Questions tagged [convolutional-neural-networks]

For questions about convolutional neural networks, also known as CNN or ConvNet.

Filter by
Sorted by
Tagged with
0
votes
0answers
15 views

How to train image segmentation task with only one class?

Is there a neural network that has architecture optimizations for segmenting only one class (object and background)? I have tried U-net but it is not providing good enough results. I am wondering if ...
2
votes
1answer
23 views

Most suitable model for video classification with a fixed camera

Consider a fixed camera that records a given area. Three things can happen in this area: No action People performing action A People performing action B I want to train a model to detect when ...
2
votes
2answers
58 views

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

Say a simple neural network's input is a collection of tags (encoded in some way), and the output is an image that corresponds to those tags. Say this network consists of some dense layers and some ...
1
vote
0answers
16 views

Using U-NET for image semantic segmentation

If it is not the right place to ask this question, please tell me and I move it to the right place. I'm getting literally crazy trying to understand how U-NET works. Maybe it is very easy but I'm ...
3
votes
1answer
58 views

Why do current models use multiple normalization layers?

In most current models, the normalization layer is applied after each convolution layer. Many models use the block $\text{convolution} \rightarrow \text{batch normalization} \rightarrow \text{ReLU}$ ...
2
votes
0answers
76 views

Which neural network should I use to transform the pixels of a video overtime?

I want to train a network with video data and have it transform pixel values overtime on an input video. This is for an art project and does not need to be super elaborate, but the videos I want to ...
1
vote
0answers
16 views

Is CNN capable of extracting the descriptive statistics features

I was trying to build a CNN model. I used time series data of daily temperature to predict if there is risk of an event, say bacteria growth. I calculated the descriptive statistics of the time series,...
3
votes
3answers
104 views

Convolutional Neural Network: does each filter in each convolution layer create a new image?

Say I have a CNN with this structure: input = 1 image (say, 30x30 RGB pixels) first convolution layer = 10 5x5 convolution filters second convolution layer = 5 3x3 convolution filters one dense layer ...
2
votes
1answer
46 views

Can a trained object detection model deal with variations of the input?

Suppose an object detection algorithm is good at detecting objects and people when an object and person is close to a camera and upright. If the person walks farther away from the camera and is "...
2
votes
0answers
33 views

FasterRCNN's RPN network training

I would like to know if my understanding of RPN training is correct, and if never training the RPN on some specific anchor box is bad (i.e if the anchor never sees good nor bad examples). To make my ...
1
vote
0answers
17 views

Optimisation of dependence of efficiency of CNN on training data

I got a large dataset of images (dimensions of 16 x 16, 250k samples) and corresponding spherical coordinates (distributed uniformly in each coordinate). On these, I trained a convolutional regression ...
0
votes
0answers
36 views

Is there an audio dataset with the corresponding phonemes in the audio?

I am looking for a dataset of clear audio, a corresponding transcript (optional), and most importantly a list of all the phonemes said in the audio, with the length of each phoneme and a mention of ...
0
votes
1answer
41 views

structure of neural network for classification problems with large amounts of null classifications

I am building a Convolution neural network to predict certain categories based on images (the location of a pointer on a surface) . However in many cases there will be no pointer in the view or ...
2
votes
1answer
24 views

Can I shuffle image channel data as a form of data augmentation?

If I want to augment my dataset, is shuffling or permuting the channels (RGB) of an image a sensible augmentation for training a CNN? IIRC, the way convolutions work is that a kernel operates over ...
1
vote
0answers
30 views

How can I get the predicted box in Faster R-CNN?

The RPN loss in Faster RCNN paper is $$ L({p_i}, {t_i}) = \frac{1}{N_{cls}} \sum_{i} L_{cls}(p_i,p_i^*) + \lambda \frac{1}{N_{reg}} \sum_i p_i^* L_{reg}(t_i, t_i^*) $$ For regression problems, we ...
2
votes
0answers
31 views

How should I handle different input sizes in graph convolution networks?

