ammieqi / deeplearningbenchmarks Goto Github PK
View Code? Open in Web Editor NEWThis project forked from jaberg/deeplearningbenchmarks
This project forked from jaberg/deeplearningbenchmarks
Intro ===== The benchmarking folder contains efforts to benchmark Theano against various other systems. Each subfolder corresponds to a particular style of implementation. Since there is a variety of benchmark problems and of software systems, there isn't a standard for how to run the benchmark suite. There is however a standard for how each benchmark should produce results. Every benchmark run should produce one or more files with the results of benchmarking. These files must end with extension '.bmark'. These files must have 'csv' lines like this: task<tab>implementation name<tab>examples/second Current Tasks ============== Dense ----- mlp_784_10 - training on 10K MNIST-sized examples with unregularized Logistic Regression (crossentropy / NLL error) mlp_784_500_10 - training on 10K examples with a single-hidden layer model with 500 hidden units mlp_784_1000_1000_1000_10 - training on 10K examples with multiple hidden layers cd1 rbm_bernoulli 1024_1024 - train an RBM from 10K 1024-dimensional inputs daa_1024_1024 - train a denoising autoassociator from 10K 1024-dimensional inputs Convolutional ------------- ConvSmall - train from 10K 32x32 inputs, as in LeNet5 - convnet_32x32_c5x5_s2x2_c5x5_s2x2_120_10 ConvMed - train from 10K 96x96 images ConvLarge - train from 10K 256x256 images Potential Tasks ================ Dense ----- mlp_32_10 - training on 10K tiny examples with unregularized Logistic Regression (crossentropy / NLL error) mlp_784_10 with L1 - training on 10K examples with L1 regularization mlp_784_10 with L2 - training on 10K examples with L2 regularization aa_64_64 - train an autoassociator from at 10K 64-dimensional inputs aa_1024_1024 - train an autoassociator from 10K 1024-dimensional inputs cd1 rbm_bernoulli 64_64 - train an RBM from 10K 64-dimensional inputs Convolutional ------------- LeNet5_32x32x3 - train from 10K Tiny-Image sized inputs (in color) conv_daa_i32x32_f7x7 - train a convolutional conv_daa_i256x256_f9x9 - train a convolutional Recurrent ---------
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.