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

Lasagne NN strange behavior with accuracy and weight convergence

!!NOT ABLE TO EXPLAIN WITHOU PICTURES!! I have a neural network, which i feed with text news, encoded with BagOfWOrds and labels {0,1}.I classify the text with convolutions. Everything seems to be working, but, in case that i have quoit a little…
user6557479
0
votes
0 answers

Neural Network Lasagne

I'm trying to build a convolutional neural network here is my code: def build_cnn(input_var=None): network = lasagne.layers.InputLayer(shape=(None ,1 ,700, 21), input_var=input_var) batchsize, seqlen, _, _…
Darth Veder
  • 159
  • 2
  • 11
0
votes
2 answers

Possible causes of CUDA get device properties error with Python3 / Theano?

I'm trying to use multiple GPUs with multiprocessing in Python3. I can run a simple test case, like the following: import theano import theano.tensor as T import multiprocessing as mp import time # import lasagne def target(): import…
Adam S.
  • 323
  • 3
  • 10
0
votes
0 answers

Can the values of the targets be NAN on multiple outputs neural network on lasagne?

Having a dataset for which 3 different outcomes exist, but there might be missing values for these outcomes, can neural networks training in lasagne deal with this NAN or should a neural network be trained for each outcome (where NAN cases are…
SwatchPuppy
  • 324
  • 1
  • 3
  • 15
0
votes
0 answers

Theano function with updates produces NAN output

my code looks like. output = lasagne.layers.get_output(output_layer) loss = function(output) * target loss = -(loss.sum()) params = lasagne.layers.get_all_params(output_layer) updates =…
xueliang liu
  • 556
  • 3
  • 13
0
votes
1 answer

How to impose weight symmetries in Lasagne

I'm working with Lasagne on a neural network. I want that on the first layer, the same weight is applied to many neurons of the input layer (and obviously I want that weights update considering the contribute of all these neurons) This because my…
Ginopinoshow
  • 81
  • 2
  • 9
0
votes
1 answer

Getting dimensions wrong when creating a feed-forward auto-encoder in Theano/Lasagne

I want to create a simple autoencoder with 3000 input, 2 hidden and 3000 output neurons: def build_autoencoder(input_var=None): l_in = InputLayer(shape=(None,3000), input_var=input_var) l_hid = DenseLayer( l_in, num_units=2, …
Romeo Kienzler
  • 3,373
  • 3
  • 36
  • 58
0
votes
1 answer

How to select the number of outputs of a nueral networks

I have a classification problem of characters. I have converted the charcters to ASCI values. How to select the number of outputs of a nueral network. Does it depend on the max vlaues of the yTrain.
Zohair Zahid
  • 119
  • 2
  • 15
0
votes
1 answer

Lasagne: neural Network Image(character) classification. Selection of size output_num_units

I am performing classification with the help of neural network used in danielnouri's blog post. The total size of the training data is 6300 samples. The data is 20*20 sized character pictures. I am unable to figure out how to select the size of…
Zohair Zahid
  • 119
  • 2
  • 15
0
votes
1 answer

Getting dimensions right for regression with lasagne

I'm trying to learn a network that outputs a value in the range -1.0..1.0. There are only six features so far, all floats. I'm having real trouble getting types and shapes aligned. So far I have: #!/usr/bin/env python3 import lasagne import numpy…
Leon Derczynski
  • 542
  • 5
  • 15
0
votes
1 answer

Trying to use ConcatLayer with different shape inputs

I am trying to work with nolearn and use the ConcatLayer to combine multiple inputs. It works great as long as every input has the same type and shape. I have three different types of inputs that will eventually produce a single scalar output…
Beaker
  • 2,804
  • 5
  • 33
  • 54
0
votes
2 answers

Adaptive learning rate Lasagne

I am using Lasagne and Theano library to build my own deep learning model following the MNIST example. Can anyone please tell me how the adaptively change the learning rate?
Avijit Dasgupta
  • 2,055
  • 3
  • 22
  • 36
0
votes
1 answer

Theano dataset dimensions error when passing into function

Using the the example network of a mlp with 2 hidden layers and two drop outs so my load_data() function has 400 rows of 20 features and my label dataset is just 400 rows of one variable that will be split into X_train X_test y_train_y_test and…
entercaspa
  • 674
  • 2
  • 7
  • 19
0
votes
1 answer

Lasagne/Theano mnist example issue

I'm trying to slightly change the code from github here to a toy example of reading a simpler two dimensional data. My toy data set has the following structure x-coordinate, y-coordinate, class Some example data points…
broccoli
  • 4,738
  • 10
  • 42
  • 54
0
votes
0 answers

Using convolution layers then recurrent layers in Lasagne

I'm trying to implement a neural network that takes the input of musical note/pitch on one axis and octave of that note on the other axis. The input is supposed to go through a convolution layer (Conv2DLayer). After convolution, the outputs should…
Saif Ur Rehman
  • 338
  • 3
  • 14
1 2 3
…
13 14