I'm a student beginning to study deep learning, and would like to practice with a simple project using a Graph Convolutional Network. However, I'm not quite sure how to handle different input sizes ...
1
vote
1answer
42 views

Relationship between training accuracy and validation accuracy

During model training, I noticed various behaviour in between training and validation accuracy. I understand that 'The training set is used to train the model, while the validation set is only used to ...
1
vote
0answers
31 views

Is weight pruning applied to all layers or only to dense layers in CNNs?

I was reading about weight pruning in convolutional neural networks. Is it applied for all the layers including convolutional layers or only it is done for dense layers?
2
votes
0answers
64 views

How can I train YOLO with the COCO dataset?

I am trying to implement the original YOLO architecture for object detection, but I am using the COCO dataset. However, I am a bit confused about the image sizes of COCO. The original YOLO was trained ...
2
votes
1answer
46 views

How GoogleNet actually deal with reducing overfitting?

Today I was going through a tutorial of Andrew Ng about Inception network. He said that GoogLeNet's hidden layers are also good in prediction and it had somehow a regularization effect, so it reduces ...
3
votes
2answers
84 views

Image vs Non-Image Data in CNN

When using CNN on non-image(times series) data prediction, what are some constraints or things to look out for as compared to image data? To be more precise, I ...
1
vote
0answers
10 views

Can Grad CAM feature maps be used for Training?

I am trying to recreate the architecture of the following paper: https://arxiv.org/pdf/1807.03058.pdf Can someone help me in explaining how are the feature maps coming out of the output of GradCam ...
1
vote
0answers
48 views

How many training data required for GAN?

I'm beginning to study and implement GAN to generate more dataset. I'll just try to experiment with state-of-the-art GAN models as described in here https://paperswithcode.com/sota/image-generation-on-...
1
vote
0answers
8 views

Keras correlation coefficient as network metric in R

does anyone know how to use the correlation coefficient or squared correlation coefficient as a metric in keras in R (although other languages may provide clues). This is for a CNN that functions ...
2
votes
0answers
32 views

Difference in the code structure of RNN and CNN

I understand that in general RNN is good for time series data and CNN image data, and have noticed many blogs explaining the ...
3
votes
1answer
29 views

Can non-sequential deep learning models outperform sequential models in time series forecasting?

Can a CNN (or other non-sequential deep learning models) outperform LSTM (or other sequential models) in time series data? I know this question is not very specific, but I experienced this when ...
0
votes
1answer
19 views

Multicamera Tracking vs Single Fisheye Camera

Suppose you want to detect objects and also track objects and people. Is it better to train a model using a single fisheye camera or using multiple cameras that mimic the view of the fisheye camera? ...
1
vote
1answer
57 views

What is the difference between Kaldi and DeepSpeech speech recognition systems in their approach?

I would like to know how do Kaldi and DeepSpeech speech recognition systems differ algorithmically? Which one would be more accurate for continuous speech in time?
2
votes
0answers
29 views

Are there any easy ways to create annotated training images for object detection?

For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, ...
5
votes
1answer
128 views

Should I train different models for detecting subsets of objects?

Suppose we have $1000$ products that we want to detect. For each of these products, we have $500$ training images/annotations. Thus we have $500,000$ training images/associated annotations. If we want ...
5
votes
1answer
63 views

Concrete example of latent variables and observables plugged into the Bayes' rule

In the context of the variational auto-encoder, can someone give me a concrete example of the application of the Bayes' rule $$p_{\theta}(z|x)=\frac{p_{\theta}(x|z)p(z)}{p(x)}$$ for a given latent ...
1
vote
1answer
23 views

How can max pooling be applied to find features in words?

I'm reading about max pooling in a dynamic CNN paper and I can see how it can help find features in images cause the pixel with the highest density gets pooled, but how does it help find features in ...
1
vote
1answer
34 views

Convolutional filters: create new ones

I'm studying a Master's Degree in Artificial Intelligence an my final work is about Convolutional Neuronal Networks. I was looking for information about filters (or kernel) at the convolutional ...
0
votes
0answers
22 views

How to count pixels in a object mask which is segmented using Mask R-CNN?

