Kento Nozawa nzw0301

nzw0301 / cifar100-channel_wise_mean_and_std.py

Created August 14, 2019 20:38

	# CIFAR-100

	import numpy as np
	import torchvision.transforms as transforms
	from torch.utils.data import DataLoader
	from torchvision.datasets import CIFAR100


	train_transform = transforms.Compose(
	[

nzw0301 / suggest_int with log argument.ipynb

Created May 18, 2020 15:49

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

nzw0301 / optuna_with_pytorch_distributed.py

Last active April 27, 2022 06:34

	"""
	Modification version of https://github.com/optuna/optuna/pull/2303 with nccl backend

	Optuna example that optimizes multi-layer perceptrons using PyTorch distributed.

	In this example, we optimize the validation accuracy of hand-written digit recognition using
	PyTorch distributed data parallel and MNIST. We optimize the neural network architecture as well
	as the optimizer configuration. As it is too time consuming to use the whole MNIST dataset, we
	here use a small subset of it.