Questions tagged [convolutional-neural-networks]
For questions about convolutional neural networks, also known as CNN or ConvNet.
-1
votes
0answers
7 views
Character Embeddings with CNN
I've read about character embeddings as suggested by Zhang, Zhao, and LeCun. These approaches takes a character stream as input. Would an encoder trained on just words, not complete texts, still be ...
0
votes
1answer
24 views
How to get a binary output from a Siamese Neural Network
I'm trying to train a Siamese network to check if two images are similar. My implementation is based on this. I find the Euclidian distance of the feature vectors(the final flattened layer of my CNN) ...
0
votes
2answers
27 views
Keras giving memory allocation error and running extremely slow
I am working on character recognition using convolutional neural networks. I have 9 layer model and 19990 training data and 4470 test data. But when I am using keras with Tensorflow backend. When I ...
1
vote
0answers
6 views
How to solve the AttributeError: 'Ssd' object has no attribute 'freeze_batchnorm'
I use a modified training script for modeling images with Tensorflow/Keras/Mobilenet_V2. After a few errors that I could solve I now get the following error:
...
-1
votes
0answers
10 views
Training a combined deep and shallow network
I want to train a combined deep and shallow neural network, say a 20 block ResNet, with a 2-layer dense network that takes the output of the ResNet and combines it with auxiliary input in the first ...
2
votes
1answer
35 views
How do randomly initialized neural networks behave?
I am wondering how the output of randomly initialized MLPs and ConvNets behave with respect to their inputs. Can anyone point to some analysis or explanation of this?
I am curious about this because ...
0
votes
0answers
11 views
Searching for an 'lost' article about image discrimination
I am searching for an article that I recently read its abstract, but cannot find the article itself anymore.
I think it was published recently and discusses how two NN are performing an image ...
2
votes
2answers
47 views
Can the same input for a plain neural network be used for a convolutional neural network?
Can the same input for a plain neural network be used for CNNs? Or does the input matrix need to be structured in a different way for CNNs compared to regular NNs?
0
votes
0answers
20 views
Small deeplearning dataset and architecture
I am doing some amateur research on training neural nets with alternative (non-SGD) approaches. Are there any known CNN architectures (other then Lenet-5), which have less number of parameters and ...
2
votes
0answers
30 views
How a game playing agent could identify potential objects and proximity?
Most implementations I'm seeing for playing games like Atari (usually similar to DeepMind's work using DQN) have 4 graphical frames of input fed into 3 convolutional layers which are then fed into a ...
0
votes
0answers
12 views
How to count people from Multi-column CNN density map?
In this paper, they use Multi-column Convolutional Neural Network (MCNN). The output of MCNN is density map (this is a matrix) and from this density map we can count the number of people.
My question ...
1
vote
1answer
23 views
Can I do oversampling by copying the same image multiple times? Will it effect my neural network accuracy?
I am working on an image data-set. As you may have guessed it is imbalanced data. I have 'Class A, 19,000 images' and 'Class B, 2,876 images'.
So I did an undersampling by removing randomly from the ...
1
vote
0answers
20 views
How to preprocess a modified dataset so that a fitted CNN makes correct predictions on an un-modified version of the dataset?
for a school project I have been given a dataset containing images of plants and weeds. The goal is to detect when there is a weed in the pictures. The training and validation sets have already been ...
1
vote
1answer
40 views
Most efficient neural network for human activity recognition
A paper from machinelearningmastery.com on human activity recognition states that 1D convolutional neural networks work the best on classification of human activities using data from accelometer. But, ...
0
votes
0answers
6 views
Creating a Semantic Segmentation Dataset for Transfer Learning
I intend to plan a pre-trained net for semantic segmentation. However, I need to include a couple of new classes for segmentation and hence I need a small new training dataset. I have a couple of ...
0
votes
0answers
11 views
Combining Two CNN's [migrated]
I Want to Combine Two CNN Into Just One In Keras, What I Mean Is that I Want The Neural Network To Take Two Images And Process Each One in Separate CNN, and Then Concatenate Them Together Into The ...
1
vote
1answer
25 views
Are commercially available neural ICs digital?
