From d97953e6ff67978da9554e7b4601aedceb21e215 Mon Sep 17 00:00:00 2001 From: "Liguros - Gitlab CI/CD [develop]" Date: Tue, 12 Apr 2022 21:03:09 +0000 Subject: Adding metadata --- dev-cpp/tiny-dnn/metadata.xml | 89 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 dev-cpp/tiny-dnn/metadata.xml (limited to 'dev-cpp/tiny-dnn/metadata.xml') diff --git a/dev-cpp/tiny-dnn/metadata.xml b/dev-cpp/tiny-dnn/metadata.xml new file mode 100644 index 000000000000..0bc53e1c06ed --- /dev/null +++ b/dev-cpp/tiny-dnn/metadata.xml @@ -0,0 +1,89 @@ + + + + + lssndrbarbieri@gmail.com + Alessandro Barbieri + + +Features + +Reasonably fast, without GPU: +With TBB threading and SSE/AVX vectorization. +98.8% accuracy on MNIST in 13 minutes training (@Core i7-3520M). +Portable and header-only: +Runs anywhere as long as you have a compiler which supports C++14. +Just include tiny_dnn.h and write your model in C++. There is nothing to install. +Easy to integrate with real applications: +No output to stdout/stderr. +A constant throughput (simple parallelization model, no garbage collection). +Works without throwing an exception. +Can import caffe's model. +Simply implemented: +A good library for learning neural networks. + +Supported networks + +layer-types + +core +fully connected +dropout +linear operation +zero padding +power +convolution +convolutional +average pooling +max pooling +deconvolutional +average unpooling +max unpooling +normalization +contrast normalization (only forward pass) +batch normalization +split/merge +concat +slice +elementwise-add +activation functions + +tanh +asinh +sigmoid +softmax +softplus +softsign +rectified linear(relu) +leaky relu +identity +scaled tanh +exponential linear units(elu) +scaled exponential linear units (selu) +loss functions + +cross-entropy +mean squared error +mean absolute error +mean absolute error with epsilon range +optimization algorithms + +stochastic gradient descent (with/without L2 normalization) +momentum and Nesterov momentum +adagrad +rmsprop +adam +adamax + + + Build tiny-dnn with double precision computations + + + Build tiny-dnn with OpenCL library support + Build tiny-dnn with Serialization support + Build tiny-dnn with TBB library support + + + tiny-dnn/tiny-dnn + + -- cgit v1.3