Nicholas Léonard

Need way to load directly from csv to tensor

2

http://fastml.com/loading-data-in-torch-is-a-mess/

Anto-Encoder Example

2

Jack requested an AutoEncoder example : https://groups.google.com/forum/#!topic/torch7/NRESl-hgMHA It would be a good idea, as it would provide an example of use-case for unsupervised training in dp. We could base ourselves...

Need smarter way to manage experiments

1

I am thinking we should launch multiple experiments in parallel from a single controller interface. The controller should allow the user to configure and launch experiments. Then the controller could...

I have some people asking of UML diagrams and such for the docs.

Preprocessing script, and Checkpoint DataSource

4

Quoting a recent discussion concerning pylearn2, Pascal Lamblin (@lamblin) offered some nice solutions to a problem both our libraries are having: > - Considering Datasets immutable, and only allow read...

RMSProp and AdaGrad Visitors

1

http://www.erogol.com/comparison-sgd-vs-momentum-vs-rmsprop-vs-momentumrmsprop/

Implement GoogleLeNet (Inception)

2

Slides: http://image-net.org/challenges/LSVRC/2014/slides/GoogLeNet.pptx Paper: http://arxiv.org/abs/1409.4842  nn example: https://github.com/nagadomi/kaggle-cifar10-torch7/blob/cuda-convnet2/inception_model.lua - [x] nn.DepthConcat Module - [x] dp.Inception Model - [ ] dp.ImageNet DataSource - [x] script to train svhn using inception :...

http://qwone.com/~jason/20Newsgroups/

Expand How Does it Work section

3

Could you guys expand on the how does it work section in the docs? Specifying how the output, gradInput, weight, gradWeight and intermediate state buffers are handled would be a...