yolov2、4,pspnet.yolo3——pytorch.zip

  • n7_945849
    了解作者
  • 7.8MB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • VIP专享
    资源类型
  • 0
    下载次数
  • 2022-05-27 08:05
    上传日期
yolov2、4,pspnet.论文 yolo3——pytorch.zip代码实现
yolov2、4,pspnet.yolo3——pytorch.zip
  • pspnet.pdf
    999.6KB
  • yolov3_pytorch
  • Dockerfile
    2.5KB
  • .gitignore
    3.7KB
  • README.md
    16.5KB
  • utils
  • parse_config.py
    2.3KB
  • google_utils.py
    2.5KB
  • gcp.sh
    10.2KB
  • adabound.py
    11.1KB
  • datasets.py
    33.3KB
  • utils.py
    39.5KB
  • torch_utils.py
    6.5KB
  • __init__.py
    0B
  • .github
  • ISSUE_TEMPLATE
  • --feature-request.md
    742B
  • --bug-report.md
    702B
  • test.py
    9.3KB
  • models.py
    20.2KB
  • cfg
  • yolov3-spp-3cls.cfg
    8.4KB
  • csresnext50-panet-spp.cfg
    10.4KB
  • yolov3-spp.cfg
    8.4KB
  • yolov3-tiny.cfg
    1.9KB
  • yolov3-1cls.cfg
    8.1KB
  • yolov3-spp3.cfg
    8.7KB
  • yolov3.cfg
    8.1KB
  • yolov3-tiny-1cls.cfg
    1.9KB
  • yolov3s.cfg
    8.4KB
  • yolov3-tiny-3cls.cfg
    1.9KB
  • yolov3-spp-1cls.cfg
    8.4KB
  • yolov3-spp-matrix.cfg
    13.1KB
  • yolov3-spp-pan-scale.cfg
    10.3KB
  • train.py
    23.5KB
  • LICENSE
    34.3KB
  • .dockerignore
    3.6KB
  • .ipynb_checkpoints
  • examples-checkpoint.ipynb
    858.1KB
  • requirements.txt
    845B
  • detect.py
    7KB
  • examples.ipynb
    738.3KB
  • weights
  • download_yolov3_weights.sh
    896B
  • data
  • coco64.txt
    2.6KB
  • coco2017.data
    87B
  • coco64.data
    77B
  • coco2014.data
    85B
  • coco1cls.data
    80B
  • coco16.data
    77B
  • coco16.txt
    672B
  • get_coco2017.sh
    871B
  • get_coco2014.sh
    872B
  • coco1.txt
    42B
  • coco1.data
    75B
  • coco.names
    621B
  • coco1cls.txt
    672B
  • coco_paper.names
    702B
  • samples
  • zidane.jpg
    165KB
  • bus.jpg
    476KB
  • yolov2.pdf
    1.5MB
  • yolov4.pdf
    3.8MB
内容介绍
<table style="width:100%"> <tr> <td> <img src="https://user-images.githubusercontent.com/26833433/61591130-f7beea00-abc2-11e9-9dc0-d6abcf41d713.jpg"> </td> <td align="center"> <a href="https://www.ultralytics.com" target="_blank" rel='nofollow' onclick='return false;'> <img src="https://storage.googleapis.com/ultralytics/logo/logoname1000.png" width="160"></a> <img src="https://user-images.githubusercontent.com/26833433/61591093-2b4d4480-abc2-11e9-8b46-d88eb1dabba1.jpg"> <a href="https://itunes.apple.com/app/id1452689527" target="_blank" rel='nofollow' onclick='return false;'> <img src="https://user-images.githubusercontent.com/26833433/50044365-9b22ac00-0082-11e9-862f-e77aee7aa7b0.png" width="180"></a> </td> <td> <img src="https://user-images.githubusercontent.com/26833433/61591100-55066b80-abc2-11e9-9647-52c0e045b288.jpg"> </td> </tr> </table> # Introduction This directory contains PyTorch YOLOv3 software developed by Ultralytics LLC, and **is freely available for redistribution under the GPL-3.0 license**. For more information please visit https://www.ultralytics.com. # Description The https://github.com/ultralytics/yolov3 repo contains inference and training code for YOLOv3 in PyTorch. The code works on Linux, MacOS and Windows. Training is done on the COCO dataset by default: https://cocodataset.org/#home. **Credit to Joseph Redmon for YOLO:** https://pjreddie.com/darknet/yolo/. # Requirements Python 3.7 or later with the following `pip3 install -U -r requirements.txt` packages: - `numpy` - `torch >= 