Simple Introduction to Tensorboard Embedding Visualisation (in r)

  – web:  http://www.pinchofintelligence.com/simple-introduction-to-tensorboard-embedding-visualisation/ – gibhub:  https://github.com/rmeertens/Simplest-Tensorflow-Tensorboard-MNIST-Embedding-Visualisation/blob/master/Minimal%20example%20embeddings.ipynb   sprite & metadata 준비 #Visualisation helper functions # the sprites # If you don’t load sprites, each digit is represented as a simple point (does NOT give you a lot of information) # To add labels, you have to create a ‘sprite Read more…

Simple Introduction to Tensorboard Embedding Visualisation

  – web:  http://www.pinchofintelligence.com/simple-introduction-to-tensorboard-embedding-visualisation/ – gibhub:  https://github.com/rmeertens/Simplest-Tensorflow-Tensorboard-MNIST-Embedding-Visualisation/blob/master/Minimal%20example%20embeddings.ipynb   ### Visualising embeddings # It helps you understand what your algorithm learned, and if this is what you expected it to learn # Embedding visualisation is a standard feature in Tensorboard. # # the most simple code to get a simple visualisation Read more…

tensorflow -mnist

  library(tensorflow) # Load mnist data datasets <- tf$contrib$learn$datasets mnist <- datasets$mnist$read_data_sets(“MNIST-data”, one_hot = TRUE) #sess <- tf$Session() sess <- tf$InteractiveSession() # Create the model x <- tf$placeholder(tf$float32, shape(NULL, 784L)) # input images yHat <- tf$placeholder(tf$float32, shape(NULL, 10L)) # target output classes #W <- tf$Variable(tf$zeros(shape(784L, 10L))) #b <- tf$Variable(tf$zeros(shape(10L))) ############################# Read more…

TensorFlow :: tutorial_mnist_Experts 2<번역>

https://tensorflow.rstudio.com/tutorial_mnist_pros.html   Training Train the Model 모델을 정의하고, training loss함수를 정의함. 이제 tensorFlow을 사용하여 바로 모델 훈련 시작 optimizer는 학습속도 0.5의 gradient descent 알고리즘을 사용한다.  TensorFlow는 전체 연산 그래프를 알고있기 때문에, loss의 gradients를 찾기위해 자동적으로 미분을 사용한다.  다행이 TensorFlow는 여러종류의 [built-in optimization algorithms] 을 가지고 있다.  (https://www.tensorflow.org/api_docs/python/train.html#optimizers).  cross entropy를 최소화하는 backpropagation 알고리즘을 Read more…

tensorflow :: 기본 예제

    library(ggplot2) ### DATA x <- rnorm(n=1000, mean=0.0, sd=0.55) y <- x* 0.1 + 0.3 + rnorm(n=1000, mean=0.0, sd=0.03) gg <- ggplot() + geom_point(aes(x,y)) library(tensorflow) use_virtualenv(“~/.pyenv/versions/tensorflowVE/”) Sys.setenv(TENSORFLOW_PYTHON=”~/python”) # Model W <- tf$Variable(tf$random_uniform(shape(1L), -1.0, 1.0)) b <- tf$Variable(tf$zeros(shape(1L))) y_hat <- W*x + b # MSE(mean squared errors) 최소화 loss <- Read more…

lab2

https://tensorflow.rstudio.com/ https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-02-1-linear_regression.py library(tensorflow) # Create 100 phony x, y data points, y = x * 0.1 + 0.3 # x_data <- runif(100, min=0, max=1) # y_data <- x_data * 0.1 + 0.3 Advertising <- read.table(“http://www-bcf.usc.edu/~gareth/ISL/Advertising.csv”,header=T, sep=”,”) x_data <- Advertising$TV y_data <- Advertising$Sales # Try to find values for W and Read more…

LAB1

    library(tensorflow) # Check TF version names(tf) tf$VERSION ################################################## # Hello ################################################## # This op is added as a node to the default graph hello <- tf$constant(“Hello, TensorFlow!”) # Create a constant op sess <- tf$Session() # start a TF session print(sess$run(hello)) # run the op and get result Read more…