Mingxing Tan

@tanmingxing

Google Brain

Vrijeme pridruživanja: listopad 2013.

Medijski sadržaj

  1. 25. stu 2019.

    Can adversarial examples improve image recognition? Check out our recent work: AdvProp, achieving ImageNet top-1 accuracy 85.5% (no extra data) with adversarial examples! Arxiv: Checkpoints:

  2. 6. kol 2019.

    Introducing EfficientNet-EdgeTPU: customized for mobile accelerators, with higher accuracy and 10x faster inference speed. blog post: Code and pertained models:

  3. 24. srp 2019.

    Introducing MixNet: AutoML + a new mixed depthwise conv (MDConv). SOTA results for mobile: 78.9% ImageNet top-1 accuracy under typical mobile settings (<600M FLOPS). Paper: Code & models:

  4. 29. svi 2019.
    Odgovor korisnicima

    Hi Andrej, here you go (Figure 8 in arxiv paper: ).

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:

    ·