Skip to content

amd-sriram/Frameworks101

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Frameworks101

Installation

sh docker_run.sh

Inside the docker, run the following:

cd /Frameworks

sh install.sh

cd src

First GPU Kernel

cd FirstGPUKernel

hipcc helloworld.cpp utils.hpp -o helloworld

./helloworld

hipcc add.cpp utils.hpp -o add

./add

Pytorch

python3 -m Pytorch.convolution

python3 -m Pytorch.conv_back

TorchCompile

To compare inference times of pytorch vs torch compile

python3 TorchCompile/pytorch_model.py

python3 TorchCompile/pytorch_compile.py

To generate the graphs

python3 -m TorchCompile.compile_graphs

ONNX

To export Resnet50 model

python3 ONNX/export_model.py

To create ONNX models

python3 ONNX/simple_onnx_model.py

python3 ONNX/complex_onnx_model.py

To benchmark pytorch vs onnx for Resnet50 model

python3 ONNX/benchmark.py

Train pytorch model using torch-ort

python3 ONNX/train_pytorch_model.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published