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
0
votes
1 answer
Using the deep neural network package "Chainer" to train a simple dataset
I'm trying to use the chainer package for a large project I'm working on. I have read through the tutorial on their website which gives an example of applying it to the MNIST dataset, but it doesn't seem to scale easily to other examples, and…
Keir Simmons
- 1,634
- 7
- 21
- 37
0
votes
1 answer
Chainer’s Sample code
I rewrote the chainer's MNIST sample code myself. But error occurred.
self.trainer.run()
'int' object is not callable'
All code here.
# main.py
from __future__ import print_function
import MultiLayerPerceptron
import chainer
import…
Rlia
- 1
- 1
0
votes
1 answer
Best practice for predicting values from model with Chainer
With Chainer, I have created model.pkl with Iris Datasets (https://github.com/silwyb/train-iris). So I can evaluate datasets, but I don't know the best way to output predicted values.
Please tell me how to predict. Just a function name would also…
silwyb
- 19
- 1
0
votes
1 answer
CUDARuntimeError with Chainer
chainer.cuda.available
and
chainer.cuda.cudnn_enabled
both return 'True'.
But when I try
cuda.to_gpu(data, 1)
it gives the following error -
CUDARuntimeError Traceback (most recent call…
shreez
- 21
- 1
- 3
0
votes
1 answer
Chainer: Cannot deserialize
Using chainer, I have model learn ptb text. Then, serialized model and optimizer. However, I cannot deserialize them.
If you know why please tell me.
import chainer
from chainer import serializers
# codes used for serializing
#…
Shion Yamaguchi
- 601
- 2
- 8
- 16
-1
votes
1 answer
How can I fix dimension i got the same error even i edit dtype with int32 or float32?
How can I fix this problem please?
dtype_attr = getattr(initializer, 'dtype', None)
if dtype is not None and dtype_attr is not None \
and numpy.dtype(dtype) != numpy.dtype(dtype_attr):
raise ValueError(
'dtype mismatch: {} !=…
Safa Mathlouthi
- 11
- 3
-1
votes
2 answers
Cuda Runtime Error cudaErrorNoDevice: no CUDA-capable device is detected
I am using Chainer, Cupy for CUDA 8.0 .
I am trying to train machine learning model using python3.5 script, but I got this error:
cupy.cuda.runtime.CUDARuntimeError: cudaErrorNoDevice: no CUDA-capable
What can I do to solve it?
Environment…
Harshal Bhamare
- 53
- 1
- 1
- 8
-1
votes
1 answer
Inference for binary image classification
This a classification process for blood cells. I have 2 classes: Mononuclear and Polynuclear. The training is done. X_test is the image array and y_test is the label array. I am trying to predict the label of a single input image.
I have changed the…
TulakHord
- 422
- 7
- 15
-1
votes
1 answer
MultiprocessIterator doesn't work
I am using MultiprocessIterator from chainer to train an NN. The code is here.
The results are:
nproc = 1, 307.65s
nproc = 4, 318.85s
nproc = 8, 302.91s
nproc = 16, 318.18s
System info:
Ubuntu 14.04.5 LTS (GNU/Linux 4.4.0-104-generic…
cmjdxy
- 396
- 1
- 2
- 15
-1
votes
1 answer
multilayer RNN with chainer (LSTM)
I'm able now to create and teach single layer rnn-s with Chainer, but I run into errors when I try to expand my network.
Here is my code, I commented out the 2. hidden layer part, so this should run as a single layer net
#Regression
class…
Basic Human Being
- 93
- 10
-1
votes
1 answer
Theano / Chainer Reporting Not Reporting Correct Free VRAM on K80 with 12GB RAM
System:
Ubuntu 16.04.2
cudnn 5.1, CUDA 8.0
I have theano installed from git (latest version).
When I run the generate sample from https://github.com/yusuketomoto/chainer-fast-neuralstyle/tree/resize-conv, it reports back out of memory whether CPU or…
Chris
- 988
- 3
- 18
- 30
-1
votes
1 answer
How to install chainer on Bluemix?
I want to use chainer on Bluemix.
Can someone provide me how to install chainer on bluemix ?
hyodo
- 1
-2
votes
1 answer
tuple index out of range (Python + Chainer)
I am new and a very beginner of coding.
Currently, I am planing to program an autoencoder for the features reduction by myself.
Although I spent most of my time solving the error I got by taking a look at web sites and books, I am still suffering…
user9690450
- 57
- 8
-2
votes
1 answer
how to use chainer.using_config to stop F.dropout in evaluate/predict process in chainer?
F.dropout is only used in train, I confused how to use chainer.using_config in it?
How does it works and chainer how to know it is in training or predict?
machen
- 283
- 2
- 10