Using pre-trained models in TensorFlow | Machine Learning for web developers
Vložit
- čas přidán 28. 08. 2024
- Prototype ideas faster and save time going into production by using pre-trained models. These machine learning models have already been trained by someone else and for some cases are ready to be used for production. From object detection to sound recognition or pose estimation and body segmentation - you can do advanced things easily with TensorFlow.js pre-made models.
What are pre-trained models?
In this Google for Developers introduction, you'll discover the pre-trained models in TensorFlow that are free to use out of the box and see how to use them in just a few lines of code.
Use cases for pre-trained models:
* Audio detection and classification
* Object detection (COCO-SSD)
* Text recognition, detection, and classification
* Speech recognition
* Body segmentation and pose detection
Catch more episodes from Machine Learning for Web Developers (Web ML) → goo.gle/learn-...
Check out TensorFlow on CZcams → goo.gle/Tensor...
Subscribe to Google Developers → goo.gle/develo...
Connect with Jason Mayes to ask questions:
LinkedIn → goo.gle/3GwgeLw
Twitter →goo.gle/3Xh6MT7
Discord →goo.gle/3WWVO5t
Use #WebML to share your learnings and creations from this course to meet your peers on social media!
See what others have already made with Web ML → goo.gle/made-wi...
Catch more episodes from Machine Learning for Web Developers (Web ML) → goo.gle/learn-WebML
The video mentions clickable links in the description, at around 15:00, but I don't see the links to the models in the description.
Thank you for this easy to follow introduction.
The examples, invisibility, teleportation, and lasers, are amazing. Very inspiring!
Thank you 🙏
Unfortunately demo at 2:19 is no longer working demo, I guess latest version need more input data, otherwise it returns empty array
Can you submit a bug report on the tfjs GitHub for this?
Fantastic technology!
Top demais obrigado pela informação cada dia melhor Google a maior empresa do mundo 😎🤜🤛 tamos juntos
Gracias Fabio! 🙏
Trying first example... and not working. Does it make sense to view the rest of the course?
Saya suka app ini berguna
I tried testing the "Text Toxicity Detection" model but I am too polite for that
огромная благодарность! инфа, огонь.💮
Many of the tfjs examples and models do not work out-of-the-box - a lot of environmental setup is needed for these to work (eg. node-gyp config) and even then, some of these projects simply don't work. This would be a much better course if you had just a few projects that worked and provided a separate module on the complete set up. This really detracts from what is otherwise a well-prepared series.
This course is designed for front end development not Node examples per se, though some will work in Node too.
nice!
Cheers glad you are enjoying the course! Check the playlist for latest videos! 4 more chapters to come out soon!
However, your simple example took 30sec, and could not answer :/ 2:19
👌
How does chatgpt use this type of pre trained model
There white paper for gpt-3 tells all, but it’s just larger and more refined than sandboxed refined and sandboxed again😂 it’s pretty lame actually, you can find a unfiltered version hosted in India but that’s all I can say because I’ll get banned again 😮
Excuse me sir, what is that device in the background with the social media logos and numbers?
It's just an LED clock
0:30
Great tutorial but unfortunately the demos provided in the GitHub does not work. They are either outdated or broken. Typical JS dependencies ecosystem bullshit.
สวัสดีครับ