Stack Overflow
Stack Overflow

Questions tagged [lasagne]

Lasagne provides a high-level API for creating neural networks using Theano on the backend. Questions about lasagne do not need to also utilize the "theano" tag, unless the question is specifically about Lasagne-Theano integration or the Theano backend.

Lasagne is a Python package build around expressions for neural networks training. was designed as a high-level API on top of , with the intention of making rapid prototyping of neural network architectures easier. It is similar in spirit to , which is built as a high-level API on top of //, although the main difference is that Lasagne implements only one backend, allowing it to integrate more deeply with Theano features.

Resources

Resources and Teaching

Implementations of Network Architectures

204 questions
0
votes
0 answers

ImportError: Could not import Theano

Hi i'm now newbie in studying machine-learning and i want to do some sample code. When i want to run this code : import lasagne from lasagne import layers from lasagne.updates import nesterov_momentum from nolearn.lasagne import NeuralNet from…
min jung Ha
  • 31
  • 2
0
votes
1 answer

Lasagne LSTM regression produces zerros as output

Inspired by Andrej Karpathy's blog i wanted to make my own version of a recurrent neural network that selects the next word instead of character. Because of the number of different words in a text is so many, i used word2vec to represent the words…
Søren Jensen
  • 153
  • 1
  • 12
0
votes
2 answers

How do I install Theano and Lasagne in Anaconda (Jupyter)?

I have been trying to install Lasagne and Theano in Anaconda (Jupyter) on MacOS Sierra (10.12.3) to use this neural network: neural-storyteller However when I try to import them in Jupyter: import lasagne import theano I get this error: ImportError…
Thinkertinkerpete
  • 1
  • 1
  • 2
0
votes
1 answer

Handling input when combining different ground truth for end-to-end CNNs

I am hoping to design a single end-to-end CNN to extract three features: segmentation and bifurcation for thing A, and detection for thing B. There will be a common weight trunk and then three branches with their own weights for the three feature…
Rhiu
  • 35
  • 6
0
votes
1 answer

Lasagne layer whose output shape depends on the input value and not its input shape

I am working on a project with lasagne and theano and need to create a custom layer. The output of this layer does not however depend on the size of the input, but on the values of the input... I know that keras (only with the tensorflow backend)…
Andrei Costinescu
  • 20
  • 7
0
votes
1 answer

How to extract numpy arrays from Theano tensor?

We are working on an implementation of 3D Convolutional Neural Networks for segmentation of 3D medical images. We have built a network with Lasagne and Theano, which successfully builds a 5D tensor. We want to extract actual 'images' as 3D numpy…
anejaf
  • 3
  • 1
0
votes
1 answer

combining RNN and CNN with lasagne

I am trying to run a 1D CNN on 10s segments of EEG data and then cover a temporal connection between the segments using an RNN. The problem is, that the RNN expects input with batch_size x sequence_length x num_inputs while the CNN outputs…
skjerns
  • 1,905
  • 1
  • 16
  • 25
0
votes
1 answer

Using Theano and Lasagne with FIPS Enabled

I have the following: Python 2.7.5 RHEL 7.3 with FIPS enabled Lasagne (0.2.dev1) Theano (0.9.0) I installed Theano and Lasange with pip without issue, but when I import lasange I receive an error related to FIPS: $: python Python 2.7.5 (default,…
Daren Eiri
  • 137
  • 12
0
votes
0 answers

TypeError: object of type 'Image' has no len()

I am writing a program to train a convnet to colorize grey scale image to CIELab image. Following is how my code goes: with open('mypicklegrey.pickle','rb') as fgrey: X_train = pickle.load(fgrey) print ('data_grey') with…
Kshitija Hande
  • 1
  • 1
0
votes
1 answer

libgpuarray Test #10 and #11 fails

Problem I always have used theano normally. WIth CUDA and CUDNN and CNMEM. I have an XTITAN. Actually I ran my code on the university server. Im trying to install libgpuarray but the tests #10 and #11 fails. What should i do…
KenobiBastila
  • 539
  • 4
  • 16
  • 52
0
votes
0 answers

Theano CPU Multicore lower utilisation on a larger dataset

I have a Multilayer Perceptron code using Theano/Lasagne that when I run on a small dataset uses multiple cores correctly. But, when I run it over a much larger dataset (with the same code) and I watch CPU utilisation in htop, I don't see it…
Ash
  • 3,428
  • 1
  • 34
  • 44
0
votes
1 answer

Theano MiniBatch Iterator not working

Theano MiniBatch Iterator not working I coded a minibatch iterator to get predicted results from my neural network. However, i made some tests and noticed a few errors. Basically : If batch_size > amount of inputs : error I made a script to show…
KenobiBastila
  • 539
  • 4
  • 16
  • 52
0
votes
0 answers

Lasagne: L2 regularization on hidden layer returns NaN from loss function

I'm trying to put together a really simple 3-layer neural network in lasagne. 30 input neurons, 10-neuron hidden layer, 1-neuron output layer. I'm using the binary_crossentropy loss function and sigmoid nonlinearity. I want to put l1 regularization…
Matthew
  • 194
  • 1
  • 3
0
votes
1 answer

Theano/lasagne: how to predict with trained model

I am new to Theano and Lasagne. I followed the official doc and can walk through the tutorial successfully. However, I have few questions. What's the format of the saved model? what is .npz file? How to interpret it? np.savez('model.npz',…
Xing Zhou
  • 71
  • 1
  • 1
  • 6
0
votes
1 answer

How to store and read nolearn.lasagne NeuralNet models using pickle

How do I store the weights and biases in nolearn.lasagne NeuralNet model? From the documentation, I can't see how to access the NeuralNet's weights and biases and store them.
Kevin George
  • 119
  • 2
  • 13
1 2 3
…
13 14