SimAM: attention mechanism without parameters
SimAM: attention mechanism without parameters
abstract
In this paper, we propose a simple but very effective attention module for convolutional neural networks. Compared with the existing channel Focus module and spatial focus module, our module does not need to add parameters to the original network, but infers the 3-D focus weight of the fe ...
Posted by czs on Sun, 14 Aug 2022 21:24:53 +0300
Detailed explanation of omnipotent Embedding 1 - Word2vec model & code implementation
Word2vec is a model proposed by Google in 2013, which trains word vectors from large-scale corpus. It is applied in many scenes, such as information extraction, similarity calculation and so on. Starting from word2vec, embedding has become popular in various fields, so word2vec is an appropriate opening. This paper hopes to give a more comprehe ...
Posted by Gordicron on Wed, 25 May 2022 17:17:02 +0300
libtorch study notes - MNIST combat
MNIST libtorch practical exercise
Ready to work
First download the MNIST database, http://yann.lecun.com/exdb/mnist/
After downloading, do not decompress it with software such as winrar. For example, t10k-images-idx3-ubyte is decompressed into t10k-images.idx3-ubyte. It is best to decompress it with tar in Linux environment.
Suppose you unzip t ...
Posted by chrys on Wed, 25 May 2022 15:51:55 +0300
pytorch on GPU - training neural network with CUDA (pytorch series-30)
Running PyTorch code on GPU - neural network programming guide
In this episode, we will learn how to use GPU and PyTorch. We will see how to use the general methods of GPU, and we will see how to apply these general techniques to train our neural networks.
Deep learning using GPU
If you haven't seen the episode about why deep learning and neur ...
Posted by bmbc on Mon, 23 May 2022 12:42:05 +0300
Regression Prediction of Vehicle Efficiency Using Fully Connected Neural Networks
Regression Prediction of Vehicle Efficiency Using Fully Connected Neural Networks
keyword: fully connected neural network, tensorflow, regression
illustrate
It mainly uses the fully connected neural network to predict the regression problem of the car's performance index MPG.
python packages include: os, pandas, tensorflow, sklearn, matplotlib
...
Posted by kevinc on Sun, 22 May 2022 19:00:03 +0300
TVM, acceleration model, optimization, inference
TVM is an open source deep learning compiler, which can be applied to all kinds of CPUs, GPUs and other special accelerators. Its goal is to enable us to optimize and run our own model on any hardware. Unlike the deep learning framework, which focuses on model productivity, TVM pays more attention to the performance and efficiency of the model ...
Posted by dkruythoff on Sun, 22 May 2022 09:15:51 +0300
Introduction to YOLO v3 algorithm
Picture from https://towardsdatascience.com/yolo-v3-object-detection-with-keras-461d2cfccef6
Data preprocessing
Input picture dimension: (416, 416, 3)
Input picture label: $[(x_1, y_1, x_2, y_2, class{\_}index), (x_1, y_1, x_2, y_2,class{\_}index), \ldots, (x_1, y_1, x_2, y_2,class{\_}index)] $represents all the real boxes marked in the pictur ...
Posted by messels on Fri, 20 May 2022 15:36:03 +0300
[Flying Paddle] Target Detection YOLO-V3 Study Notes
Before learning this course, I heard the name of YOLO. During the epidemic, an up master trained the detection of pedestrian masks through yolo and it was a great success. Without further ado, let's start learning.
Basic Concepts in Object Detection
Before starting to learn YOLO, first learn some basic concepts of target detection. After all, Y ...
Posted by Pro Ninja on Fri, 20 May 2022 08:48:32 +0300
SimpleRNN realizes stock forecast
Please check the previous articles for the principle.
1. Data source
  SH600519.csv is the daily k-line data of sh600519 Guizhou Maotai downloaded by tushare module. In this example, only its C-column data is used (as shown in the figure):   use the opening price for 60 consecutive days to predict the opening price on ...
Posted by phpnewbie25 on Thu, 19 May 2022 23:01:07 +0300
[PyTorch] Note 02: Autograd auto derivation
From PyTorch 1.4 tutorial
Outline
Tensor
torch.autograd.backward
If the result node is scalar
If the result node is a vector
[PyTorch] Note 02: Autograd auto derivation
In PyTorch, the core of all neural networks is autograd package
1 Tensor
torch.Tensor is the core class of this autograd
A Tensor tensor usually records the following ...
Posted by rusbb on Thu, 19 May 2022 21:17:09 +0300