Questions tagged [convnet]

For questions regarding "Convolutional Neural Networks" (CNN)

Filter by
Sorted by
Tagged with
5
votes
1answer
209 views

Data augmentation parameters

When I use data augmentation to increase the train dataset, should I use all augmentation techniques (parameters in keras)? Which data augmentation parameters should use with flow_from_directory?
9
votes
1answer
549 views

keras' ModelCheckpoint not working

I'm trying to train a model in keras and I'm using ModelCheckpoint to save the best model according to a monitored validation metric (in my case the Jaccard index). While I can see the model ...
5
votes
1answer
4k views

Optimizer for Convolutional neural network

What is the best optimizer for Convolutional neural network (CNN)? Can I use RMSProp for CNN or only for RNN?
3
votes
1answer
757 views

Data augmentation in deep learning

I am working on a deep learning project for face recognition. I am using the pre-trained model VGG16. The dataset has around 100 classes, and each class have 80 images. I split the dataset 60% ...
7
votes
1answer
91 views

CNN or Viola-Jones for facial detection

I was wondering since CNNs have dominated every image-related task. Is the Viola-Jones face detector still considered state-of-the-art, or have CNNs surpassed its performance?
3
votes
2answers
2k views

Data augmentation: ImageDataGenerator vs openCV

I would like to increase the data in my dataset to create a CNN deep learning classification model. Which is better for the model, using data augmentation by ...
7
votes
2answers
126 views

Neural Network Architecture for Identifying Image Copies

I have a large image collection and wish to identify the images within that collection that appear to copy other images from the collection. To give you a sense of the kinds of image pairs that I ...
2
votes
1answer
1k views

L2 regularization increase the loss rate of the deep learning model

When I add L2 regularization to my deep learning model the training and validation loss rate is increased. Why ????
3
votes
0answers
224 views

convolutional neural network with cross validation in Keras

I want to use K-fold cross-validation on my dataset of images. I am reading the data (images) from a directory. How do I use cross validation with convolutional neural network in Keras?
1
vote
0answers
13 views

Relationship between objects - ConvNets

Is there some interesting work on modeling relationship between objects in images? This seems like a natural extension to object detection/segmentation, but I couldn't find anything well-cited. I'm ...
2
votes
2answers
187 views

How to determine the number of the training images in Keras after data augmentaion?

I want to create a CNN model and I am using data augmentation. I want know the number of augmented images in Keras. How to determine the number of the training images in Keras after data augmentation?...
14
votes
1answer
6k views

What is the difference between upsampling and bi-linear upsampling in a CNN?

I am trying to understand this paper and am unsure of what bi-linear upsampling is. Can anyone explain this at a high-level? https://arxiv.org/abs/1606.00915
2
votes
0answers
158 views

Data augmentation / feature extraction on pre-trained convnets

I'm reading 'Deep Learning with Python' by François Chollet, which is an excellent book. He talks about using pre-trained convnets (in his example, VGG16) and then running smaller datasets to tweak ...
8
votes
1answer
187 views

data augmentation when using flow_from_directory in CNN

I want to use a small dataset to create CNN model. So, I am using data augmentation to increase the train dataset. Should I use all augmentation techniques (arguments) that listed here? I have ...
1
vote
0answers
865 views

Triplet loss - what threshold to use to detect similarity between two embeddings?