Apparently, one can buy a special-purpose integrated circuit (an IC like this one, for instance) to host a convolutional neural network.
QUESTION
Is such a circuit digital? Except for digital random-...
0
votes
1answer
7 views
Image prediction model when data-set classes have visual similarity
Lets say we have a data-set of all cats and we have to identify the cat breed based on given test image. As, the two different cat breeds have visual similarity can we use existing networks (VGG, ...
1
vote
0answers
19 views
Machine learning approach to facial recognition
First of all i'm very new to the field. maybe my question is a bit too naive of even trivial..
I'm currently trying to understand how can i go about recognizing different faces.
Here is what i tried ...
0
votes
0answers
10 views
How to add 2 new classes to trained Res50 Net(Keras)
I have 2 new collections of images, for example(just for example) cucumbers and tomatoes. I want to get 3 probabilities. Prob if img is a tomato, cucumbers, and the third prob for any another object. ...
0
votes
0answers
13 views
Simplified Inception-Resnet for small datasets
I trained a neural network for face recognition with triplet loss using the Inception-Resnet v1 architecture (see figure below, taken form the paper). However, since the dataset is very small compared ...
0
votes
1answer
26 views
How does the internal convolution Neural Network work?
I found the below image of how a CNN works but I don't really understand it. I do understand CNNs (I think) but I find this diagram very confusing.
My summarized, simplified understanding :
-...
0
votes
0answers
23 views
Is Mobilenet_V2 trained on the COCO dataset or on the ILSVRC-2012-CLS dataset better for classifying objects in aerial data? [migrated]
I would like to use a pretrained CNN Mobilenet_V2 for classifying objects in aerial data. Is Mobilenet_V2 trained on the COCO dataset suitable for classifying objects from aerial images or are there ...
1
vote
3answers
50 views
Features Map convolutional neural network
I have a question about convolutional neural newtork.
Consider this image: conv example
We have a part of an input matrix and a filter. Ok, now we can do the convolution and the result is a scalar, ...
0
votes
0answers
17 views
Batch normalization in convolutional nn
Let's say we have a convolutional layer which outputs C number of channels with width W and height H and we train it with a batch size of B. We feed that output to batch norm layer. So I have a couple ...
0
votes
0answers
15 views
How to train a multi inputs deep learning model using every combination of inputs?
I am beginner in deep learning. I want to create a multi inputs CNN model in Keras. The model takes two inputs of images to give the two images class. The two images from differnt datasets that have ...
-1
votes
0answers
20 views
Which is the best neural network that has the best accuracy for detection of cars?
I am on a look out for a trained neural network which has best accuracy for classification of cars. I can't seem to find any resource online that can help me find one. I could only find this Image-...
0
votes
0answers
13 views
what should be the chain rule to calculate the weight change for the input layer
for example to calculate the weight change in the hidden layer i am deriving it by the following : -
THE FOREWARD PASS:
\begin{equation*}
\mathtt{\begin{array}{ l }
\ \ \ \ \ \ p1_{in}\text{=\ i1\...
0
votes
0answers
14 views
Multi-inputs Convolutional Neural Network Examples
I am new in deep learning field, and I want to create a Convolutional Neural Network (cnn) that takes two inputs of images and produces one output of the inputs class. I have searched for sources of ...
0
votes
1answer
33 views
What should a good loss curve look like?
This is a very basic question. I'm running a faster rcnn trainer on a dataset for object recognition. My images range from 200x200 to 7360x4912 in resolution. There are only 2 classes being trained (...
0
votes
1answer
12 views
Problem extracting features from convolutional layer where the dimensions are big for feature maps
I have trained a convolutional neural network on images to detect emotions. Now I need to use the same network to extract features from the images and use the features to train an LSTM. The problem is:...
6
votes
2answers
95 views
What is the difference between a receptive field and a feature map?
In a CNN, the receptive field is the portion of the image used to compute the filter's output. But one filter's output (which is also called a "feature map") is the next filter's input.
What's the ...
1
vote
0answers
18 views
Multi-channel CNNs and channels
In language models, CNNs can extract different n-gram features from the input. From my current understanding, these models are called "multi-channel CNNs". I'm referring to these materials:
https://...