1.1.0` - `opencv-python` - `tqdm` # Tutorials * [GCP Quickstart](https://github.com/ultralytics/yolov3/wiki/GCP-Quickstart) * [Transfer Learning](https://github.com/ultralytics/yolov3/wiki/Example:-Transfer-Learning) * [Train Single Image](https://github.com/ultralytics/yolov3/wiki/Example:-Train-Single-Image) * [Train Single Class](https://github.com/ultralytics/yolov3/wiki/Example:-Train-Single-Class) * [Train Custom Data](https://github.com/ultralytics/yolov3/wiki/Train-Custom-Data) # Jupyter Notebook Our Jupyter [notebook](https://colab.research.google.com/github/ultralytics/yolov3/blob/master/examples.ipynb) provides quick training, inference and testing examples. # Training **Start Training:** `python3 train.py` to begin training after downloading COCO data with `data/get_coco_dataset.sh`. Each epoch trains on 117,263 images from the train and validate COCO sets, and tests on 5000 images from the COCO validate set. **Resume Training:** `python3 train.py --resume` to resume training from `weights/last.pt`. **Plot Training:** `from utils import utils; utils.plot_results()` plots training results from `coco_16img.data`, `coco_64img.data`, 2 example datasets available in the `data/` folder, which train and test on the first 16 and 64 images of the COCO2014-trainval dataset. <img src="https://user-images.githubusercontent.com/26833433/63258271-fe9d5300-c27b-11e9-9a15-95038daf4438.png" width="900"> ## Image Augmentation `datasets.py` applies random OpenCV-powered (https://opencv.org/) augmentation to the input images in accordance with the following specifications. Augmentation is applied **only** during training, not during inference. Bounding boxes are automatically tracked and updated with the images. 416 x 416 examples pictured below. Augmentation | Description --- | --- Translation | +/- 10% (vertical and horizontal) Rotation | +/- 5 degrees Shear | +/- 2 degrees (vertical and horizontal) Scale | +/- 10% Reflection | 50% probability (horizontal-only) H**S**V Saturation | +/- 50% HS**V** Intensity | +/- 50% <img src="https://user-images.githubusercontent.com/26833433/66699231-27beea80-ece5-11e9-9cad-bdf9d82c500a.jpg" width="900"> ## Speed https://cloud.google.com/deep-learning-vm/ **Machine type:** preemptible [n1-standard-16](https://cloud.google.com/compute/docs/machine-types) (16 vCPUs, 60 GB memory) **CPU platform:** Intel Skylake **GPUs:** K80 ($0.20/hr), T4 ($0.35/hr), V100 ($0.83/hr) CUDA with [Nvidia Apex](https://github.com/NVIDIA/apex) FP16/32 **HDD:** 1 TB SSD **Dataset:** COCO train 2014 (117,263 images) **Model:** `yolov3-spp.cfg` **Command:** `python3 train.py --img 416 --batch 32 --accum 2` GPU |n| `--batch --accum` | img/s | epoch<br>time | epoch<br>cost --- |--- |--- |--- |--- |--- K80 |1| 32 x 2 | 11 | 175 min | $0.58 T4 |1<br>2| 32 x 2<br>64 x 1 | 41<br>61 | 48 min<br>32 min | $0.28<br>$0.36 V100 |1<br>2| 32 x 2<br>64 x 1 | 122<br>**178** | 16 min<br>**11 min** | **$0.23**<br>$0.31 2080Ti |1<br>2| 32 x 2<br>64 x 1 | 81<br>140 | 24 min<br>14 min | -<br>- # Inference `detect.py` runs inference on any sources: ```bash python3 detect.py --source ... ``` - Image: `--source file.jpg` - Video: `--source file.mp4` - Directory: `--source dir/` - Webcam: `--source 0` - RTSP stream: `--source rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa` - HTTP stream: `--source http://wmccpinetop.axiscam.net/mjpg/video.mjpg` To run a specific models: **YOLOv3:** `python3 detect.py --cfg cfg/yolov3.cfg --weights yolov3.weights` <img src="https://user-images.githubusercontent.com/26833433/64067835-51d5b500-cc2f-11e9-982e-843f7f9a6ea2.jpg" width="500"> **YOLOv3-tiny:** `python3 detect.py --cfg cfg/yolov3-tiny.cfg --weights yolov3-tiny.weights` <img src="https://user-images.githubusercontent.com/26833433/64067834-51d5b500-cc2f-11e9-9357-c485b159a20b.jpg" width="500"> **YOLOv3-SPP:** `python3 detect.py --cfg cfg/yolov3-spp.cfg --weights yolov3-spp.weights` <img src="https://user-images.githubusercontent.com/26833433/64067833-51d5b500-cc2f-11e9-8208-6fe197809131.jpg" width="500"> # Pretrained Weights Download from: [https://drive.google.com/open?id=1LezFG5g3BCW6iYaV89B2i64cqEUZD7e0](https://drive.google.com/open?id=1LezFG5g3BCW6iYaV89B2i64cqEUZD7e0) ## Darknet Conversion ```bash $ git clone https://github.com/ultralytics/yolov3 && cd yolov3 # convert darknet cfg/weights to pytorch model $ python3 -c "from models import *; convert('cfg/yolov3-spp.cfg', 'weights/yolov3-spp.weights')" Success: converted 'weights/yolov3-spp.weights' to 'converted.pt' # convert cfg/pytorch model to darknet weights $ python3 -c "from models import *; convert('cfg/yolov3-spp.cfg', 'weights/yolov3-spp.pt')" Success: converted 'weights/yolov3-spp.pt' to 'converted.weights' ``` # mAP ```bash python3 test.py --weights ... --cfg ... ``` - mAP@0.5 run at `--nms-thres 0.5`, mAP@0.5...0.95 run at `--nms-thres 0.7` - YOLOv3-SPP ultralytics is `ultralytics68.pt` with `yolov3-spp.cfg` - Darknet results: https://arxiv.org/abs/1804.02767 <i></i> |Size |COCO mAP<br>@0.5...0.95 |COCO mAP<br>@0.5 --- | --- | --- | --- YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |320 |14.0<br>28.7<br>30.5<br>**35.4** |29.1<br>51.8<br>52.3<br>**54.3** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |416 |16.0<br>31.2<br>33.9<br>**39.0** |33.0<br>55.4<br>56.9<br>**59.2** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |512 |16.6<br>32.7<br>35.6<br>**40.3** |34.9<br>57.7<br>59.5<br>**60.6** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |608 |16.6<br>33.1<br>37.0<br>**40.9** |35.4<br>58.2<br>60.7<br>**60.9** ```bash $ python3 test.py --save-json --img-size 608 --nms-thres 0.5 --weights ultralytics68.pt Namespace(batch_size=16, cfg='cfg/yolov3-spp.cfg', conf_thres=0.001, data='data/coco.data', device='1', img_size=608, iou_thres=0.5, nms_thres=0.7, save_json=True, weights='ultralytics68.pt') Using CUDA device0 _CudaDeviceProperties(name='GeForce RTX 2080 Ti', total_memory=11019MB) Class Images Targets P R mAP@0.5 F1: 100%|███████████████████████████████████████████████████████████████████████████�
评论
    相关推荐
    • pytorch
      火炬
    • Pytorch
      Pytorch
    • pytorch
      :alien_monster: PyTorch变形金刚 PyTorch-Transformers(以前称为pytorch-pretrained-bert )是用于自然语言处理(NLP)的最先进的预训练模型库。 该库当前包含以下模型的PyTorch实现,预训练的模型权重,使用脚本...
    • pytorch4.4.0轮子
      torch-1.4.0-cp36-cp36m-win_amd64.whl torchvision-0.5.0-cp36-cp36m-win_amd64.whl Win+R键进入命令行窗口,切换当前目录至上述资解压目录 输入命令pip install torch-1.4.0-cp36-cp36m-...进行安装pytorch1.4.0版本
    • dbn pytorch
      主要使用pytorch 实现的DBN网络,用于对数据做回归,单个数据维度为(N,21),其中N为不定长,输出则为(N,1),对应N个值
    • pytorch
      pytorch
    • PYTORCH_project
      火炬 pytorch_intro1: : v 8PnxJ3s3Cwo list PLHOsBEAyYj3xf4i20sCA5o8MgVW5sIiHD index pytorch_intro2: : v EMXfZB8FVUA list PLqnslRFeH2UrcDBWF5mfPGpqQDSta6VK4 씨이발다
    • pytorch教程
      pytorch教程 这是udacity的pytorch免费课程笔记本的存储库
    • pytorch
      pytorch
    • Pytorch
      火炬 该存储库用于学习pytorch所有概念均面向深度学习