-
Seems we are missing affine transformations? eg:
- translate
- rotate
- scale
- and might not technically be an affine transformation, but also cutting a random patch
Note that during learning, thes…
-
Hi everybody! I'm having an issue with saving my graph objects to disk, in which the graph objects are taking up large amounts of disk space regardless of whether or not I have node or edge metadata a…
-
A neural net typically accepts a vector(n-D array of numbers) as input. Therefore, a process needs to convert a graph into vectors before the neural net does learn and predict: every node, every edge,…
-
layers.py, on which most of the nntools code is based, has always been geared towards feed-forward neural networks. We should look into recurrent neural networks as well. Personally I don't have a lot…
-
Hello everyone,
I open this post to present some new APIs and types of model i have in mind, before start working on them in order to understand: are they feasible? are they needed? or simply understa…
-
I found an MIT Licensed Convolutional Neural Network
https://github.com/siddharth950/Convolutional-Neural-Network/blob/master/convolutionalNeuralNetwork.py
It might be useful to include in sklearn/n…
-
Let me know what you think. What is this missing? Any way to make it simpler and more elegant?
``` python
''' Simple model with 2 branches merging into one
left right
| |
\ …
-
I'm curious if other people would be interested in having examples in this fashion: https://github.com/enlitic/lasagne4newbs/blob/master/mnist_conv.py. I've found the existing examples to be a little …
-
Multiple factors motivate this proposal including #57, #119, #129, the papers and codes of Generative Stochastic Networks (GSN) [1, 2, 3, 4, 5], and the scene labeling paper using Recurrent Convolutio…
-
Hi all,
I have just modified caffe to run for dense pixel labelling for my semantic scene understanding task. I am testing that on a very simplistic network with only one convolution layer followed …