juntang-zhuang

aa: rand-m9-mstd0.5
amp: true
apex_amp: false
aug_splits: 0
batch_size: 192
bn_eps: null
bn_momentum: 0.1
bn_tf: false
channels_last: false
checkpoint_hist: 10

juntang-zhuang

#!/bin/bash
NUM_PROC=2
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=$NUM_PROC train.py "$@" --model efficientnet_b0 --weight-decay 2.5e-2 --drop 0.2 --drop-path 0.2 --lr 0.002 --batch-size 192 --epochs 400 --sched cosine --opt adabelief --workers 8 --warmup-lr 1e-4 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --bn-momentum 0.1 --mixup 0.2 --mixup-off-epoch 400 --min-lr 1e-5

juntang-zhuang

Whether you're trying to give back to the open source community or collaborating on your own projects, knowing how to properly fork and generate pull requests is essential. Unfortunately, it's quite easy to make mistakes or not know what you should do when you're initially learning the process. I know that I certainly had considerable initial trouble with it, and I found a lot of the information on GitHub and around the internet to be rather piecemeal and incomplete - part of the process described here, another there, common hangups in a different place, and so on.

In an attempt to coallate this information for myself and others, this short tutorial is what I've found to be fairly standard procedure for creating a fork, doing your work, issuing a pull request, and merging that pull request back into the original project.

Creating a Fork

Just head over to the GitHub page and click the "Fork" button. It's just that simple. Once you've done that, you can use your favorite git client to clone your repo or j

juntang-zhuang

"""A training script of Soft Actor-Critic on OpenAI Gym Mujoco environments.

This script follows the settings of https://arxiv.org/abs/1812.05905 as much
as possible.
"""
import argparse
from distutils.version import LooseVersion
import functools
import logging
import sys

juntang-zhuang

Updated 4/11/2018

Here's my experience of installing the NVIDIA CUDA kit 9.0 on a fresh install of Ubuntu Desktop 16.04.4 LTS.

Table of Contents

• Install NVIDIA Graphics Driver via apt-get
• Install CUDA
• Install cuDNN

Table of contents generated with markdown-toc