Chainer is an open source deep learning framework written in Python.
Chainer
A Powerful, Flexible, and Intuitive Framework for Neural Networks
For more info see chainer.org
Questions tagged [chainer]
194 questions
1
vote
2 answers
TypeError: numpy.ndarray or cuda.ndarray are expected
I want to train Convolution3d model in chainer. In my training roop, I have this error.
TypeError: numpy.ndarray or cuda.ndarray are expected.
I thought the reason for the error was that the input was a list.
So,I changed input array to numpy…
musako
- 897
- 2
- 10
- 26
1
vote
1 answer
TypeError: Argument 'x' has incorrect type (expected cupy.core.core.ndarray, got numpy.ndarray)
Executing the following minimal example in cupy.
import numpy, cupy, cupyx
print( cupyx.get_runtime_info() )
mydata = numpy.empty((3,), dtype='f')
#gpu = False
gpu = True
if not gpu:
xp = numpy
else:
xp = cupy
mydata_like =…
navneeth
- 1,239
- 12
- 21
1
vote
0 answers
Chainer and float64 support
I want to know how to make chainer support float64 precision calculations. Below is my simple Autoencoder code I wrote in chainer. Initially I was running it with float32 dtype but now I want to test out float64 precision how do I do that ?
class…
Kanmani
- 479
- 7
- 21
1
vote
1 answer
Creating a Dataset to input only Images
I need a dataset object that contains only images for unsupervised learning in Chainer framework. I am trying to use DatasetMixin for this purpose.
Images is a list containing images.
class SimpleDataset(dataset.DatasetMixin):
def __init__(self,…
TulakHord
- 422
- 7
- 15
1
vote
1 answer
Calculating number and size of filters for given input size
I have an autoencoder to regenerate input images. The image shape is (10, 1308608). 1308608 is 4*644*508.
class AutoEncoder(chainer.Chain):
def __init__(self, input_size, n_filters, n_units, filter_size,
activation):
self.activation =…
TulakHord
- 422
- 7
- 15
1
vote
1 answer
Regression with chainer
How can I do regression with Chainer?
Just replacing the usual L.Classifier with a loss function like F.mean_squared_error does not work, e.g.
from chainer import iterators, optimizers, training
from chainer import Chain
from chainer.datasets import…
cheersmate
- 2,385
- 4
- 19
- 32
1
vote
1 answer
PyTorch and Chainer implementations of the Linear layer- are they equivalent?
I want to use a Linear, Fully-Connected Layer as one of the input layers in my network. The input has shape (batch_size, in_channels, num_samples). It is based on the Tacotron paper: https://arxiv.org/pdf/1703.10135.pdf, the Enocder prenet part.
It…
dkwasny
- 13
- 2
1
vote
1 answer
cupy.cuda.runtime.CUDARuntimeError: cudaErrorInsufficientDriver
I try to reproduce some codes with chainer. However, there is something wrong with cuda setting.
I used the conda environment with python 3.5 and ubuntu16.04. I used chainer 5.4.0 and cupy 5.4.0.
When I used "cupy.show_config()", the result…
yangpaopao
- 11
- 1
1
vote
1 answer
CuDNN is not available in binary-installed cupy
I installed Cupy using the binary package cupy-cuda92, but CuDNN is not loaded.
$ pip install cupy-cuda92==5.4.0 chainer==5.4.0
$ python -c 'import chainer;…
Keisuke
- 86
- 4
1
vote
0 answers
Chainer - Python - CUDA_ERROR_INVALID_SOURCE
I have a machine with two different GPUs (one RTX and one Titan V) and often it fails to run tasks. This behaviour is mostly observed in GPU with id=1.
The same task can be run successfully in a different machine or GPU with id=0.
The precise…
GrigorisG
- 888
- 8
- 13
1
vote
1 answer
Chainer module 'cupy.cudnn' has no attribute 'softmax_forward'
I am trying to run neural network on chainer by GPU. but it seems to be just not working.
I tried some version of cuda already, 9.0, 10.1, 10.0. Before I had some problem cupy installation. Now I am just install cupy through Anaconda…
Dale Lin
- 11
- 3
1
vote
1 answer
Invalid operation is performed in: LinearFunction (Forward)
this is the main code. The images size is 420*420
import os
import chainer
from chainer import training
from chainer.training import extensions
batchsize = 64
epoch = 10
gpu = 0
dataset = "/content/gdrive/My Drive/images/"
out =…
evgeni fotia
- 4,650
- 3
- 16
- 34
1
vote
1 answer
Validation accuracy dropping in CNN Chainer
I am classifying cell images using CNN in Chainer. The validation accuracy of the model is dropping along with the rise of main/training accuracy. I want to know why the validation accuracy is decreasing and what are the ways to increase the…
TulakHord
- 422
- 7
- 15
1
vote
1 answer
How to load multiple matrices into a Chainer model using the iterator interface?
I have a question regarding Chainer's iterator interface, and how it interfaces with a Trainer, Updater and Model.
My data are graphs, and hence are of varying matrix shapes. I have concatenated the features matrix into one large dense matrix,…
ericmjl
- 13,541
- 12
- 51
- 80
1
vote
1 answer
Batchsize in input shape of chainer CNN
I have a training set of 9957 images. The training set has shape (9957, 3, 60, 80).
Is batchsize required when putting training set to model?
If required can the original shape be considered correct for fitting to conv2D layer or do I need to add…
Athirooban
- 11
- 1