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
NVIDIA Deep Learning Examples
GPUNet-2 pretrained weights (PyTorch, AMP, ImageNet)
Model
NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
GPUNet-2 pretrained weights (PyTorch, AMP, ImageNet)

GPUNet-2 ImageNet pretrained weights

1 Version
21.12.0_ampSelected
05/10/2022 7:56 PM UTC395.09 MBAccuracy: 0450 EpochsBatch Size: 128GPU: V100
architecture
KeyValue
typegpunet_2
performance
KeyValue
val_top182.226
val_top595.966
training
KeyValue
aarand-m9-mstd0.5
drop0.3
drop_connect0.2
batch_size128
ampTrue
decay_epochs2.4
lr0.068
crop_pct1.0
img_size384
epochs450
decay_rate0.97
data_dir/data/imagenet