Tag：neural network
-
[note] pytorch quick start: collection of basic parts
Pytorch quick start Tensors Tensors runs through pytorch Similar to multidimensional arrays, one feature is hardware acceleration Initialization of tensors There are many ways Direct value data = [[1,2],[3,4]] x_data = torch.tensor(data) From numpy array np_arr = np.array(data) x_np = torch.from_numpy(np_array) From another tensor x_ones = torch.ones_like(x_data) Assign 01 or random value shape = (2,3,) […]
-
TF learning convolutional neural networks convolutional network model
Convolutional neural networks Convolution operation and pooling operationDeep separable convolutionData enhancementTransfer learning General structure: Convolutional neural network (convolution+subsampling)n + fully connected layers,FCm classification Full convolution neural network (convolution+subsampling)n + pixelwise classificationK Object segment Convolution operation:Solve the problem of too many neural network parameters, for example, the picture size is 10001000, the next layer neuron is […]
-
Pytorch: the pit between train mode and eval mode
Article catalogue preface 1. Train mode and eval mode 2. BatchNorm 3. Mathematical principles Concluding remarks preface the blogger was accidentally killed in the recent development processpytorchintrainMode andevalMode pit o (* ≥ д ≦)o!!， Let’s not talk about the cause of being trapped. This article will introduce it in detailtrainMode andevalThe influence of pattern […]
-
Keras deep learning practice (2) — using keras to construct neural network
Keras deep learning practice (2) — using keras to construct neural network 0 Preface 1. Keras introduction and installation 2. Keras’s initial experience in constructing neural network 3. Training vanilla neural network 3.1 introduction to vanilla neural network and MNIST data set 3.2 review of training neural network steps 3.3 constructing neural network model using […]
-
Machine learning: summary of linear model learning (3): linear model based on pytorch
Based on Teacher Zhou Zhihua’s《machine learning》I. previous articleStudy notesAs well as other information on the network, this part of the linear model is summarized. Connection:Machine learning: summary of linear model learning (2)。 Study time: April 19, 2022 ~ April 20, 2022 Article catalogue 1. Data preprocessing 2. Pytorch linear regression 3. Pytorch linear classification 4. […]
-
ValueError: Please provide model inputs as a list or tuple of 2 or 3 elements: (input, target)
ValueError: Please provide model inputs as a list or tuple of 2 or 3 elements: (input, target) Error reporting information Traceback (most recent call last): File “vae.py”, line 170, in <module> train_model(vae) File “vae.py”, line 161, in train_model vae.fit(sequence, epochs=epochs) File “/home/fanjiarong/.local/lib/python2.7/site-packages/tensorflow_core/python/keras/engine/training.py”, line 819, in fit use_multiprocessing=use_multiprocessing) File “/home/fanjiarong/.local/lib/python2.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py”, line 235, in fit use_multiprocessing=use_multiprocessing) File […]
-
The sorting of some resources of Zhihu station B mainly involves graph neural network and programming language
Skill class Learning resources of station B Ppt production WORD Drawing revision software Ppt template How to improve English Listening Thesis writing auxiliary website Hard core class FFT various language codes RSA encryption algorithm Application scenario of machine learning algorithm ditto Understanding of convolution The relation between F transform, L transform and Z transform Feature […]
-
Neural networks and deep learning
@[toc] 1.1 welcome 1.2 what is neural network The simplest neural network Insert picture description here 1.3 supervised learning with neural network CNN: suitable for image data RNN: suitable for (one-dimensional) time series data Structured data structured data and unstructured data unstructured data 1.4 why does deep learning rise? data（big data) computer(CPU、GPU) algorithms The improvement […]
-
Deep learning notes 01 – Introduction
1 Introduction catalogue 1 Introduction 1.2 machine learning 1.3 express learning Local representation Distributed representation Express learning Traditional feature extraction and representation learning 1.4 deep learning 1.5 artificial neural network 1.2 machine learning Traditional machine learning can be regarded as shallow learning: it does not involve feature learning, and features are extracted by manual experience […]
-
Neural network model + Advanced
Part I neural network model Analog data set.seed(888) x1 <- rnorm(1000,0) set.seed(666) x2 <- rnorm(1000,0) logit1 <- 2+3*x1+x1^2-4*x2 logit2 <- 1.5+2*x1-3*x2^2+x2 Denominator <- 1+exp(logit1)+exp(logit2) #denominator for probability calculation vProb <- cbind(1/Denominator,exp(logit1)/Denominator,exp(logit2)/Denominator) #calculating the matrix of probabilities for there choices mChoices <- t(apply(vProb,1,rmultinom,n=1,size=1)) #Assigning value 1 to maximum probability and 0 for the rest to get […]
-
Neural network and back propagation algorithm
catalog: 1. What is neural network 2. Forward propagation 3. Back propagation of error (BP algorithm) 4. Manually implement a basic fully connected neural network FCNN 5. Neural network practice – handwritten numeral recognition 6. Vectorization programming 1、 What is neural network Artificial neural network is referred to as “neural network”. In short, it is […]
-
R language combined with COVID-19 COVID-19 stock price prediction: ARIMA, KNN and neural network time series analysis
Original link: http://tecdat.cn/?p=24057 1. Summary The goal of this paper is to use various prediction models to predict the future stock price of Google, and then analyze various models. The Google stock data set was obtained from Yahoo Finance using the quantmod package in R. 2. Introduction Prediction algorithm is a process of trying to […]