Questions tagged [convolutional-neural-network]

A convolutional neural network is a form of neural network with an additional convolutional layer, typically used in image & audio analysis. The convolutional layer is essentially a filtering stage defined by the kernel which is used. For example, a convolutional layer could have a kernel which extracts edges from an image towards the goal of learning which objects are in a scene.

Filter by
Sorted by
Tagged with
4
votes
2answers
6k views

What is the shape of conv3d and conv3d_transpose?

I want to do a GAN with coloured pictures. This means I need a three dimensional input and therefore I like to use conv3d and conv3d_transpose. Unfortunately in the TensorFlow documentation, I can't ...
4
votes
2answers
610 views

Why are results without Transfer Learning better than with Transfer Learning?

I developed a neural network for license plate recognition and used the EfficientNet architecture (https://keras.io/api/applications/efficientnet/#efficientnetb0-function) with and without pretrained ...
4
votes
1answer
32 views

Can you use fully convolutional networks for binary classification?

I know that fully convolutional networks can be used for image segmentation and similar but I wondered if you could also apply them to simple image classification tasks. And if so, what is the proper ...
4
votes
2answers
35 views

What is the benefit of using Max pooling in convnets as opposed to just using convolution layers? (from Francois Chollet's Deep Learning with Python)

I am reading Francois Chollet's Deep learning with python, and I came across a section about max pooling that's really giving me trouble. I simply don't understand what he means when he talks about "...
4
votes
4answers
1k views

What is the state-of-the art ANN architecture for MNIST?

What is actually the best neural network architecture for the classic MNIST digit classifying task? I couldn't find any that would claim to be the winner...
4
votes
1answer
285 views

Why do CNNs with ReLU learn that well?

Convolutional Neural Networks (CNNs) use almost always the rectified linear activation function (ReLU): $$f(x) = max(0, x)$$ However, the derivative of this function is $$f'(x) = \begin{cases} 0 &...
4
votes
1answer
751 views

CNN computing time on good CPU vs cheap GPU

I am a researcher working on my first deep learning project, which consists of using a CNN (pre-trained VGG16+2 densely connected layers) to classify drone imagery of vegetation. In trying to hack ...
4
votes
1answer
4k 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 ...
4
votes
1answer
2k views

How to implement PCA color augmentation as discussed in AlexNet

I read through "ImageNet Classification with Deep Convolutional Neural Networks" again specifically for details on how to implement PCA color augmentation. I am unsure if I have it right. ...
4
votes
1answer
1k views

CNN Multi-class vs Binary Class Image Classification

Suppose we have a training set of 3 classes of image: 1.Cats, 2.Dogs, 3.Neither cats nor dogs. We're only really bothered about detecting whether an image is a cat/dog, or neither, but we don't care ...
4
votes
1answer
3k views

What is the best architecture for Auto-Encoder for image reconstruction?

I am trying to use Convultional Auto-Encoder for its latent space (embedding layer), specifically, I want to use the embedding for K-nearest neighbor search in the latent space (similar idea to ...
4
votes
1answer
51 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 ...
4
votes
3answers
6k views

Number of Fully connected layers in standard CNNs

I have a question targeting some basics of CNN. I came across various CNN networks like AlexNet, GoogLeNet and LeNet. I read at a lot of places that AlexNet has 3 Fully Connected layers with 4096, ...
4
votes
2answers
478 views

How does inception decrease the computational cost?

From the second paragraph of 3.1 Factorization into smaller convolution in the paper Rethinking the inception architecture for computer vision: This setup clearly reduces the parameter count by ...
4
votes
1answer
2k views

Why is the learning rate for the bias usually twice as large as the the LR for the weights?

I've noticed in a few caffe models I've been working with that the learning rate for the bias is often set to be twice that of the one for the weights. Another user mentions that this is the case in ...
4
votes
1answer
634 views

Training a CNN with limited weight sharing

I am currently working with speech recognition, in which i would like to try to use CNN instead of the normal feature extraction step. I been reading this paper which proposes method using cnn. The ...
4
votes
0answers
431 views

1D CNN Variational Autoencoder Conv1D Size

I am trying to create a 1D variational autoencoder to take in a 931x1 vector as input, but I have been having trouble with two things: Getting the output size of 931, since maxpooling and upsampling ...
4
votes
0answers
314 views

How to detect vanishing and exploding gradients with Tensorboard?

I have two "sub-questions" 1) How can I detect vanishing or exploding gradients with Tensorboard, given the fact that currently write_grads=True is deprecated in the Tensorboard callback as per "un-...
4
votes
1answer
743 views

How to use PCA in CNN for image recognition using Keras?

I created a CNN model for image classification and I want to use Principal Component Analysis (PCA) but when I run pca.fit() code, the code still running for hours ...
4
votes
0answers
4k views

Memory problems with smaller CNN [closed]

Hello everyone I'm having a weird problem. I having problem with one of two models I've been using. Models take an image data as input and outputs joystick and keyboard information. A simple CNN, ...
4
votes
0answers
269 views

how to propagate error from convolutional layer to previous layer?

I've been trying to implement a simple convolutional neural network. But I've been stuck at this problem for over a week. To be specific, assume there are 3 layers in a convolutional pass, marked as ...
4
votes
2answers
611 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?...
3
votes
2answers
178 views

Why are my predictions bad, if my accuracy in train is roughly 100% (Keras CNN)

In my CNN i have to handle 2 classes in a binary system, I have 700 images each class to train, and others to validation. This is my train.py: ...
3
votes
1answer
2k 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
2answers
659 views

Did anybody ever use mean pooling and publish it?