1
vote
0answers
11 views
Using features extracted from a CNN as convolutional filter
I'm a bit confused about this. Assume I have a CNN network with two branches:
Top
Bottom
The top branch outputs a feature vector of shape 1x1x1x10 (batch, h, w, c)
The bottom branch outputs a ...
0
votes
0answers
26 views
Visualizing convolutional layers for text data
For a project, I am doing document-level sentiment analysis. Each document is a short Yelp review with a couple of sentences that have subjective, positive/negative features.
I am using convolutional ...
2
votes
1answer
83 views
How to combine input from different types of data sources?
I've to train a neural network using microphone data (wav files), accelerometer sensor data and light sensor data.
Right now the approach I thought was to convert all data into images and combine ...
2
votes
1answer
49 views
How to measure the reasoning capabilities of neural networks
Which possibilities exist to evaluate the visual reasoning capabilities of neural networks in the field of image recognition?
Are there methods to measure the ability of machine reasoning?
Or ...
1
vote
0answers
14 views
neural network deconvolution filters
I understand the concept of convolution.
Let's say that my input dimension is 3 x 10 x 10
And if I say that I will have 20 activation maps and a filter size of 5, ...
2
votes
1answer
51 views
Best way to create an image dataset for CNN
I am creating a dataset made of many images which are created by preprocessing a long time series. Each image is an array of (128,128) and the there are four classes. I would like to build a dataset ...
1
vote
1answer
33 views
Neural Network for Optical Mark Recognition?
I've created a neural net using the ConvNetSharp library which has 3 fully connected hidden layers. The first having 35 neurons and the other two having 25 neurons each, each layer with a ReLU layer ...
2
votes
0answers
18 views
If there are several computers on a subnet, can training time be reduced by distributing the work across them?
We have multiple computers and the ability to ssh between them. What are options using either Java, C/C++, JavaScript, or Python to distribute our learning tasks? We will be using DCNN, DQN, and LSTM ...
5
votes
1answer
53 views
Does it make sense to apply softmax on top of relu?
While working through some example from Github I've found this network (it's for FashionMNIST but it doesn't really matter).
Pytorch forward method (my query in upper case comments with regards to ...
1
vote
0answers
17 views
What is meant by “model discriminability for local patches within the receptive field”?
In the Abstract section of the paper Network In Network, what does the authors actually mean to say?
4
votes
1answer
42 views
What are the ways to calculate the error rate of a deep Convolutional Neural Network, when the network produces different results using the same data?
I am new to the object recognition community. Here I am asking about the broadly accepted ways to calculate the error rate of a deep CNN when the network produces different results using the same data....
0
votes
1answer
49 views
Why is there Transition layers in DenseNet?
The DenseNet architecture can be summarize with this figure :
Why there is transition layers between each blocks ?
In the papers, they justify the use of transition layers as follow :
The ...
2
votes
1answer
21 views
Maxpooling in inception?
Maxpooling is performed as one of the steps in inception which yields same output dimension as that of the input.
Can anyone explain how this max pooling is performed?
1
vote
1answer
25 views
Recognising Noise in Simple Classification
I have created a classifier for some simple gestures using an input layer, a hidden layer with tanh activation and an output softmax layer, I'm also using the Adam optimiser. The network classifies ...
4
votes
1answer
44 views
How to define a loss function for a classifier where the confusion between some classes is more important than the confusion between others?
I have a dataset of images belonging to $N$ classes, $A_1, A_2...A_n,B_1,B_2...B_m$ and I want to train a CNN to classify them. The classes can be considered as subclasses of two broader classes $A$ ...
0
votes
1answer
29 views
Inception neural network input layer confusion
According to the original paper on page 4, 224x224x3 image is reduced to 112x112x64 using a filter ...
1
vote
1answer
45 views
Is 1mb an acceptable memory size for images being trained in a CNN?
I am using Tensorflow CNN to build an image classification/prediction model. Currently all the images in the dataset are each about 1mb in size.
Most examples out there use very small images.
The ...
