| http://models.topazlabs.com/v1/gnn-v1-fp16-256x256-1x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp16-256x256-2x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp16-256x256-4x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp16-384x384-1x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp16-384x384-2x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp16-384x384-4x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp32-256x256-1x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp32-256x256-2x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp32-256x256-4x-ov.tz | |
| http://models.topazlabs.com/v1/gnn-v1-fp32-384x384-1x-ov.tz |
| """ | |
| PyTorch Guided Filter for multi-channel (color) guide image and 1 channel | |
| (grayscale) source image | |
| """ | |
| import torch as T | |
| import torch.nn as nn | |
| def box_filter_1d(tensor, dim, r): | |
| cs = tensor.cumsum(dim).transpose(dim, 0) |
| # Copyright 2019 Google LLC. | |
| # SPDX-License-Identifier: Apache-2.0 | |
| # Author: Anton Mikhailov | |
| turbo_colormap_data = [[0.18995,0.07176,0.23217],[0.19483,0.08339,0.26149],[0.19956,0.09498,0.29024],[0.20415,0.10652,0.31844],[0.20860,0.11802,0.34607],[0.21291,0.12947,0.37314],[0.21708,0.14087,0.39964],[0.22111,0.15223,0.42558],[0.22500,0.16354,0.45096],[0.22875,0.17481,0.47578],[0.23236,0.18603,0.50004],[0.23582,0.19720,0.52373],[0.23915,0.20833,0.54686],[0.24234,0.21941,0.56942],[0.24539,0.23044,0.59142],[0.24830,0.24143,0.61286],[0.25107,0.25237,0.63374],[0.25369,0.26327,0.65406],[0.25618,0.27412,0.67381],[0.25853,0.28492,0.69300],[0.26074,0.29568,0.71162],[0.26280,0.30639,0.72968],[0.26473,0.31706,0.74718],[0.26652,0.32768,0.76412],[0.26816,0.33825,0.78050],[0.26967,0.34878,0.79631],[0.27103,0.35926,0.81156],[0.27226,0.36970,0.82624],[0.27334,0.38008,0.84037],[0.27429,0.39043,0.85393],[0.27509,0.40072,0.86692],[0.27576,0.41097,0.87936],[0.27628,0.42118,0.89123],[0.27667,0.43134,0.90254],[0.27691,0.44145,0.913 |
| #CODE | |
| #Generate root password | |
| import random, string | |
| password = ''.join(random.choice(string.ascii_letters + string.digits) for i in range(20)) | |
| #Download ngrok | |
| ! wget -q -c -nc https://bin.equinox.io/c/4VmDzA7iaHb/ngrok-stable-linux-amd64.zip | |
| ! unzip -qq -n ngrok-stable-linux-amd64.zip | |
| #Setup sshd |
Single-process:
python main_amp.py -a resnet50 --b 224 --deterministic --workers 4 --opt-level O1 ./bare_metal_train_val/
Multi-process:
python -m torch.distributed.launch --nproc_per_node=2 main_amp.py -a resnet50 --b 224 --deterministic --workers 4 --opt-level O1 ./bare_metal_train_val/
| #!/usr/bin/env python3 | |
| # -*- coding: utf-8 -*- | |
| # https://toster.ru/q/72866 | |
| # How to | |
| # wget http://gist.github.com/... | |
| # chmod +x ya.py | |
| # ./ya.py download_url path/to/directory | |
| import os, sys, json |
Building Tensorflow from source on Ubuntu 16.04LTS for maximum performance:
TensorFlow is now distributed under an Apache v2 open source license on GitHub.
On Ubuntu 16.04LTS+:
Step 1. Install NVIDIA CUDA:
To use TensorFlow with NVIDIA GPUs, the first step is to install the CUDA Toolkit as shown:
In this article, I will share some of my experience on installing NVIDIA driver and CUDA on Linux OS. Here I mainly use Ubuntu as example. Comments for CentOS/Fedora are also provided as much as I can.
curl to get the JSON response for the latest releasegrep to find the line containing file URLcut and tr to extract the URLwget to download itcurl -s https://api.github.com/repos/jgm/pandoc/releases/latest \
| grep "browser_download_url.*deb" \
| cut -d : -f 2,3 \
| tr -d \" \