gotch/example/mnist
2020-07-03 11:20:52 +10:00
..
cnn.go BREAKING CHANGE(nn/linear): removed pointer receiver 2020-07-03 11:20:52 +10:00
linear.go feat(nn/rnn): added rnn.go feat(nn/conv-transpose): added conv-transpose.go 2020-06-24 18:14:34 +10:00
main.go fix(KaimingUniformInit): fixed incorrect init of KaimingUniform method 2020-06-24 12:47:10 +10:00
nn.go BREAKING CHANGE(nn/linear): removed pointer receiver 2020-07-03 11:20:52 +10:00
README.md WIP(example/mnist): nn 2020-06-18 17:14:48 +10:00

Linear Regression, NN, and CNN on MNIST dataset

MNIST

  • MNIST files can be obtained from this source and put in data/mnist from root folder of this project.

  • Load MNIST data using helper function at vision sub-package

Linear Regression

  • Run with go clean -cache -testcache && go run . -model="linear"

  • Accuraccy should be about 91.68%.

Neural Network (NN)

  • Run with go clean -cache -testcache && go run . -model="nn"

  • Accuraccy should be about TODO: update%.

Convolutional Neural Network (CNN)

  • Run with go clean -cache -testcache && go run . -model="cnn"

  • Accuraccy should be about TODO: update%.