DAVIDSTUTZ

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

TAG»TORCH«

11thAPRIL2017

Reading/Writing JSON and HDF5 in Lua/Torch

Reading and writing JSON and HDF5 in Lua/Torch using luajson and torch-hdf5.

08thAPRIL2017

Convolutional Variational Auto-Encoder in Torch

An example of a convolutional variational auto-encoder for fixed-size rectangles in $24 \times 24$ images with different anchors; convolutional variant of the snippet presented here: Variational Auto-Encoder in Torch. The variational auto-encoder is able to learn a $2$-dimensional code shown in the interpolations below the listing. The example can easily be adapted to more complex data.

08thAPRIL2017

Variational Auto-Encoder in Torch

An example of a variational auto-encoder for fixed-size rectangles in $24 \times 24$ images with different anchors. The variational auto-encoder is able to learn a $2$-dimensional code shown in the interpolations below the listing. The example can easily be adapted to more complex data.

Examples for Getting Started with Torch for Deep Learning

This article is a collection of Torch examples meant as introduction to get started with Lua and Torch for deep learning research. The examples can also be considered individually and cover common use cases such as training on CPU and GPU, weight initialization and visualization, custom modules and criteria as well as saving and fine-tuning models.

18thMARCH2017

Example of Fine-Tuning in Torch

An example of fine-tuning an auto-encoder for classification. The example demonstrates how arbitrary modules can easily be extended to fix the weights and/or biases after loading a model. Additionally it shows how weights and biases can manually be copied between models with a different structure.

14thMARCH2017

Defining Torch Modules on Custom Data Structures

Minimal example of defining a custom Torch module on a custom data structure. This example defines a simple data structure wrapping two Torch tensors and defines a linear nn.Module to operate on this data structure. While the backward pass is not implemented, the example illustrates how Torch can be extended for deep learning on custom data structures.

11thMARCH2017

Custom Abs Criterion in Torch

A simple custom abs-criterion in Torch extending nn.Criterion.

09thMARCH2017

Manual Weight and Bias Initialization in Torch

Simple LUA package to manually initialize the weights and biases of a network in Torch according to different strategies — these include uniform and normal initialization as well as heuristic and Xavier initialization. The package is easily extended to include additional initialization schemes and allows to initialize weights and biases using different strategies.

09thMARCH2017

Convolutional Auto-Encoder using Torch’s optim Package

A simple convolutional auto-encoder implemented in Torch and trained using Torch’s optim package.

Installing Torch and iTorch, Installing ZeroBrane Studio with Torch Support

In this series, I blog about development and research with Ubuntu. This time: how to install LUA, Torch and iTorch and use Torch from within ZeroBrane Studio.