov7/tools/YOLOv7-Dynamic-Batch-TENSORRT.ipynb 12.01MB
  90. yolov7/tools/YOLOv7CoreML.ipynb 873.18KB
  91. yolov7/tools/YOLOv7onnx.ipynb 1.47MB
  92. yolov7/tools/YOLOv7trt.ipynb 1.69MB
  93. yolov7/tools/compare_YOLOv7_vs_YOLOv5m6.ipynb 3.73MB
  94. yolov7/tools/compare_YOLOv7_vs_YOLOv5m6_half.ipynb 3.75MB
  95. yolov7/tools/compare_YOLOv7_vs_YOLOv5s6.ipynb 3.73MB
  96. yolov7/tools/compare_YOLOv7e6_vs_YOLOv5x6.ipynb 3.74MB
  97. yolov7/tools/compare_YOLOv7e6_vs_YOLOv5x6_half.ipynb 3.74MB
  98. yolov7/tools/instance.ipynb 476.94KB
  99. yolov7/tools/keypoint.ipynb 465.25KB
  100. yolov7/tools/reparameterization.ipynb 30.77KB
  101. yolov7/tools/visualization.ipynb 482.29KB
  102. yolov7/train.py 37.14KB
  103. yolov7/train_aux.py 36.56KB
  104. yolov7/utils/
  105. yolov7/utils/__init__.py 6B
  106. yolov7/utils/activations.py 2.2KB
  107. yolov7/utils/add_nms.py 5.48KB
  108. yolov7/utils/autoanchor.py 6.98KB
  109. yolov7/utils/aws/
  110. yolov7/utils/aws/__init__.py 5B
  111. yolov7/utils/aws/mime.sh 780B
  112. yolov7/utils/aws/resume.py 1.09KB
  113. yolov7/utils/aws/userdata.sh 1.22KB
  114. yolov7/utils/datasets.py 54.91KB
  115. yolov7/utils/general.py 36.01KB
  116. yolov7/utils/google_app_engine/
  117. yolov7/utils/google_app_engine/Dockerfile 821B
  118. yolov7/utils/google_app_engine/additional_requirements.txt 105B
  119. yolov7/utils/google_app_engine/app.yaml 172B
  120. yolov7/utils/google_utils.py 4.76KB
  121. yolov7/utils/loss.py 73.27KB
  122. yolov7/utils/metrics.py 9.09KB
  123. yolov7/utils/plots.py 20.43KB
  124. yolov7/utils/torch_utils.py 15.1KB
  125. yolov7/utils/wandb_logging/
  126. yolov7/utils/wandb_logging/__init__.py 6B
  127. yolov7/utils/wandb_logging/log_dataset.py 815B
  128. yolov7/utils/wandb_logging/wandb_utils.py 15.88KB

资源介绍:

论文实现 - YOLOv7：可训练的免费包为实时物体检测器树立了新标杆
# Official YOLOv7 Implementation of paper - [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://arxiv.org/abs/2207.02696) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/yolov7-trainable-bag-of-freebies-sets-new/real-time-object-detection-on-coco)](https://paperswithcode.com/sota/real-time-object-detection-on-coco?p=yolov7-trainable-bag-of-freebies-sets-new) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/yolov7) Open In Colab [![arxiv.org](http://img.shields.io/badge/cs.CV-arXiv%3A2207.02696-B31B1B.svg)](https://arxiv.org/abs/2207.02696)
## Web Demo - Integrated into [Huggingface Spaces ����](https://huggingface.co/spaces/akhaliq/yolov7) using Gradio. Try out the Web Demo [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/yolov7) ## Performance MS COCO | Model | Test Size | APtest | AP50test | AP75test | batch 1 fps | batch 32 average time | | :-- | :-: | :-: | :-: | :-: | :-: | :-: | | [**YOLOv7**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) | 640 | **51.4%** | **69.7%** | **55.9%** | 161 *fps* | 2.8 *ms* | | [**YOLOv7-X**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) | 640 | **53.1%** | **71.2%** | **57.8%** | 114 *fps* | 4.3 *ms* | | | | | | | | | | [**YOLOv7-W6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) | 1280 | **54.9%** | **72.6%** | **60.1%** | 84 *fps* | 7.6 *ms* | | [**YOLOv7-E6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) | 1280 | **56.0%** | **73.5%** | **61.2%** | 56 *fps* | 12.3 *ms* | | [**YOLOv7-D6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) | 1280 | **56.6%** | **74.0%** | **61.8%** | 44 *fps* | 15.0 *ms* | | [**YOLOv7-E6E**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt) | 1280 | **56.8%** | **74.4%** | **62.1%** | 36 *fps* | 18.7 *ms* | ## Installation Docker environment (recommended)
Expand ``` shell # create the docker container, you can change the share memory size if you have more. nvidia-docker run --name yolov7 -it -v your_coco_path/:/coco/ -v your_code_path/:/yolov7 --shm-size=64g nvcr.io/nvidia/pytorch:21.08-py3 # apt install required packages apt update apt install -y zip htop screen libgl1-mesa-glx # pip install required packages pip install seaborn thop # go to code folder cd /yolov7 ```
## Testing [`yolov7.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) [`yolov7x.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) [`yolov7-w6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) [`yolov7-e6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) [`yolov7-d6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) [`yolov7-e6e.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt) ``` shell python test.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights yolov7.pt --name yolov7_640_val ``` You will get the results: ``` Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.51206 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.69730 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.55521 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35247 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.55937 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66693 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.38453 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.63765 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.68772 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.53766 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.73549 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.83868 ``` To measure accuracy, download [COCO-annotations for Pycocotools](http://images.cocodataset.org/annotations/annotations_trainval2017.zip) to the `./coco/annotations/instances_val2017.json` ## Training Data preparation ``` shell bash scripts/get_coco.sh ``` * Download MS COCO dataset images ([train](http://images.cocodataset.org/zips/train2017.zip), [val](http://images.cocodataset.org/zips/val2017.zip), [test](http://images.cocodataset.org/zips/test2017.zip)) and [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip). If you have previously used a different version of YOLO, we strongly recommend that you delete `train2017.cache` and `val2017.cache` files, and redownload [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip) Single GPU training ``` shell # train p5 models python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml # train p6 models python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml ``` Multiple GPU training ``` shell # train p5 models python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml # train p6 models python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 128 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml ``` ## Transfer learning [`yolov7_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7_training.pt) [`yolov7x_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x_training.pt) [`yolov7-w6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6_training.pt) [`yolov7-e6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6_training.pt) [`yolov7-d6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6_training.pt) [`yolov7-e6e_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e_training.pt) Single GPU finetuning for custom dataset ``` shell # finetune p5 models python train.py --workers 8 --device 0 --batch-size 32 --data data/custom.yaml --img 640 640 --cfg cfg/training/yolov7-custom.yaml --weights 'yolov7_training.pt' --name yolov7-custom --hyp data/hyp.scratch.custom.yaml # finetune p6 models python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/custom.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6-custom.yaml --weights 'yolov7-w6_training.pt' --name yolov7-w6-custom --hyp data/hyp.scratch.custom.yaml ``` ## Re-parameterization See [reparameterization.ipynb](tools/reparameterization.ipynb) ## Inference On video: ``` shell python detect.py --weights
100+评论
captcha

