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
17 views

Why does the validation loss not go down when training my TensorFlow implementation of AlexNet?

I am trying to implement AlexNet in Tensorflow. Matlab has a built-in AlexNet implementation that I use with the cats and dogs dataset (mledu-datasets/cats_and_dogs_filtered.zip). In Matlab, ...
0
votes
0answers
19 views

How to generate a Matrix out of Sparse Data

So I have a system that takes 32 inputs (all of which are 1 or 0) and generates 32 outputs (all of which are complex numbers that lie roughly in the range of (0,2)). The response of this system to its ...
-1
votes
0answers
24 views

computational complexity of attention in dynamic-convolution

I'm reading this paper , Dynamic convolution-Attention over Convolution kernels. I couldn't understand the complexity of attention i.e., How to calculate O(π(...
0
votes
1answer
19 views

Semantic segmentation failing in small instance detection

I performed semantic segmentation with U-net. My dataset consists of grayscale images of defects. After training the dataset for I got an metric accuracy of only 0.3 - 0.4 IOU. Eventhough it is merely ...
0
votes
0answers
4 views

How to find rotation x/y/z of chessboard diagram with what network architecture?

I want to recognize pieces of chessboard diagram (not real 3d pieces but just diagram). I split this task in some operation like rotation/cutting/segmentation. First of all I want to detect chessboard ...
0
votes
0answers
31 views

Can anyone recommend me a very good pre-trained model for face or head detection? [closed]

I really need to know the best pre-trained models to detect faces and/or peoples' head. Not a face recognition model, but only to classify whether an object is a person's head/face or not. I'm ...
1
vote
1answer
42 views

Can the (sparse) categorical cross-entropy be greater than one?

I am using AlexNet CNN to classify my dataset which contains 10 classes and 1000 data for each class, with 60-30-10, splits for train, validation, and test. I used different batch sizes, learning ...
1
vote
0answers
22 views

What are the benefits of using ELU over other activation functions in CNNs?

I have come up with some examples of CNNs (segmentation CNNs) that use ELU (exponential linear unit) as an activation function. What are the benefits of this activation function over others, such as ...
0
votes
1answer
33 views

Difference between Neural Compute Stick 2 and Google Coral USB for edge computing [closed]

I am trying understand machine learning inferece, and i would like to know what exactly is the difference between Google Coral USB and Movidius Intel Neural Compute Stick 2. From what i could gather ...
0
votes
1answer
51 views

Keras DQN Model with Multiple Inputs and Multiple Outputs [closed]

I am trying to create a DQN agent where I have 2 inputs: the agent's position and a matrix of 0s and 1s. The output is composed of the agent's new chosen position, a matrix of 0s and 1s (different ...
1
vote
1answer
24 views

Is average pooling equivalent to a strided convolution with a specific constant kernel?

It seems to me that average pooling can be replaced by a strided convolution with a constant kernel. For instance, a 3x3 pooling would be equivalent to a strided convolution (of stride $3$) with a $3 \...
1
vote
0answers
15 views

Given a dataset and a neural network, is there some heuristic or theorem to determine whether this neural network has enough capacity? [duplicate]

What is the consensus regarding NN "capacity" or expressive power? I remember reading somewhere that expressive power grows exponentially with depth, but I cannot seem to find that exact ...
0
votes
1answer
19 views

DQN rgb input channels problem using pytorch

I've been trying to learn about CNN's and reinforcement learning and I found this project to play with: https://github.com/adityajn105/flappy-bird-deep-q-learning I've been trying to change the code ...
2
votes
0answers
23 views

What are ways to learn a classifier for labelling a series of images rather than individual images?

... and how do I reword my question in the title? I have a dataset where each "instance" has a "series" of multiple photos taken from different angles. I need to classify each ...
1
vote
0answers
20 views

How can I improve the performance on unseen data for semantic segmentation using an auto-encoder?

I am using simple autoencoders for the task of semantic segmentation on the VOC2012 dataset. I am currently using a simple autoencoder based model. It is trained on adam optimizer with cross-entropy ...
0
votes
0answers
16 views

Need suggestion for Reinforcement Learning based visual landing system for quadcopters (UAVs)

I have deep interest in quadcopters. I need ideas for designing of an experiment. I have a programmable quadcopter. I can autonomously land it on a staitonary landing pad with a vision algorithm. ...
0
votes
0answers
22 views

In CNNs, why do we sum the filter derivatives w.r.t the loss function to get the final gradient?