I have trained my triplet loss model using FaceNet's architecture. I used 11k hands dataset. Now I want to see how well my model performed, so I feed it 2 images of the same class and get back their ...
2
votes
1answer
76 views

Resource and useful tips on Transfer Learning in NLP

I have a few label data for training and testing a DNN. Main purpose of my work is to train a model which can do a binary classification of text. And for this purpose, I have around 3000 label data ...
1
vote
0answers
36 views

How to calculate the level of sparsity of a deep learning model (CNN/MLP)? [closed]

Recently I am studying on the sparsity of the deep learning model (CNN/MLP). I am using Tensorflow as the framework to build the models, but how to calculate the level of the sparsity of each ReLU ...
1
vote
0answers
289 views

TensorFlow restored model returning constant negative prediction

I've trained a CNN model using Google Colab with TensorFlow. It is a pretty basic CNN: ...
1
vote
0answers
29 views

Detecting directions using Convolutional neural networks [closed]

I am working on a task where I have to detect damages on the vehicles and exactly where the damage has occurred. So I have to not only detect the damage on the door but also mentioned which door(front ...
2
votes
0answers
282 views

Tensorflow CNN sometimes converges, sometimes not

originally asked on stackoverflow, deleted Im having trouble traing a convolutional neural network in tensorflow. When I start my program, sometimes the model learns nicely (cost/cross_entropy goes ...
0
votes
1answer
433 views

Keras cNN Transfer Model: Reduce Final Model Size?

I'm working with multiple cNNs to be ran on mobile devices. If I create these cNNs from scratch (black n white, 256x256), I'm able to produce a binary classification model of about 10mb, which is a ...
0
votes
1answer
33 views

CNN only performs well when split into 2 models [closed]

I have 2 groups of data of equal shape (the main difference between the 2 are that one has half as many features - and consequently different labels of course)that perform better when they are trained ...
2
votes
1answer
155 views

MLP conv layers

When should MLP conv layers be used instead of normal conv layers? Is there a consensus? Or is it the norm to try both and see which one performs better? I would love to better understand the ...
1
vote
0answers
16 views

Convolutional Neural Network with feature inputs also directly connected to fullly connected layers

Imagine you are trying to classify movie reviews you have both the actual review and also some information about the movie. I pass the actual review through a few convolutional layers and some max ...
0
votes
1answer
221 views

application of CNN in genomics

Since CNN has been widely applied in DNA sequence data, I'm wondering why CNN is not often used for predicting phenotype from SNP data, given that SNPs are essentially parts of DNA sequences and ...
2
votes
1answer
1k views

It is helpful to normalize target variables for a regression neural network?

It is customary to normalize feature variables and this normally does increase the performance of a neural network in particular a CNN. I was wondering if normalizing the target could also help ...
1
vote
2answers
159 views

What are the benefits and tradeoffs of a 1D conv vs a multi-input seq2seq LSTM model?

I have 6 sequences, s1,..,s6. Using all sequences I want to predict a binary vector q = [0,0,0,1,1,1,0,0,0,1,1,1,...], which is a mask of the activity of the 6 sequences. I have looked at seq2seq ...
2
votes
1answer
274 views

Display images after augmentation in Keras

How can I display all images after augmentation? How can I get the number of the trained data after augmentation? Thank you
1
vote
0answers
45 views

Resources for CNN example with Keras

Please provide me with excellent resources to learn deep learning with Keras, imbalance images classes and using imageGenerator, Transfer learning with Keras. Thank you
1
vote
2answers
783 views

Data augmentation based on the class type in the CNN model

I would like to use CNN model to classify images but some classes in my dataset have low amount of data. Can I apply data augmentation based on the number of the images in the class? For example, ...
1
vote
1answer
608 views

How to arrange the image dataset in CNN?

How do I arrange the image dataset in CNN? Should I put each image category in a separate folder? Or all of them in the same folder? Should the image name be the category name? I would like to see an ...
3
votes
1answer
40 views

Is there any work done on reconfigurable convolutional neural networks?