    相关资源

    1. 波形生成器软件，和 示波器软件

      yishuihanq#硬件开发ZIP8.1MB7月前
      资源摘要:波形生成器软件，和 示波器软件

    2. Anaconda 安装所遇到的一系列问题

      2301_80488214#网络技术ZIP803B7月前
      资源摘要:anaconda安装需要将anaconda/scripts监测环境变量里面。安装anaconda以后使用conda指令时，不能使用清华源

    3. C++实现的高效A*算法

      2301_80488214#大数据ZIP8.12KB7月前
      资源摘要:A-Star算法这是利用C++实现的高效的A-Star算法。只对算法的程序实现做了穷尽而为的优化，并没有对算法自行进行改进。优化的主要方法是：快速判断路径节点是否在开启/关闭链表中、快速查找最小f值的节点以及优化路径节点分配内存的问题。运行环境支持c++11的编译器

    4. python反编译的脚本文件

      weixin_63279914#安全技术ZIP208.59KB7月前
      资源摘要:用cmake打包好的python反编译脚本

    5. 华硕P9X79-DELUXE bios

      2403_86677803#物联网ZIP4.78MB7月前
      资源摘要:改良最新bios

    6. 用seq2seq模型玩对联 利用深度学习对对联

      2301_80488214#人工智能ZIP24.82KB7月前
      资源摘要:用法打开couplet.py并配置文件位置和超参数。然后运行python couplet.py以训练模型。你可以在 Tensorbloard 上看到训练损失和 bleu 分数。learning_rate当你发现损失停止下降时，你可能需要重新配置。如果您停止训练并想继续训练。您可以设置restore_model为True并使用m.train(<epoches>, start=<start>)，这start是您已经运行的步骤。我已经在 Nvidia GTX-1080 GPU 上训练了该模型大约 4 天。运行经过训练的模型打开server.py并配置vocab_file和model_dir参数。然后运行python server.py将启动一个可以播放对联的web服务。或者使用 Dockerfile 构建 Docker 镜像并使用 Docker 运行它。记得将正确的模型文件路径挂载到 Docker 容器中。

    7. 自定的 Ubuntu 设置

      2301_80488214#操作系统ZIP6.99MB7月前
      资源摘要:只需运行一条命令，即可将全新安装的 Ubuntu 转变为配置齐全、美观且现代化的 Web 开发系统。这就是 Omakub 的一行宣传。无需为每个基本工具编写定制配置，只需开始使用或掌握所有最新的命令行工具即可。Omakub 是 Linux 最佳状态的坚定主张。

    8. Element Audio 插件主机

      2301_80488214#网络技术ZIP2.94MB7月前
      资源摘要:特征独立运行或作为 DAW 中的插件运行**将音频和 MIDI 从任意位置传输到任意位置现场演奏虚拟乐器和效果创建可重复使用的仪器和效果图与 MIDI 时钟进行外部同步子图 – 相互嵌套的图自定义键盘快捷键占位节点内置虚拟键盘多次撤消/重做脚本 - 自定义 DSP 和 DSP UI直接在图表中嵌入插件 UI
    站长QQ:九六九五七三七