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
ResNet50 checkpoints (PaddlePaddle, AMP, ImageNet)
Model
NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
ResNet50 checkpoints (PaddlePaddle, AMP, ImageNet)

ResNet50 checkpoint trained with AMP on ImageNet

1 Version
22.05.0_ampSelected
06/07/2022 12:36 PM UTC197.47 MBAccuracy: 090 EpochsBatch Size: 256GPU: A100
architecture
KeyValue
taskclassification
typeresnet50
performance
KeyValue
val_top177.1185427
val_top593.2955994
training
KeyValue
batch_size256
weight_decay3.0517578125e-05
num_classes1000
lr2.048
optimizer_batch_size2048
archresnet50
lr_schedulecosine
datasetImageNet
epochs90
warmup5
label_smoothing0.1
momentum0.875