I have segmented concrete cracks from concrete structure images using Mask R-CNN. Now I need to measure the length of the segmented masked crack. Will the pixel counting method work? Can anyone help?...
1
vote
0answers
8 views

Loss function for increasing the quality of the image when labels are not perfectly alligned

I am trying to increse the quality of the images that I gather from the microscope. That is a acoustic microscope and there are lots of technical details but in a nutshell the low quality images and ...
2
votes
0answers
13 views

Size of image input of neural networks while resizing may not be appropriate

I have the following problem while using convolutional neural networks to detect forgeries: Resizing the image to fit the required input size may not be a good way because the forgery detection ...
2
votes
1answer
43 views

What could I do to this CNN to achieve a higher accuracy on the cifar10 dataset?

I have achieved around 85% accuracy using the following architecture: I used a learning rate of 0.001 and trained the model over 125 epochs with a batch size of 64. Any suggestions would be much ...
2
votes
1answer
32 views

Semantic issues with predictions made by my trained model

I'm new to Deep Learning. I used Keras and trained a inception_resnet_v2 model for my binary classification application (fire ...
2
votes
1answer
63 views

ValueError: Error when checking target: expected dense_3 to have shape (1,) but got array with shape (2,)

I am trying to build a CNN model on Keras. The data has a dimension of 921 rows × 10000 columns. Here is the code: ...
0
votes
0answers
14 views

Plot class activation heatmap of Caffe Model in Python

Given the following 3 research papers, the authors have shown different heatmap graphical representations for features of the trained CNN models: On the performance of Convnet feature for place ...
1
vote
4answers
76 views

What are examples of books or papers on the details of convolutional neural networks?

I'm studying a master's degree and my final work is going to be about the convolutional neural network. I read a lot of books and I did Convolutional Network Standford's course, but I need more. Are ...
1
vote
1answer
74 views

Making a CNN for phoneme classification

I was making a simple phoneme classification model for a 10 week-long class project and I ran into a small question. Is it possible, to create a model that takes a 1-second (the longest phoneme is 0.2 ...
1
vote
1answer
21 views

Best approach for 2D Grid Image Segmentation

I'm working on a project where I need to extract text from grocery discount flyers like the Costco announcement below (retrieved in a random google search, Costco is not the deal here): If I just run ...
0
votes
1answer
35 views

Interpreting Keras Yolov3 config file [closed]

How does one interpret the "min_input_size", "max_input_size" and "anchors" fields in the Yolov3 config file here. In particular, suppose we have the following: ...
1
vote
1answer
47 views

Is it possible to train a CNN to predict the dimensions of primitive objects from point clouds?

Is it possible to train a convolutional neural network (CNN) to predict the dimensions of primitive objects such as (spheres, cylinders, cuboids, etc.) from point clouds? The input to the CNN will be ...
2
votes
1answer
65 views

What is the fastest way to train a CNN with billions of examples?

I have a CNN model that I need to train for a large scale genomics application. It is working well with a subset of my training data. I have scaled up to a subset of about 130 million examples and ...
0
votes
0answers
8 views

How to measure object size from the disparity map using CNN?

I am a student learning about image processing using CNN. I want to learn how to measure the object size from the disparity map obtained from left and right stereo images.
0
votes
0answers
12 views

How to measure the size of an crack which is segmented from an image using Mask-RCNN?

I am a masters student going to work in a project to analyze the cracks in underwater concrete structures. I need some suggestions for data acquisition and length measurement of the crack. I have ...
2
votes
1answer
44 views

Pose estimation using CNNs on Point clouds

In the case of single shot detection of point clouds, that is the point cloud of an object is taken only from one camera view without any registration. Can a Convolutional Network estimate the 6d pose ...
2
votes
0answers
19 views

How to properly use batch normalization during inference

I am trying to manually implement calculations of the image classification process using pre-trained weights from the MobilenetV2 network. I know how to apply filter weights to the channels, but not ...