Stack Overflow
Stack Overflow

Questions tagged [nolearn]

nolearn is a Python package with utility functions for machine learning tasks.

nolearn is a package with utility functions for machine learning tasks.

Dependencies:

Resources:

43 questions
83
votes
3 answers

How to calculate the number of parameters for convolutional neural network?

I'm using Lasagne to create a CNN for the MNIST dataset. I'm following closely to this example: Convolutional Neural Networks and Feature Extraction with Python. The CNN architecture I have at the moment, which doesn't include any dropout layers,…
Waddas
  • 1,353
  • 2
  • 16
  • 28
19
votes
4 answers

Download a specific branch of a github project

To cut the story short, to run a convolutional neural network model, I need an special version of nolearn, which has a url of the form https://github.com/dnouri/nolearn/tree/1659e4811e498dc1f442d8e6486d0831f85255b4/nolearn . However, there are no…
Ali Shakiba
  • 1,255
  • 2
  • 15
  • 29
6
votes
2 answers

Lasagne/nolearn autoencoder - how to get hidden layer output?

I've trained an autoencoder using lasagne/nolearn. Suppose the network layers are [500, 100, 100, 500]. I've trained the neural net like so: net.fit(X, X) I want to do something like the following: net.predict(X, layer=2) so I'll get the…
Stergios
  • 3,126
  • 6
  • 33
  • 55
5
votes
0 answers

Very High Errors in Deep Belief Network with Nolearn in Python

I'm new to Nolearn and Theano in general. When I tried the code in a Nolearn tutorial, I get extremely high error rates of 0.9! Why am I getting such high errors while the tutorial is getting errors of 0.005? Is anyone else able to reproduce this…
Nyxynyx
  • 61,411
  • 155
  • 482
  • 830
5
votes
0 answers

Nolearn/Lasagne neural network not starting training

I am using Theano 0.7, nolearn 0.6adev and lasagne 0.2.dev1 to train a neural net on GPU (in an IPython 3.2.1 notebook). However, because of the first layer ('reduc'), the following network does not start training, aven after waiting a few…
P. Camilleri
  • 12,664
  • 7
  • 41
  • 76
5
votes
3 answers

How to define a cost function in nolearn, lasagne?

I'm doing a neural network in nolearn, a Theano based library that uses lasagne. I'm not understanding how do I define my own cost function. The output layer is only 3 neurons [0, 1, 2] and I want it to be mostly sure when it gives 1 or 2, but…
jbssm
  • 6,861
  • 13
  • 54
  • 81
3
votes
1 answer

Cutoff on Neural Network regression predictions

Context: I have a set of documents, each of them with two associated probability values: probability to belong to class A or and probability to belong to class B. The classes are mutually exclusive, and the probabilities add up to one. So, for…
Álvaro Marco
  • 2,029
  • 17
  • 29
3
votes
1 answer

nolearn 0.5 are not compatible with lasagne 0.1 or 0.2?

When I want to import: from nolearn.lasagne import NeuralNet I always got this error "cannot import name mse". My Theano version is 0.7.0.
Kun
  • 581
  • 1
  • 5
  • 27
2
votes
0 answers

'DataFrame' object has no attribute 'data' but I have added it in my dataset

I was following this tutorial on using deep belief networks https://www.pyimagesearch.com/2014/09/22/getting-started-deep-learning-python/ then I decided to attach my external dataset and I get the following error : Traceback (most recent call…
LUNATIC
  • 21
  • 5
2
votes
1 answer

Convolutional Neural Network - Visualizing weights

Main Problem I cannot understand the Plot of the weights of a specific layer. I used a method from no-learn : plot_conv_weights(layer, figsize=(6, 6)) Im using lasagne as my neural-network library. The plot comes out fine, but I dont know how i…
KenobiBastila
  • 539
  • 4
  • 16
  • 52
2
votes
1 answer

How is this class's __call__ method working, when it's called without proper arguments?

I'm going through Daniel Nouri's tutorial on facial recognition using CNN's, and I've come across a bit of the code which I don't understand. Daniel is defining a Class to be called at the end of each iteration during the training of the network,…
Isaiah Becker-Mayer
  • 171
  • 2
  • 3
2
votes
0 answers

Working with Theano and Lasagne AttributeError

Now i'm working with then and lasagne. I have .csv input file with named emotions, and coordinates of them on photo. I'n trying to teach neural net to understand emotion by coordinates. When i'm parsing .csv file to then variables, and giving it to…
Константин Фомин
  • 21
  • 2
2
votes
0 answers

Full CNN - Is it possible to implement in (nolearn) Lasagne?

I am currently working with a very simple CNN and I am trying to figure out a way to make it into a Full CNN. By Full I mean not having any Dense layer and instead implement a deconvnet. The deconvnet part will be used as a localization part of the…
Saudin Botonjic
  • 21
  • 2
2
votes
0 answers

Unset trainable attributes for parameters in lasagne / nolearn neural networks

I'm implementing a convolutional neural network using lasagne nolearn. I'd like to fix some parameters that prelearned. How can I set some layers untrainable? Actually, though I removed 'trainable' attribute of some layers, the number shown in the…
Naoaki ONO
  • 91
  • 1
  • 3
2
votes
3 answers

Realtime Data augmentation in Lasagne

I need to do realtime augmentation on my dataset for input to CNN, but i am having a really tough time finding suitable libraries for it. I have tried caffe but the DataTransform doesn't support many realtime augmentations like rotating etc. So for…
whitewalker
  • 433
  • 2
  • 6
  • 13
1
2 3