Skip to main content
ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • NVIDIA Deep Learning Examples
    ResNet50 v1.5 for PyTorch
    Resource
    NVIDIA Deep Learning Examples
    ResNet50 v1.5 for PyTorch

    With modified architecture and initialization this ResNet50 version gives ~0.5% better accuracy than original.

  • Changelog

    1. September 2018
    • Initial release
    1. January 2019
    • Added options Label Smoothing, fan-in initialization, skipping weight decay on batch norm gamma and bias.
    1. May 2019
    • Cosine LR schedule
    • MixUp regularization
    • DALI support
    • DGX2 configurations
    • gradients accumulation
    1. July 2019
    • DALI-CPU dataloader
    • Updated README
    1. July 2020
    • Added A100 scripts
    • Updated README
    1. February 2021
    • Moved from APEX AMP to Native AMP

    Known issues

    There are no known issues with this model.