IAM

OPENSOURCEFAN STUDYING
STUDYINGCOMPUTERSCIENCEANDMATH COMPUTERSCIENCE

Check out the latest superpixel benchmark — Superpixel Benchmark (2016) — and let me know your opinion! @david_stutz

ARCHIVEMONTHLY»FEBRUARY2017«

24thFEBRUARY2017

SNIPPET

A simple implementation of batch normalization in Tensorflow. Note that the implementation is meant for training — i.e. for testing on individual samples, the mean and variance should be fixed in advance. Also note that tf.nn.moments is replaced by a custom method for computing mean and variance to avoid the problem described here.

Interested?

ARTICLE

Installing Bazel, Masking Graphics Cards for Tensorflow

In this series, I collect problems I come across when using Ubuntu for research and development. In this article: installing Bazel on Ubuntu and masking graphics cards from being considered by Tensorflow.

Interested?

23thFEBRUARY2017

SNIPPET

In specific cases, tf.nn.moments cannot be run on the GPU (see here). This is problematic when training (convolutional) neural networks where moments are part of the computation graph (e.g. for normalization). This snippet is a simple work around, computing mean and variance along the provided dimensions manually.

Interested?

21thFEBRUARY2017

SNIPPET

Auto-encoder in Torch using Torch’s optim package and GPU acceleration.

Interested?

21thFEBRUARY2017

SNIPPET

Auto-encoder in Torch using Torch’s optim package.

Interested?

20thFEBRUARY2017

SNIPPET

Simple auto-encoder example implemented in Torch (following the documentation)

Interested?

20thFEBRUARY2017

SNIPPET

Auto-encoder implemented in Torch using Torch’s cunn for GPU-acceleration.

Interested?