In a Convolutional Neural Network, unlike the fully connected layers, the same filter is used multiple times on the input while convolving - so during backpropagation, we get multiple derivatives for ...
0
votes
0answers
36 views

How to determine the number of fully connected layers for a convolutional neural network?

How many fully connected layers should be added to a convolutional neural network? Does it depend on input size to the fully connected layer? If so, how do we decide? What if the input size of the ...
1
vote
0answers
24 views

Is the 3d convolution associative given that it can be represented as matrix multiplication?

I'm trying to understand if a 3D convolution of the sort performed in a convolutional layer of a CNN is associative. Specifically, is the following true: $$ X \otimes(W \cdot Q)=(X \otimes W) \cdot Q, ...
0
votes
0answers
16 views

CNN to detect presence/absense of label on images with mixed labels

Here's my problem: I work with medical image classification, and currently I have 3 classes: class A: images with lesion 1 only; and images with lesion 1 and N other lesions class B: images with 2 ...
1
vote
0answers
22 views

What is a “center loss”?

I have seen that a center loss is beneficial in computer vision, especially in face recognition. I have tried to understand this concept from the following material A Discriminative Feature Learning ...
1
vote
2answers
78 views

How to verify classification model trained on classification dataset on a detection dataset for classification purpose?

I am working on a problem that involves two tasks - detection and classification. There is no single dataset for both tasks. I am training two models, separate on detection dataset and another on ...
0
votes
1answer
18 views

Will changing the dimension reduction size of a neural network (i.e. SSD ResNet-50) change the overall outcome and accuracy of the model?

I am training a convolutional neural network to detect objects (weeds amongst crops, in my case) using TensorFlow. The original dimensions of the raw training photos are 4000 x 3000 pixels, which must ...
0
votes
0answers
22 views

Generating data from a High-Res. RGB image for a CNN

Say I want to build a detection model that detects the existence of X or NO X. The only piece of information I have, though, is a high res. RGB image, say 100k (width) x ~1000 pixels (height). Let's ...
1
vote
1answer
43 views

Single-Shot Learning for Object Re-Identification

I am looking for a way to re-identify/classify/recognize x real life objects (x < 50) with a camera. Each object should be presented to the AI only once for learning and there's always only one of ...
0
votes
0answers
34 views

Is the “mlpconv” layer in the “Network in Network” paper computing $1 \times 1$ convolutions or not?

I am reading the Network in Network paper. This is the equation they introduce for their mlpconv layer (equation 2 in the paper, page 3): $$ \begin{aligned} f_{i, j,...
0
votes
1answer
46 views

Are there any rules for choosing batch size? [duplicate]

I am training a CNN with a batch size of 128, but I have some fluctuations in the validation loss, which are greater than one. I want to increase my batch size to 150 or 200, but, in the code examples ...
1
vote
0answers
14 views

Why do we add additional axis in CNN autoencoder while denoising?

I am currently learning about autoencoders and I follow https://www.tensorflow.org/tutorials/generative/autoencoder When denoising images, authors of tutorial add an additional axis to the data and I ...
3
votes
1answer
50 views

Is there a common way to build a neural network that seeks to extract spatial and temporal information simultaneously?

Is there a common way to build a neural network that seeks to extract spatial and temporal information simultaneously? Is there an agreed up protocol on how to extract this information? What ...
1
vote
0answers
35 views

How to have closer validation loss and training loss in training a CNN

I am using an AlexNet architecture as my Convolutional Neural Network. A learning rate of 0.00007 and 128 batch_size. I have 20000 data and 10% test, 40% validation, and 50% for training. I used 100 ...
2
votes
1answer
50 views

When should we use separable convolution?

I was reading the "Deep Learning with Python" by François Chollet. He mentioned separable convolution as following This is equivalent to separating the learning of spatial features and the ...
0
votes
1answer
33 views

Computer vision - Can you put more weight on a specific part of the object?

Let's say I'm looking for any item that has a certain shape (outline) in a photo. but I can further classify it only according to particular features, that most of them are expected to be shown only ...
0
votes
1answer
51 views

Is it possible to know the distance objects are from camera based on only knowing one object's height?

