mingfeima

General guidelines for CPU performance on PyTorch

This file serves a BKM to get better performance on CPU for PyTorch, mostly focusing on inference or deployment. Chinese version available here.

1. Use channels last memory format

Right now, on PyTorch CPU path, you may choose to use 3 types of memory formats.

• torch.contiguous_format: default memory format, also referred as NHCW.
• torch.channels_last: also referred as NHWC.
• torch._mkldnn: mkldnn blocked format.

akurniawan

import itertools
import torch
from torchtext.experimental.datasets.translation import DATASETS, TranslationDataset
from torchtext.vocab import build_vocab_from_iterator
from torchtext.experimental.functional import (
    vocab_func,
    totensor,
    sequential_transforms,
)
from torchtext.data.utils import get_tokenizer

jmp84

import argparse
import logging

import torch
from fairseq.checkpoint_utils import load_model_ensemble_and_task
from fairseq.sequence_generator import SequenceGenerator


def get_args():
    parser = argparse.ArgumentParser(

lsawaniewski

# Htop
sudo apt install -y htop

# Byobu
sudo apt install -y byobu

# Gdebi
sudo apt install -y gdebi-core

# GIT

wphicks