Abhilashvj/planogram-compliance

1---2sdk: streamlit3sdk_version: 1.10.0 # The latest supported version4app_file: app.py5pinned: false6fullWidth: True7---8## <div align="center">Planogram Scoring</div>9<p>10 11</p>12- Train a Yolo Model on the available products in our data base to detect them on a shelf13- https://wandb.ai/abhilash001vj/YOLOv5/runs/1v6yh7nk?workspace=user-abhilash001vj14- Have the master planogram data captured as a matrix of products encoded as numbers (label encoding by looking the products names saved in a  list of all - the available product names )15- Detect the products on real images from stores.16- Arrange the detected products in the captured photograph to rows and columns 17- Compare the product arrangement of captured photograph to the existing master planogram and produce the compliance score for correctly placed products18 19</div>20 21## <div align="center">YOLOv5</div>22<p>23YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents <a href="https://ultralytics.com">Ultralytics</a>24 open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.25</p>26 27</div>28 29## <div align="center">Documentation</div>30 31See the [YOLOv5 Docs](https://docs.ultralytics.com) for full documentation on training, testing and deployment.32 33## <div align="center">Quick Start Examples</div>34 35<details open>36<summary>Install</summary>37 38[**Python>=3.6.0**](https://www.python.org/) is required with all39[requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) installed including40[**PyTorch>=1.7**](https://pytorch.org/get-started/locally/):41<!-- $ sudo apt update && apt install -y libgl1-mesa-glx libsm6 libxext6 libxrender-dev -->42 43```bash44$ git clone https://github.com/ultralytics/yolov545$ cd yolov546$ pip install -r requirements.txt47```48 49</details>50 51<details open>52<summary>Inference</summary>53 54Inference with YOLOv5 and [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36). Models automatically download55from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases).56 57```python58import torch59 60# Model61model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, custom62 63# Images64img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list65 66# Inference67results = model(img)68 69# Results70results.print()  # or .show(), .save(), .crop(), .pandas(), etc.71```72 73</details>74 75 76## <div align="center">Why YOLOv5</div>77 78<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/114313216-f0a5e100-9af5-11eb-8445-c682b60da2e3.png"></p>79<details>80  <summary>YOLOv5-P5 640 Figure (click to expand)</summary>81 82<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/114313219-f1d70e00-9af5-11eb-9973-52b1f98d321a.png"></p>83</details>84<details>85  <summary>Figure Notes (click to expand)</summary>86 87* GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size88  32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS.89* EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8.90* **Reproduce** by91  `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`92 93</details>94 95### Pretrained Checkpoints96 97[assets]: https://github.com/ultralytics/yolov5/releases98 99|Model |size<br><sup>(pixels) |mAP<sup>val<br>0.5:0.95 |mAP<sup>test<br>0.5:0.95 |mAP<sup>val<br>0.5 |Speed<br><sup>V100 (ms) | |params<br><sup>(M) |FLOPs<br><sup>640 (B)100|---                    |---  |---      |---      |---      |---     |---|---   |---101|[YOLOv5s][assets]      |640  |36.7     |36.7     |55.4     |**2.0** |   |7.3   |17.0102|[YOLOv5m][assets]      |640  |44.5     |44.5     |63.1     |2.7     |   |21.4  |51.3103|[YOLOv5l][assets]      |640  |48.2     |48.2     |66.9     |3.8     |   |47.0  |115.4104|[YOLOv5x][assets]      |640  |**50.4** |**50.4** |**68.8** |6.1     |   |87.7  |218.8105|                       |     |         |         |         |        |   |      |106|[YOLOv5s6][assets]     |1280 |43.3     |43.3     |61.9     |**4.3** |   |12.7  |17.4107|[YOLOv5m6][assets]     |1280 |50.5     |50.5     |68.7     |8.4     |   |35.9  |52.4108|[YOLOv5l6][assets]     |1280 |53.4     |53.4     |71.1     |12.3    |   |77.2  |117.7109|[YOLOv5x6][assets]     |1280 |**54.4** |**54.4** |**72.0** |22.4    |   |141.8 |222.9110|                       |     |         |         |         |        |   |      |111|[YOLOv5x6][assets] TTA |1280 |**55.0** |**55.0** |**72.0** |70.8    |   |-     |-112 113<details>114  <summary>Table Notes (click to expand)</summary>115 116* AP<sup>test</sup> denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results117  denote val2017 accuracy.118* AP values are for single-model single-scale unless otherwise noted. **Reproduce mAP**119  by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`120* Speed<sub>GPU</sub> averaged over 5000 COCO val2017 images using a121  GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) V100 instance, and122  includes FP16 inference, postprocessing and NMS. **Reproduce speed**123  by `python val.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45 --half`124* All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation).125* Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) includes reflection and scale126  augmentation. **Reproduce TTA** by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`127 128</details>129 130## <div align="center">Contribute</div>131 132We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible. Please see133our [Contributing Guide](CONTRIBUTING.md) to get started.134 135## <div align="center">Contact</div>136 137For issues running YOLOv5 please visit [GitHub Issues](https://github.com/ultralytics/yolov5/issues). For business or138professional support requests please visit [https://ultralytics.com/contact](https://ultralytics.com/contact).139 140<br>141 142<div align="center">143    <a href="https://github.com/ultralytics">144        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-github.png" width="3%"/>145    </a>146    <img width="3%" />147    <a href="https://www.linkedin.com/company/ultralytics">148        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-linkedin.png" width="3%"/>149    </a>150    <img width="3%" />151    <a href="https://twitter.com/ultralytics">152        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-twitter.png" width="3%"/>153    </a>154    <img width="3%" />155    <a href="https://youtube.com/ultralytics">156        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-youtube.png" width="3%"/>157    </a>158    <img width="3%" />159    <a href="https://www.facebook.com/ultralytics">160        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-facebook.png" width="3%"/>161    </a>162    <img width="3%" />163    <a href="https://www.instagram.com/ultralytics/">164        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-instagram.png" width="3%"/>165    </a>166</div>167