ubuntu16.04 one step installation of cuda10 02, PyTorch, PaddlePaddle, TensorRT
Since many frameworks and suites have stopped supporting CUDA 10.0, CUDA 10.0 will be installed as originally 0's server is reconfigured cuda10 2 and new drive
Original drive unloading
1. Stop X Server
sudo service lightdm stop
2. Uninstall the previous Driver
sudo /usr/bin/nvidia-uninstall
After uninstallation is completed, enter N ...
Added by ricardo.leite on Fri, 31 Dec 2021 21:07:17 +0200
Triton: openai open source GPU Programming artifact
preface
We will release Triton 1.0, an open source Python like programming language that enables researchers without CUDA experience to write efficient GPU code - in most cases equivalent to the code generated by experts. Triton makes it possible to reach the peak of hardware performance with relatively little effort; For example, it can b ...
Added by callie212 on Fri, 31 Dec 2021 20:40:08 +0200
Hengyuan cloud_ [text classification] text data enhancement 1 (paper notes)
Source: Hengyuan cloud community( Hengyuan cloud, a shared computing platform focusing on AI industry)
Original address| Text data enhancement
Original author Jiao Hui
Recently, I was doing news headline classification and found an article with data enhancement to learn: One is enough! Overview of data enhancement methods This paper implem ...
Added by tony-kidsdirect on Fri, 31 Dec 2021 19:21:48 +0200
Automatic derivation with numpy and PyTorch, torch Implementation of two-layer neural network based on NN Library
Realize the step-by-step deepening from manual derivation to automatic derivation and then to the model.
Implementation of two-layer neural network with numpy
A fully connected ReLU neural network, a hidden layer, no bias, L2 Loss (h is hidden layer, ReLU activation function):
h
...
Added by karldenton on Fri, 31 Dec 2021 17:56:23 +0200
Super parameter adjustment and automatic time series modeling are carried out by genetic algorithm
In previous articles, we introduced some knowledge based on genetic algorithm. This article will use genetic algorithm to process machine learning model and time series data.Super parameter adjustment (TPOT)Automatic machine learning (Auto ML) helps us find the most suitable model for prediction by automating the whole machine learning process. ...
Added by VMinder on Fri, 31 Dec 2021 16:05:22 +0200
[source code analysis] machine learning parameter server PS Lite ----- communication module Van
[source code analysis] machine learning parameter server PS Lite (2) -- communication module Van
0x00 summary
This is the second part of the parameter server series, which introduces the communication module Van of PS Lite.
Other articles in this series are:
[source code analysis] machine learning parameter server PS Lite (1) -- postoff ...
Added by mattchewone on Fri, 31 Dec 2021 15:05:13 +0200
PyTorch: data reading mechanism under batch training DataLoader
First clarify the meaning of several common nouns: batch, epoch and iteration Batch: usually, we divide a data set into several small sample sets, and then feed a small part to the neural network for iteration. Each small part of the sample is called a batch. Epoch: all the data in the training set are trained completely in the model (including ...
Added by schandhok on Thu, 30 Dec 2021 22:12:53 +0200
Transfer learning of deep learning to realize Magic Baby recognition
Through the previous practice of in-depth learning, whether it is the CNN network built by ourselves or the official network model called through migration learning, it has its advantages and disadvantages. This experiment calls various common CNN network models to understand their characteristics and compare the accuracy of classification for ...
Added by warewolfe on Thu, 30 Dec 2021 17:10:50 +0200
Tensorflow 2 actual combat (kears) - generative countermeasure Network - GAN, WGAN-GP
1, Background introduction
1.1 introduction to data set
The Anime dataset used in this actual combat is PNG picture of "high definition animation character Avatar". The pictures are 64x64 color pictures, a total of 21551. The examples of the pictures are as follows:
1.2 model introduction
The "generation countermeasure ...
Added by shadownet on Thu, 30 Dec 2021 11:48:07 +0200
saliency map code parsing
Recently I needed to use the saliency map, studied it for a long time, took a note
What does saliency map do?
The saliency map can be understood as a feature map to measure the impact of the characteristics of each pixel point in the image on the classification results. Looking at the image below, you can see that the outline of the dog in th ...
Added by drakal30 on Wed, 29 Dec 2021 23:29:16 +0200