Weights & Biases

@weights_biases

Building the future of ML. Head to to improve ML model performance, track training progress, & collaborate on results. 🤓🏋️‍♀️

Vrijeme pridruživanja: svibanj 2018.

Tweetovi

Blokirali ste korisnika/cu @weights_biases

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @weights_biases

  1. Poništi
  2. 3. velj

    Today we show you how you can get up and running with W&B in a GCP instance, so you can start tracking your model experiments like a pro.

    Poništi
  3. 2. velj

    If you're curious about training models in , we wrote a quick walkthrough using with way too many comments. Enjoy! 🎃

    Poništi
  4. 2. velj

    Today Nick from W&B shows you how to visualize and share your 3D point clouds with just a few lines of code. This is super useful for debugging your self driving models & any others trained on point clouds.

    Poništi
  5. 1. velj

    We ❤️ the open source community. So we built anonymous mode to make your ML workflow easier! With one line of code, W&B will keep track your experiments+metrics, so you can focus on building groundbreaking models!

    Poništi
  6. proslijedio/la je Tweet
    31. sij

    from discusses the excitement, problems, and opportunities for deep learning in the real-world at

    Poništi
  7. 31. sij
    Poništi
  8. 30. sij

    We're on Product Hunt today! 🥳 After months of hard work, we’re excited to share Sweeps with all of the world! We'd love for you to check it out, & give it an upvote & comment if you like what you see. 🙂

    Poništi
  9. 29. sij

    If you want to learn how to generate movie scripts, recipes, code and everything in between using LSTMs and GRUs we highly recommend this class by ! Video: Code:

    Poništi
  10. 28. sij

    One of the students in our applied deep learning class took a GPT-2 model and used it to generate domain names - the results are pretty incredible.

    Poništi
  11. proslijedio/la je Tweet
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    27. sij

    Nice initiative. Looking forward to nerd DL out.

    Poništi
  13. 27. sij

    Could the human strategy of learning by progressively increasing specificity or difficulty, known as curriculum learning, benefit a neural network?

    Poništi
  14. proslijedio/la je Tweet
    26. sij
    Poništi
  15. proslijedio/la je Tweet
    26. sij

    If you're doing ML & need a community of people to nerd out with – W&B Forum is it. We have folks entering & winning hackathons together, getting help on weekend projects, talking shop. It's a great time🥰

    Prikaži ovu nit
    Poništi
  16. 26. sij
    Poništi
  17. 25. sij

    Let us do the gnarly parts of your Machine Learning work for you. Learn how to keep track of your experiments with just a few lines of code with Weights & Biases.

    Poništi
  18. 25. sij

    Today we show you how to do object detection with RetinaNet and find your best performing model using Weights & Biases.

    Poništi
  19. proslijedio/la je Tweet
    24. sij

    Hi guys, Catalyst is 1 year old today, Thank you for your support! ❤️ ``` pip install catalyst ``` Break the cycle - use the Catalyst!🚀

    Poništi
  20. proslijedio/la je Tweet
    23. sij

    THANK YOU to our day 2 Presenting Sponsor: . It was great working with you!

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·