Stack Overflow
Stack Overflow

Questions tagged [chainer]

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

194 questions
0
votes
0 answers

Building layer wise model for Encoding-Decoding Image

I am writing an autoencoder model for an image encoding-decoding problem. I want to understand the node distribution in each layer of the model suitable for images. For the below code I am using 10 images of shape (21*28*3). class…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

Stacked Autoencoder

I have a basic autoencoder structure. I want to change it to a stacked autoencoder. From what I know the stacked AE differs in 2 ways: It is made up of layers of sparse vanilla AEs It does layer-wise training. I want to know if sparsity is a…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

Chainer Autoencoder

I am trying to write a vanilla autoencoder for compressing 13 images. However I am getting the following error: ValueError: train argument is not supported anymore. Use chainer.using_config The shape of images is (21,28,3). filelist = 'ex1.png',…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

How to convert padded sequence tensor to expected RNN format?

I have a tensor of shape (batch_size, max_sequence_length, embedding_size) that is padded to maximum length to store sequences. I also have (batch_size, max_sequence_length, vocab), for example: # Batch size many, (batch_size, 4,…
nuric
  • 11,027
  • 3
  • 27
  • 42
0
votes
1 answer

VOCBboxDataset returns incorrect dataset size when applied to my dataset

I have a 250 image dataset and 250 annotation files with two classes: ball and player. The folder also has three text files train.txt, val.txt, test.txt containing lists of training,testing and validation images respectively. bball_labels =…
TulakHord
  • 422
  • 7
  • 15
0
votes
3 answers

MultiprocessIterator throws error when changing batch_size

I want to train a Faster R-CNN with ChainerCV. As a first test I mostly copied the provided example, I only changed the lines corresponding the dataset to use my custom dataset. I checked if my dataset is fully functional with all operations…
tdiekel
  • 21
  • 6
0
votes
2 answers

Training Code for a CNN model written in Chainer

I am writing the training code for TwoStream-IQA which is a two-stream convolutional neural network. This model predicts the quality score for the patches being assessed through two streams of the network. In the training below, I have used test…
sana
  • 410
  • 2
  • 6
  • 24
0
votes
1 answer

How to convert this Keras code to Chainer code? (LSTM Autoencoder)

Here, I have LSTM Autoencoder written in Keras. I want to convert the code to Chainer. import numpy as np from keras.layers import Input, GRU from keras.models import Model input_feat = Input(shape=(30, 2000)) l = GRU( 100, return_sequences=True,…
Sakurai.JJ
  • 553
  • 3
  • 10
0
votes
1 answer

How can I use binary_cross_entropy in binary classification in Chainer

I have train dataset of 8000 images and labels. Validation set consists of 1957 images and labels. The test set contains 2487 images. Each image contains White Blood Cell images. WBC is divided innto 4 categories: Eosinophil, Neutrophil, Monocyte…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

Inference code for prediction in multi-class image classification

I am trying to take a single input image and predict its label. Training data image was converted to array and labels to int and made into a single dataset using DatasetMixin before feeding into classifier. So I have converted the image into…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

While training epoch details are not updated and does not complete all eochs

I am training blood cell images using chainer. While training the epoch details doesn't get updated and does not run the given set of epochs. I want to understand the cause of this problem.. When the training is interrupted and restarted only a…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

Chainer CNN- TypeError: forward() missing 1 required positional argument: 'x'

I'm trying to run a classifier on Chainer, but failed due to the following error. I have no idea about the error, because I confirmed that the iterator actually sent a batch to the trainer. Is there a problem with the neural network model? Or, the…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

cupy.cuda.cudnn.CuDNNError: CUDNN_STATUS_INTERNAL_ERROR

My cupy and chainer versions are as follows Chainer: 4.1.0 NumPy: 1.15.4 CuPy: CuPy Version : 4.1.0 CUDA Root : /usr/local/cuda-9.0 CUDA Build Version : 9000 CUDA Driver Version : 9020 CUDA Runtime Version :…
Rahul
  • 41
  • 6
0
votes
1 answer

AtrributeError MomentSGD optimizer has no attribute prepare

Recently, I run the code released by other authors. They utilized chainer v1.3, but I installed v4. When I run the code, it errors that Attribute Errors: MomentSGD optimizer has no attribute prepare. Here I post the codes of this part: class…
Meng Liu
  • 1
0
votes
1 answer

Data size varies in every epoch

I've written a program using "Chainer" to train my model, the data is coming from another function where I am using Python's yield. What I have observed is the size of data changes in every epoch. def load(file_path): with codecs.open(path, 'r',…
Gurpreet.S
  • 125
  • 2
  • 8
1 2 3
…
12 13