├── .gitignore ├── LICENSE ├── README.md ├── RUN.md ├── data └── FashionMNIST │ ├── processed │ ├── test.pt │ └── training.pt │ └── raw │ ├── t10k-images-idx3-ubyte │ ├── t10k-images-idx3-ubyte.gz │ ├── t10k-labels-idx1-ubyte │ ├── t10k-labels-idx1-ubyte.gz │ ├── train-images-idx3-ubyte │ ├── train-images-idx3-ubyte.gz │ ├── train-labels-idx1-ubyte │ └── train-labels-idx1-ubyte.gz ├── model.py ├── single-machine-and-multi-GPU-DataParallel.py ├── single-machine-and-multi-GPU-DistributedDataParallel-launch.py ├── single-machine-and-multi-GPU-DistributedDataParallel-mp.py ├── single-machine-and-multi-GPU-DistributedDataParallel-slurm.py ├── single-machine-and-single-GPU.py └── test └── torch_distributed_launch ├── README.md ├── train.py └── wrong_attemp.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/README.md -------------------------------------------------------------------------------- /RUN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/RUN.md -------------------------------------------------------------------------------- /data/FashionMNIST/processed/test.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/processed/test.pt -------------------------------------------------------------------------------- /data/FashionMNIST/processed/training.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/processed/training.pt -------------------------------------------------------------------------------- /data/FashionMNIST/raw/t10k-images-idx3-ubyte: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/t10k-images-idx3-ubyte -------------------------------------------------------------------------------- /data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz -------------------------------------------------------------------------------- /data/FashionMNIST/raw/t10k-labels-idx1-ubyte: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/t10k-labels-idx1-ubyte -------------------------------------------------------------------------------- /data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz -------------------------------------------------------------------------------- /data/FashionMNIST/raw/train-images-idx3-ubyte: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/train-images-idx3-ubyte -------------------------------------------------------------------------------- /data/FashionMNIST/raw/train-images-idx3-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/train-images-idx3-ubyte.gz -------------------------------------------------------------------------------- /data/FashionMNIST/raw/train-labels-idx1-ubyte: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/train-labels-idx1-ubyte -------------------------------------------------------------------------------- /data/FashionMNIST/raw/train-labels-idx1-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/data/FashionMNIST/raw/train-labels-idx1-ubyte.gz -------------------------------------------------------------------------------- /model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/model.py -------------------------------------------------------------------------------- /single-machine-and-multi-GPU-DataParallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/single-machine-and-multi-GPU-DataParallel.py -------------------------------------------------------------------------------- /single-machine-and-multi-GPU-DistributedDataParallel-launch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/single-machine-and-multi-GPU-DistributedDataParallel-launch.py -------------------------------------------------------------------------------- /single-machine-and-multi-GPU-DistributedDataParallel-mp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/single-machine-and-multi-GPU-DistributedDataParallel-mp.py -------------------------------------------------------------------------------- /single-machine-and-multi-GPU-DistributedDataParallel-slurm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/single-machine-and-multi-GPU-DistributedDataParallel-slurm.py -------------------------------------------------------------------------------- /single-machine-and-single-GPU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/single-machine-and-single-GPU.py -------------------------------------------------------------------------------- /test/torch_distributed_launch/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/test/torch_distributed_launch/README.md -------------------------------------------------------------------------------- /test/torch_distributed_launch/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/test/torch_distributed_launch/train.py -------------------------------------------------------------------------------- /test/torch_distributed_launch/wrong_attemp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HongxinXiang/pytorch-multi-GPU-training-tutorial/HEAD/test/torch_distributed_launch/wrong_attemp.py --------------------------------------------------------------------------------