yui-mhcp/detection

Object and Text detection project

😋 Yui-mhcp 😋

A centralization of Deep Learning projects

Welcome to my GitHub profile ! The objective of my projects is to make Deep Learning more accessible and practical for real-world applications ! 😋

The core mission here is to aggregate a wide range of Deep Learning topics in one place, making it easier for you to dive into this fascinating field. Each repository not only focuses on a specific area of Deep Learning, but also includes tutorials and reference links. These resources are carefully selected to help you grasp both the practical and theoretical aspects of Deep Learning, which can sometimes be challenging to find.

In addition to educational resources, I’m committed to developing and sharing open-source applications and features derived from these repositories. My aim is to showcase the versatility, fun, and utility of Deep Learning applications, even for those without access to extensive computational resources.

I encourage you to share your own Deep Learning projects, whether they’re practical tools or just for fun. By doing so, you’ll help increase their visibility and demonstrate the real-world potential of Deep Learning techniques. If your project aligns with the spirit of this initiative, I’d be thrilled to feature it here.

Moreover, if you have ideas for potential applications or interesting projects but lack the time or expertise to bring them to life, don’t hesitate to reach me out ! 😋

Covered topics

Currently developped topics :

• Image classification *
• Object detection
• Siamese networks
• Speech-To-Text (STT)
• Text-To-Speech (TTS)
• Generative Adversarial Networks (GAN)
• Object segmentation
• Natural Language Processing (NLP) : Masked Language Modeling (MLM)
• Natural Language Processing (NLP) : Question-Answering (Q&A)
• Natural Language Processing (NLP) : Text Generation
• Natural Language Processing (NLP) : Translation
• Optical Character Recognition (OCR)
• Reinforcment Learning (RL) for single-player games
• Reinforcment Learning (RL) for adversarial games

Additional utilities :

• Custom losses / metrics / callbacks
• Dataset processing / analyzing
• Plot / visualization utils
• Audio processing
• Image processing
• Text processing
• Multi-threading framework

All topics are in separate repositories so that it is easier to contribute to a particular topic without carrying about other projects

* It is a demonstration code to show how to subclass BaseModel. I will add a dedicated repository later for general classification (text / image / ...).

Available features

• Speaker Verification (SV)
• Face Recognition : the code is available but the model is not performant enough yet
• Search text in audios / videos
• Live transcription / subtitle generation : some models tend to be accurate enough for transcription but they will be further improved
• Text-To-Speech logger : logging-based logger that reads your logs with TTS models
• Optical Character Recognition (OCR) : this projects allows to detect text in an image, and performs OCR on the detected text

Available applications

Application / features ideas

Contacts and licence

Contacts :

• Mail : [email protected]
• Discord : yui0732

The goal of these projects is to enable easier development and deployment of new applications leveraging Deep Learning technology. To support this purpose, all associated code is made available under the Affero General Public License (AGPL) v3, supplemented by a clause that prohibits commercial use.

These projects are released as “free software". This classification allows you to freely utilize, modify, deploy, and share the software, provided you adhere to the terms of the License. It is important to note that while the software is freely available, it is not public domain and retains copyright protection. The distribution and usage conditions are designed to guarantee that every user have the opportunity to employ and modify any version of the code for their own projects. Additionally, the extra provision is intended to promote the development of free applications without access limitations.

If you wish to use this project into a proprietary or commercial endeavor, you should obtain a separate License. For further details on this process, please contact me directly.

For my protection, it is important to note that all projects are available on an "As Is" basis, without any warranties or conditions of any kind, either explicit or implied. However, do not hesitate to report issues on the repository's project, or make a Pull Request to solve it 😄

If you use this project in your work, please add this citation to give it more visibility ! 😋

@misc{yui-mhcp
    author  = {yui},
    title   = {A Deep Learning projects centralization},
    year    = {2021},
    publisher   = {GitHub},
    howpublished    = {\url{https://github.com/yui-mhcp}}
}

Acknowledgments

Thanks to @Ananas120 for his contribution and sharing his implementation of Transformers architectures + his master thesis' code about Q&A !