Jan Kautz

@jankautz

Computer vision, deep learning, and more...

Boston
Vrijeme pridruživanja: lipanj 2011.

Tweetovi

Blokirali ste korisnika/cu @jankautz

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

  1. proslijedio/la je Tweet
    2. sij

    Selecting the right data for training can be a massive undertaking. Learn how active learning can streamline the process with greater precision than manual data curation:

    Poništi
  2. 30. pro 2019.

    OpenCV now supports hardware-accelerated optical flow on Turing GPUs:

    Poništi
  3. proslijedio/la je Tweet

    Learn how to easily build an accurate, fine-tuned ASR model on GPUs using Neural Modules (NeMo) toolkit in this walkthrough + notebook.

    Poništi
  4. proslijedio/la je Tweet
    18. pro 2019.

    very excited to share UNAS, my first project . UNAS unifies differentiable and RL-based NAS, enabling us to search with both diff. & non-diff. loss. UNAS also proposes a generalization based loss to discover networks prone to overfitting. paper:

    Prikaži ovu nit
    Poništi
  5. 3. pro 2019.

    Excited to share that won the Magazine’s “Best of What’s New Award” in the engineering category.

    Poništi
  6. proslijedio/la je Tweet
    13. stu 2019.

    Research efforts in computer vision and are on the rise. To accelerate 3D research, NVIDIA releases Kaolin as a PyTorch library. See how researchers use Kaolin to move 3D models into the realm of neural networks.

    Poništi
  7. proslijedio/la je Tweet
    7. stu 2019.

    Inference is a complex challenge, but NVIDIA posted the top results on the new benchmarks, measuring the performance of inference workloads in data centers and at the edge. Learn more:

    Poništi
  8. proslijedio/la je Tweet
    3. stu 2019.

    When people ask me what is the future of painting or brushes, I tell This is. This shows the power of and working together to enhance human creativity. I extracted and processed the video using the SPADE algorithm and augmented it on the feed.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    31. lis 2019.

    We will be doing a poster session for our paper on FUNIT: Few-shot Unsupervised Image-to-Image Translation () at Hall 1B. Poster 139. Hope to see you there.

    Poništi
  10. proslijedio/la je Tweet

    AI pet-swapping app shows you what your dog would look like as a bear

    Poništi
  11. proslijedio/la je Tweet
    28. lis 2019.

    Temporal cycle consistency for unsupervised video interpolation. We use them to adapt, improve and distill pre-trained interpolation models in unseen domains with no additional high FPS data from the target domain. With , presenting at

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet

    In this post, shares two lines of code that tripled training speed for using mixed precision on .

    Poništi
  13. 24. lis 2019.

    Join us at the emerging AI technologies session at , where I’ll be talking about how to use AI to synthesize data, such as images and videos.

    Poništi
  14. proslijedio/la je Tweet
    23. lis 2019.

    Best explanation I've seen yet of this relative color phenomena. I had to take it into Photoshop to trust the image...it is correct.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet

    Announced today at - NVIDIA Jarvis, an SDK for building and deploying applications that fuse vision, speech and other sensors to enable conversation-based experiences that are natural, engaging and accurate. Apply for early access today:

    Poništi
  16. proslijedio/la je Tweet
    21. lis 2019.

    You can now simplify deployment at the edge, on hybrid, on-prem, and in the cloud, with the new GPU Operator, Helm charts, and NGC-Ready edge systems.

    Poništi
  17. proslijedio/la je Tweet
    4. lis 2019.

    We're headed to Mobile World Congress LA. Join us for a keynote address with CEO Jensen Huang on 10/21. :

    Poništi
  18. 3. lis 2019.

    Great to see ’s being used as a “creative partner” in digital art.

    Poništi
  19. 26. ruj 2019.

    NVIDIA announced RTX broadcast today, which uses to bring advanced features to live streaming.

    Poništi
  20. proslijedio/la je Tweet
    17. ruj 2019.

    What blows me away is the performance of . It's so fast, you don't even see it on the chart... >2000x faster on the GPlus dataset. Plus, it's now multi-gpu and scales to 300GB on the largest machines. Great work !

    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:

    ·