I found a couple of sources which mention mean pooling for convolutional neural networks (CNNs) - including all lectures I had about CNNs so far - but I could not find any paper with at least 10 ...
3
votes
1answer
5k views

Can I use the Softmax function with a binary classification in deep learning?

I want to create a deep learning model (CNN) for binary classification, can I used the softmax function instead of the sigmoid function in binary classification? Adding the classification layer to ...
3
votes
1answer
916 views

How is the evaluation setup for YouTube faces of FaceNet?

The YouTube Faces database (YTF) consists of 3,425 videos of 1,595 different people. Given two videos, the task for YTF is to decide if they contain the same person or not. Having $n$ comparisons, the ...
3
votes
2answers
3k views

Is Flatten() layer in keras necessary?

In CNN transfer learning, after applying convolution and pooling,is Flatten() layer necessary? I have seen an example where after removing top layer of a vgg16 ,first applied layer was ...
3
votes
1answer
988 views

How to make a region of interest proposal from convolutional feature maps?

Problem Keras does not have any direct implementation of region of interest pooling. I am aware of how to perform maxpooling, but I don't know how to get bounding boxes from feature maps passed from ...
3
votes
1answer
2k views

CNN backpropagation between layers

I have this CNN architecture: I know how to calculate error for weights based on the output and update weights between output<-->hidden and hidden<-->input layers. The problem is that I have ...
3
votes
1answer
10k views

How Can I Compute Information-Gain for Continuous- Valued Attributes

Decision trees handle only discrete values, but the continuous values we need to transform to discrete. My question is HOW? I know the steps which are: Sort the value A in increasing order. Find ...
3
votes
1answer
111 views

Why do the deconv outputs of layer >= 2 of Zeiler&Fergus look so unrealistic?

Reading the Zeiler&Fergus paper (my summary), I wonder how exactly they trained the deconv net. What was their data? I think for one CNN which they want to analyze, they train exactly one deconv ...
3
votes
1answer
128 views

How do CNNs use a model and find the object(s) desired?

Background: I'm studying CNN's outside of my undergraduate CS course on ML. I have a few questions related to CNNs. 1) When training a CNN, we desire tightly bounded/cropped images of the desired ...
3
votes
1answer
30 views

Does a Convolutional Layer in a Neural Network learn the correlation between its input signals via its kernel?

I am interested in the theory behing what a convolutional neural network learns with its convolutional operations. I think it learns (useful) kernels which measure the correlation between its input ...
3
votes
1answer
339 views

Why can't I use data augmentation with a pretrained convnet?

Reading Deep Learning with Python by François Chollet. In section 5.3.1, we've instantiated a pretrained convnet, VGG16, and are given two options to proceed: A) Running the convolutional base over ...
3
votes
1answer
1k 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 (...
3
votes
2answers
2k views

Different number of images in classes

I am working on a 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 classes have 5 images and ...
3
votes
1answer
6k 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 ...
3
votes
1answer
1k views

How to apply my deep learning model to a new dataset?

I am doing semantic segmentation (multi-class classification of image pixels) using convolutional neural networks (CNN) in Keras. In particular, I am applying this to aerial images of crops (...
3
votes
1answer
2k views

Layer notation for convolutional neural networks

When reading about convolutional neural networks (CNNs), I often come across a special notation used in the community and in scientific papers, describing the architecture of the network in terms of ...
3
votes
3answers
941 views

How does “ Sparsity of connections” in CNNs causes the network to have less parameters?

I am studying Andrew NG's lectures on Convolutional Neural Network and he had provided two reasons for CNNs having less parameters compared to Non-Convolutional networks . They are : Parameter ...
3
votes
1answer
1k views

How to combine different models in Keras?

I have a pre-trained network, consist of two parts, the feature extraction, and the similarity learning. The network takes two inputs and predicts the images are same or not. The feature extraction ...
3
votes
2answers
929 views

Does CNN take care of zoom in images?

Suppose a convolution neural network is trained on small images of an object, say flower, as in following 3 training images: Will this CNN correctly classify if the same object is present in zoomed ...
3
votes
1answer
983 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% ...
3
votes
1answer
203 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
2answers
164 views

What to do when facial recognition fails to find a face?

I am currently implementing a CNN to recognise the identity of people given a portrait picture of the person. The objective is to maximise the clf.score function in sklearn, the database is composed ...
3
votes
1answer
87 views

Problem designing CNN network

I seem to have a problem modelling my CNN network. I want to extract from features vector from different sized images. Whats consistent with the images is the y-axis, and the color dimension, but ...
3
votes
2answers
7k views

How does strided deconvolution works?

I am trying to understand how the shape of the image changes after deconvolution ? I am trying to understand the example code of convolutional autoencoder from neon. ...
3
votes
1answer
704 views

What do positive and negative gradient values mean for Convolutional Neural Network?

As we have the typicall pass of the neural network we make a forawrd pass to predict classes and then we have cost function and based on that we calculate gradients. I'm wondering what are the ...
3
votes
1answer
85 views

Does it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?

this is my first machine learning project and actually also my first question here. I am a novice to machine learning with a background in theoretical physics. I want to use a CNN to detect scratches ...

1 2
3
4 5
12