I am doing a project where I have to know distance a particular object is from camera. In the photo I only know one of the object's height, but I don't know how far away that object is and I don't ...
2
votes
2answers
143 views

What is the need for so many filters in a CNN?

Consider the following coding line related to CNNS Conv2D(64, (3,3), strides=(2, 2), padding='same') It is a convolution layer with filter size $3 \times 3$ and ...
-1
votes
1answer
45 views

How can I train a CNN to detect when a person is smoking outside of shop given images from a video camera?

My friend is working at a pizza shop. He takes cigarette breaks in an area that is covered by the public webcam of our town. I now want to train a convolutional neural network to be able to detect ...
0
votes
0answers
11 views

Cocatenate feature extractor layers with different channels

I have a network architecture for feature extraction and I wanted to concatenate layers of the same dimensions but with different feature channels. ...
0
votes
0answers
23 views

Choice of loss function for semantic segmentation

I am training a U-Net for semantic segmentation of large medical images (4096x4096px). The two classes are "too" unbalanced. The white pixels are just about 0.1% (or less) of the whole image....
0
votes
0answers
25 views

Pytorch and keras ddqn seem identical, only keras learns

I followed a tutorial for ddqn to beat pong, it beats it with a perfect score in keras, but trying to translate it to pytorch it doesn't learn at all. What am I missing? I pasted all the code for each ...
0
votes
1answer
23 views

Image Classification for watermarks with poor results

Just starting learning things about tensorflow and NN. As an exercise I decided to create a dataset of images, watermarked and not, in order to binary classify these. First of all, the dataset ( you ...
1
vote
0answers
27 views

Training a CNN for semantic segmentation of large 4600x4600px images

I am trying to implement a CNN (U-Net) for semantic segmentation of similar large grayscale ~4600x4600px medical images. The area I want to segment is the empty space (gap) between a round object in ...
1
vote
0answers
16 views

Model output segmentation maps which are not full

I created a VGG based U-Net in order to perform image segmentation task on yeast cells images obtained by a microscope. There are a couple of problems with the data: There is inhomogeneity in the ...
1
vote
1answer
73 views

How to mathematically describe the convolution operation (with a Gaussian kernel)?

I have to build a model where I pre-process the data with a Gaussian kernel. The data are an $n\times n$ matrix (i.e one channel), but not an image, thus I can't refer to this matrix as an image and ...
2
votes
1answer
43 views

Comparing a large/general CNN to a smaller more specialized one?

I am still somewhat a novice in the ML world, but I had a strange idea about CNNs and wanted to ask if this would be a valid way to check the robustness of a general CNN that classifies certain images....
0
votes
0answers
29 views

How to implement or avoid masking for transformer?

When it comes to using Transformers for image captioning is there any reason to use masking? I currently have a resnet101 encoder and am trying to use the features as the input for a transformer model ...
2
votes
1answer
59 views

Can we apply transfer learning between any two different CNN architectures?

There are many types of CNN architectures: LeNet, AlexNet, VGG, GoogLeNet, ResNet, etc. Can we apply transfer learning between any two different CNN architectures? For instance, can we apply transfer ...
1
vote
1answer
39 views

Pytorch Deep q network not learning and step not stepping towards target

I am trying to create a simple deep q network for rl with conv2d layers. I can’t figure out what I am doing wrong, and the only thing I can see that doesn’t seem right is when I get the model ...
2
votes
1answer
40 views

Should I remove the text overlaying some images in the dataset before training the CNN?

If I am attempting to train a CNN on some image data to perform image classification, but some of the images have pieces of text overlaying them (for the purpose of description to humans), then is it ...
1
vote
0answers
19 views

Duplicating calculations in CNN-LSTM architecture

I want to use frames from video game and analyze them using CNN and LSTM. But when I have the model defined like that ...
1
vote
1answer
37 views

Research paths/areas for improving the performance of CNNs when faced with limited data

I've been reading through the research literature for image processing, computer vision, and convolutional neural networks. For image classification and object recognition, I know that convolutional ...
0
votes
1answer
29 views

How to construct input dependent convolutional filter?

I am constructing a convolutional variational autoencoder for images, starting out with mnist digits. Typically I would specify convolutional layers in the following way: ...

1
2 3 4 5
17