Comet.Box

KO | EN

gitlite — search

#javascript #php #ruby #python #java #puppet #c-sharp #erlang #jquery #hacktoberfest #library #logic-programming

★ 29 Open GitHub ↗

Collection of Object Detection and Segmentation Pipelines🛸🚀

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Comet.Box 📦📦

[![All Contributors](https://img.shields.io/badge/all_contributors-31-orange.svg?style=flat-square)](https://raw.githubusercontent.com/Comet-AI/Comet.Box/main/)

<img align="right" width="159px" src="https://github.com/Comet-AI/Comet.Box/blob/main/utils/comet.png">

![GitHub contributors](https://img.shields.io/github/contributors/Comet-AI/Comet.Box?style=for-the-badge)
![GitHub forks](https://img.shields.io/github/forks/Comet-AI/Comet.Box?style=social)
![GitHub issues](https://img.shields.io/github/issues/Comet-AI/Comet.Box)
[![Open Source Love svg1](https://badges.frapsoft.com/os/v1/open-source.svg?v=103)](https://github.com/ellerbrock/open-source-badges/)

### **Comet.Box:** A collection of efficient and fast implementation of SOTA Object Detection,Segementation and NLP Models.

### Why Comet.Box?

* Want to get Started with Advanced Computer Vision and NLP?
    * Comet.Box provides you a large variety of Computer Vision and NLP pipelines.
    
* Want to run high-end, the latest state-of-the-art models, but you lack GPU and RAM?
    * All implementation in Comet Box is done using Google Collab or Kaggle Kernels
    
### Some key Features!!

``` 
* Run training and inference in one place.
* All the implementation of NLP tasks is done by using Hugging Face.
* Train your model over customer data very easily.
```

### **Who can use the Comet.Box?**

🚩 Comet.Box templates are meant for those people who have intermediate knowledge of Object Detection, Segementation models, and Algorithms.

🚩 Comet.Box only provides you a basic template to kick start your initial part on any Detection, Segementation, Gans, NLP project or task. You would still need to add some custom cfg and other files according to your datasets or corpus.

## Important Elements

- A) Inference Engine
    - Original pre-trained models (from original authors and implementations) for inferencing and analyzing.
    - Pretrained models on coco, voc, cityscpaes, type datasets.
    It- Useful to analyze which algorithm works best for you.
    - Useful to generate semi-accurate annotations (coco, pascal-voc, yolo formats) on a new dataset.

## Create real-world Object Detection applications 
<table>
  <tr>
    <td>Wheat detection in field</td>
    <td>Multi-Human Pose Detection</td>
    <td>Ship Detection in Oceans on Satellite Images</td>
  </tr>
  <tr>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/predictions%20(3).jpg" width=420 height=340></td>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/Human_Pose.gif" width=420 height=340></td>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/ships.png" width=420 height=340></td>
  </tr>
    <tr>
    <td>Underwater Fish Detection</td>
      <td>Real-Time Object Detection on Crowd</td>
      <td>Real world Object Detection using Facebook DETR</td>
  </tr>
  <tr>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/fish.png" width=420 height=340></td>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/detection.gif" width=420 height=340></td>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/download (2).png" width=420 height=340></td>  
  </tr>
    <tr>
      <td>Car Detection using YoloV5</td>
      <td>Object Detection using RetinaNET</td>
      <td>Human Pose Detection using HRNET</td>
    </tr>
  <tr>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/cae_Detc.jpg" width=420 height=340></td>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/cs.jpg" width=420 height=340></td>
    <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/HRNET.gif" width=420 height=340></td>
      
  </tr>
    <tr>
      <td>Mask Detection using CNN</td>
   <td>Tiger Detection in wild using Yolov5</td>
    </tr>
     <tr>
    <td><img src="https://github.com/CoinShift-Imaging/CoinShift-Imaging-Box/blob/main/Face%20Mask%20Detection/Sample_image_1.jpg" width=420 height=340></td>
    <td><img src="https://user-images.githubusercontent.com/53366877/111144447-19958d80-85ad-11eb-9d81-5ed9e8ea23ab.gif" width=420 height=340></td>
  </tr>
    
        
</table>

## Gans and Transformer Applications
<table>
   <tr>
     <td>DeepFakes using GANS and AutoEncoders</td>
	<td>CGans on MNIST</td>
   </tr>
   <tr>
      <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/my deepfake.gif" width=420 height=340></td>
	   <td><img src="https://i.postimg.cc/FKD29bT6/digitmnist-cgan.gif" width=420 height=340></td>
  </tr>
</table>

## Real world Segmentation Models
<table>
   <tr>
     <td>Real Time Segmentation on Videos using YolACT++</td>
     <td>Medical Images Segementation using UNET</td>
     <td>Object Segmentation using Mask-RCNN</td>
   </tr>
   <tr>
      <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/yol.png" width=420 height=340></td>
      <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/unet.gif" width=420 height=340></td>
      <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/seg_obj.png" width=420 height=340></td>
      
     
  </tr>
</table>

## Classification Model's
<table>
   <tr>
     <td>COVID-19 Radiography Classification using Resnet18</td>
   </tr>
   <tr>
      <td><img src="https://github.com/CoinShift-Imaging/CoinShift-Imaging-Box/blob/main/Classification_Zoo/Sample_Image.png" width=400 height=340></td>
  </tr>
</table>

## Natural Language Processing
<table>
   <tr>
     <td>Sentence Classification using BERT Hugging Face</td>
      <td>Question/Answering using DistillBERT</td>
   </tr>
   <tr>
      <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/BERT.jpg" width=420 height=340></td>
      <td><img src="https://github.com/DARK-art108/CoinShift-Imaging/blob/main/utils/Q.png" width=420 height=340></td>
      
     
  </tr>
</table>
      
  
  ### **🧿Visit [Model Zoo DET](https://github.com/DARK-art108/CoinShift-Imaging/tree/main/Model%20Zoo%20DET) for Detection Models👓**
  ### **🧿Visit [Model Zoo SEG](https://github.com/DARK-art108/CoinShift-Imaging/tree/main/Model%20Zoo%20SEG) for Segmentation Models👓**
  ### **🧿Visit [NLP Model Zoo](https://github.com/CoinShift-Imaging/CoinShift-Imaging-Box/tree/main/NLP) for NLP SOTA Models👓**
  ### **🧿Visit [Classification Model Zoo](https://github.com/CoinShift-Imaging/CoinShift-Imaging-Box/tree/main/Classification_Zoo) for Classification Models👓**
  
  ### Want to Contribute or join us?
  
  **🚀 To contribute to Comet.Box repository raise an issue in the git-repo or dm on LinkedIn**
   - Ritesh - [Ritesh](https://www.linkedin.com/in/ritesh-yadav2011/)
   
  **📧 To Join us Shoot a mail to**
    - [Mail Here](daydreamingguy941@gmail.com)
   
### Upcoming Updates

- [ ] Detection Project:
   - [ ] ANPR
- [ ] Segmentation using:
     - [ ] Mask-RCCN
     - [ ] Detectron-2
- [ ] NLP Models
    - [x] Fine Tune BERT
    - [ ] Elmo Model
    - [x] DistilBERT
    - [ ] GPT-1 and GPT-2
- [ ] Object Tracking

### We would love to hear from you about your feedback!! 🥰

- Drop us a [Mail](daydreamingguy941@gmail.com)

## Contributors ✨

### Thanks to these wonderful people

Comet.Box

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README