Skip to content
Avatar

Highlights

  • Arctic Code Vault Contributor
  • Pro

Pinned

  1. PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more

    Python 4.6k 654

  2. A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

    Python 584 85

  3. Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

    Python 1.1k 150

  4. Dual Path Networks (DPN) supporting pretrained weights converted from original MXNet implementation

    Python 188 45

  5. A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

    Python 270 116

  6. A PyTorch port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

    Python 154 56

707 contributions in the last year

Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Mon Wed Fri

Contribution activity

September 2020

Created an issue in google/objax that received 9 comments

Training state as a Module attribute

As mentioned in a Twitter thread, I am curious about the decision to propagate training state through the call() chain. From my perspective this ap…

9 comments

Seeing something unexpected? Take a look at the GitHub profile guide.

You can’t perform that action at this time.