Convolutional Neural networks are used in supervised learning meaning models are always "set in stone" after training (architecture and paramters) so this might not even be possible, but is there any ...
1
vote
1answer
278 views

Loss function range normalization

This is from a referee report in a conference to which I submitted my paper - I don't quite get it and I'm not sure what I need to do about it. I use Euclidean loss and Softmax cross-entropy (...
0
votes
1answer
43 views

Using cloud to create CNN model

Are there any differences in the results of training the deep learning algorithm (CNN) using a device with a GPU and using any device with a cloud service such as AWS and Floydhub?
0
votes
2answers
217 views

Different number of images in classes

I am working on deep learning CNN project. The dataset contains more than 500 classes and the classes have different numbers of items (images). For example, some of the classses have 5 images and some ...
3
votes
1answer
3k views

Oscillating loss in CNN

So I designed my own CNN with 10 layers of convolutions and no maxpoolings or any other connections. When I ran it on a dataset I got the following loss curve (blue) the other one is accuracy vs ...
0
votes
1answer
273 views

The effect of the image type and the image conversion on deep learning CNN model

Does the type of the image affects (jpg, png, bmp) on the CNN deep learning algorithm? Dose converting the image type affects on the CNN deep learning algorithm (ex. converting bmp to jpg or ppm to ...
1
vote
0answers
198 views

Expected behaviour of loss and accuracy when using data augmentation

I have implemented a convolutional neural network in Keras, and I use off-line data augmentation in the training set. The way I do this is that I create batches of training data in separate files (...
2
votes
3answers
147 views

400 positive and 13000 negative: how to split dataset up (train, test, validation)

Working on a medical diagnostic convolutional neural networking problem, and it's not obvious (to me) how the dataset should be split up. Do I have enough data to split it in 3, or should I just have ...
0
votes
1answer
784 views

Subtracting grand mean from train and test images

I am building an image classifier based off the VGG_face keras implementation. It is easiest for me to extract a csv file full of the representations and then try classifiers on those representations. ...
1
vote
2answers
112 views

ML model to transform words

I build model that on input have correct word. On output there is possible word written by human (it contain some errors). My training dataset looks that: ...
2
votes
0answers
23 views

Contextual Object Detection

An example of what I'd like to do is identify the price of a product on a product page. While I can train a CNN to identify prices, it's likely that it would recognise every instance of a price on a ...
3
votes
1answer
119 views

Difficulty in choosing Hyperparameters for my CNN

My task is to estimate a person's age based on a face image of that person. To that end I'm using a CNN and at first stage I was based on the following article: DeepExpectation which uses a VGG16 ...
3
votes
1answer
544 views

Keras bug NasNetlarge no top

I am trying to use NasNetlarge in Keras without the top but I cant get rid of the top: ...
2
votes
2answers
49 views

how can I infer no target in a target classification problem based on deep learning?

Let's take the MNIST dataset (My application is different) with a lot of noise, I am going to train a deep NN to classify the letters. What's the right way to infer, there's no letter possibility? or ...
2
votes
1answer
66 views

Why don't convolutional computer vision networks use horizontally - symmetric filters?

If, for example, I have a neural network for classifying dog breeds, and I feed it an image of some dog, inherently it shouldn't matter whether I feed it the original image or the image, mirrored ...
2
votes
1answer
61 views

How to determine the number of forward and backward passes in deep learning (CNN)? [closed]

Is there a way to determine the number of forward and backward passes in the training of a neural network using python?
1
vote
1answer
546 views

Visualizing ConvNet filters using my own fine-tuned network resulting in a “NoneType” when running: K.gradients(loss, model.input)[0]

I have a fine-tuned network that I created which uses vgg16 as it's base. I am following section 5.4.2 Visualizing CovNet Filters in Deep Learning With Python (which is very similar to the guide on ...
4
votes
1answer
3k views

Keras intuition/guidelines for setting epochs and batch size

I'm using Python with Keras to make a convolutional neural network (CNN) for an image classifier. I took about 50 images of documents and 150 images of non-documents for training. I shrunk the ...
3
votes
0answers
3k views

Memory problems with smaller CNN

Hello everyone I'm having a weird problem. I got data that is the image and the output which is the joystick info and keyboard. The model that I don't have problems running out of memory(and crashing)...