Welcome to our forum area!

Facing a tricky embedded vision project? In our forum you can discuss specific applications, solutions or hardware and software architecture topics. You will find answers on general technology questions and get support from other developers to bring your idea to life. Browse our forum below, participate and enjoy the exhange with like-minded people from all over the world. Just give it a go! Please have a look at our netiquette and keep it in mind when creating a post.

+Add post

Linear vs ReLU activation

Created by:  |   |  Replies: 2
It seems ReLU is often used as an activation function in neural networks? But could not quite understand w...

How can I use "loss" to determine how my model is doing?

Created by:  |   |  Replies: 3
When training my model in Keras after each epoch model outputs a values named "loss". I assume it somehow ...

Differences in Keras vs Pytorch vs Scikit-Learn

Created by:  |   |  Replies: 2
Can any of this libraries be used to solve machine learning problems? What are the differences between them?

Tensorflow nightly

Created by:  |   |  Replies: 3
What is tensorflow nightly?

What is text normalization?

Created by:  |   |  Replies: 12
I am learning natural language processing (NLP). Recently I encountered the term "text normalization". Can...

Do I need to rewrite project in Tensorflow 2?

Created by:  |   |  Replies: 2
I have an old project that I want to use again. It is written in TensorFlow 1. Do you think I should rewri...

Square error for logistic regression

Created by:  |   |  Replies: 2
Hi! Help me please to clarify it. Why we can not use square error as cost function for logistic regression...

Neural network using JavaScript

Created by:  |   |  Replies: 6
Hi everybody! I am a professional web developer. My primary programming language is JavaScript. I use JS a...

Bidirectional sequence models

Created by:  |   |  Replies: 3
I know about such neural networks as LSTM and GRU, which are good for working with sequence data. But rece...

Dense neural networks for computer vision problems

Created by:  |   |  Replies: 5
I know that convolutional neural networks are used in all areas of modern computer vision. But what is the...

Why traditional RNN isn't working in practice?

Created by:  |   |  Replies: 1
I have heard that traditional recurrent neural networks aren't suitable for use in real life. Other types ...

Can NN achieve the same results as RNN?

Created by:  |   |  Replies: 1
Speaking about real-life implementation, can the single-layer neural network work as good as RNN?

Classification based on the taxonomy

Created by:  |   |  Replies: 9
I need to perform classification of companies according to the defined taxonomy. It has 3 levels. How I c...

How do I use DNNEstimator from tensorflow?

Created by:  |   |  Replies: 1
When researching which algorithm to use in the text classification I stumbled upon usage of DNNClassifier....

Should I migrate to TensorFlow 2.0?

Created by:  |   |  Replies: 8
I heard about new version of TensorFlow and that it is more simple, like 'keras'. But does it lose it term...

Size of training data for neural network

Created by:  |   |  Replies: 6
I have a time series forecasting task. I have heard that LSTM neural networks are one of the best algorith...

How to inspect learned parameters of the layer in Keras?

Created by:  |   |  Replies: 4
My current project includes training the deep neural network for natural text processing. I want to be abl...

Image normalization in Keras

Created by:  |   |  Replies: 4
I'm trying to do image classification with Keras. I have read that it is usually a good idea to normalize ...

What impact cause feature scaling on the model performance?

Created by:  |   |  Replies: 3
While working with data preprocessing before modelling few questions rose in my head. Is it possible that ...

AI tools for food recognition

Created by:  |   |  Replies: 4
I want to build and app for the restaurant that will recognise food on the clients trays. What should I st...

Need support?

Just drop us an email to ... Show more