{ "id": 297534, "title": "YOLOX resources for beginners", "url": "/competitions/tensorflow-great-barrier-reef/discussion/297534", "author_name": "", "post_date": "2021-12-27T22:30:48.883177800Z", "votes": 16, "comment_count": 2, "views": 0, "content": "

I have learnt a lot from @remekkinas. Many, many, many thanks for sharing your notebooks, knowledge and time on YOLOX implementation. 🙏🏽

\n

I have also found the following really useful and wanted to share it. 🤝🏽

\n
\n

YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. With this version of YOLO, the authors won the 1st Place on Stream Perception Challenge (Workshop on Autonomous Driving at CVPR 2021.

\n
\n

Source Code: https://github.com/Megvii-BaseDetection/YOLOX
\nYOLOX paper: https://arxiv.org/abs/2107.08430v2
\nUseful Blog/Article: https://aicurious.io/posts/papers-yolox/
\nUseful Blog/Article: https://www.forecr.io/blogs/ai-algorithms/how-to-train-a-custom-object-detection-model-with-yolox

\n

Hope this helps Kagglers trying to understand YOLOX a bit better 😊

", "messages": [ { "id": "1630975", "postDate": "12/27/2021 22:30:48", "content": "

I have learnt a lot from @remekkinas. Many, many, many thanks for sharing your notebooks, knowledge and time on YOLOX implementation. 🙏🏽

\n

I have also found the following really useful and wanted to share it. 🤝🏽

\n
\n

YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. With this version of YOLO, the authors won the 1st Place on Stream Perception Challenge (Workshop on Autonomous Driving at CVPR 2021.

\n
\n

Source Code: https://github.com/Megvii-BaseDetection/YOLOX
\nYOLOX paper: https://arxiv.org/abs/2107.08430v2
\nUseful Blog/Article: https://aicurious.io/posts/papers-yolox/
\nUseful Blog/Article: https://www.forecr.io/blogs/ai-algorithms/how-to-train-a-custom-object-detection-model-with-yolox

\n

Hope this helps Kagglers trying to understand YOLOX a bit better 😊

", "rawMarkdown": "I have learnt a lot from @remekkinas. Many, many, many thanks for sharing your notebooks, knowledge and time on YOLOX implementation. 🙏🏽\n\nI have also found the following really useful and wanted to share it. 🤝🏽\n\n> YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. With this version of YOLO, the authors won the 1st Place on Stream Perception Challenge (Workshop on Autonomous Driving at CVPR 2021. \n\nSource Code: https://github.com/Megvii-BaseDetection/YOLOX\nYOLOX paper: https://arxiv.org/abs/2107.08430v2\nUseful Blog/Article: https://aicurious.io/posts/papers-yolox/\nUseful Blog/Article: https://www.forecr.io/blogs/ai-algorithms/how-to-train-a-custom-object-detection-model-with-yolox\n\nHope this helps Kagglers trying to understand YOLOX a bit better 😊", "votes": null }, { "id": "1630976", "postDate": "12/27/2021 22:37:35", "content": "

Thank you very much @gavisr for mentioning me and my notebooks. This is the best I can get from you. Thank you! 😁
\nI will introduce some changes to Yx soon (till end of this week) … Hope you like it and benefit from it. Have a good competition and score. 👍

", "rawMarkdown": "Thank you very much @gavisr for mentioning me and my notebooks. This is the best I can get from you. Thank you! 😁\nI will introduce some changes to Yx soon (till end of this week) ... Hope you like it and benefit from it. Have a good competition and score. 👍", "votes": null }, { "id": "1630982", "postDate": "12/27/2021 22:49:28", "content": "

You've been a superstar ⭐! Thank you again for sharing knowledge.

", "rawMarkdown": "You've been a superstar ⭐! Thank you again for sharing knowledge.", "votes": null } ], "comments": [ { "id": 1630976, "author_name": "remekkinas", "author_url": "", "post_date": "12/27/2021 22:37:35", "content": "

Thank you very much @gavisr for mentioning me and my notebooks. This is the best I can get from you. Thank you! 😁
\nI will introduce some changes to Yx soon (till end of this week) … Hope you like it and benefit from it. Have a good competition and score. 👍

", "votes": null, "replies": [ { "id": 1630982, "author_name": "gavisr", "author_url": "", "post_date": "12/27/2021 22:49:28", "content": "

You've been a superstar ⭐! Thank you again for sharing knowledge.

", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "1630975": "I have learnt a lot from @remekkinas. Many, many, many thanks for sharing your notebooks, knowledge and time on YOLOX implementation. 🙏🏽\n\nI have also found the following really useful and wanted to share it. 🤝🏽\n\n> YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. With this version of YOLO, the authors won the 1st Place on Stream Perception Challenge (Workshop on Autonomous Driving at CVPR 2021. \n\nSource Code: https://github.com/Megvii-BaseDetection/YOLOX\nYOLOX paper: https://arxiv.org/abs/2107.08430v2\nUseful Blog/Article: https://aicurious.io/posts/papers-yolox/\nUseful Blog/Article: https://www.forecr.io/blogs/ai-algorithms/how-to-train-a-custom-object-detection-model-with-yolox\n\nHope this helps Kagglers trying to understand YOLOX a bit better 😊", "1630976": "Thank you very much @gavisr for mentioning me and my notebooks. This is the best I can get from you. Thank you! 😁\nI will introduce some changes to Yx soon (till end of this week) ... Hope you like it and benefit from it. Have a good competition and score. 👍", "1630982": "You've been a superstar ⭐! Thank you again for sharing knowledge." }, "source": "meta" }