wehub/mrdbourke--pytorch-deep-learning
1
0
Fork 0
Code Issues Pull Requests Actions 1 Deployments Packages Projects Releases Wiki Activity
Files
main
mrdbourke--pytorch-deep-lea…/extras/pytorch_2_results
T
History

README.md

PyTorch 2.0 Brief Testing Results

Setup

  • Model: ResNet50 (from TorchVision)
  • Data: CIFAR10 (from TorchVision)
  • Epochs: 5 (single run) and 3x 5 (multiple runs)
  • Batch size: 128
  • Image size: 224

See full code in the PyTorch 2.0 Intro notebook.

Single run (5 epochs once)

NVIDIA RTX 4080

results of training a resnet50 model on a nvidia rtx 4080 for 5 epochs with a batch size of 128 and image size of 224

NVIDIA A100

results of training a resnet50 model on a nvidia a100 for 5 epochs with a batch size of 128 and image size of 224

Multi run (5 epochs 3x)

NVIDIA RTX 4080

results of training a resnet50 model on an rtx 4080 for 5 epochs with a batch size of 128 and image size of 224 for 3 rounds

NVIDIA A100

results of training a resnet50 model on a nvidia a100 for 5 epochs with a batch size of 128 and image size of 224 for 3 rounds

Reference in New Issue View Git Blame Copy Permalink