Questions tagged [deep-learning]

The tag has no usage guidance.

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

How to train huge ML model on multiple budget machines on web?

Is there a way to train huge models (1+ TiB of parameter data) being distributed on web? For example, I have a several hundreds of budget machines, each equipped with 2-4 GiB of RAM and with no ...
ababo's user avatar
  • 111
1 vote
0 answers
10 views

MobileNet not improving [closed]

I am trying to train a MobileNetV2 on a custom dataset, to image Classification task. Cardinality is 864 images, split in 70%/20%/10%, balanced between the 3 different classes. Weights are pre-loaded ...
Mattia's user avatar
  • 11
1 vote
0 answers
18 views

Using Computer Vision Techniques to Detect and Overlay Books in Images

I want to use computer vision techniques to find a book in a random background image, figure out how it's rotated, and then overlay a new book onto it. Here are the steps I plan to take: Use object ...
Abishek Anbarasan's user avatar
2 votes
0 answers
30 views

Light browser-side JavaScript library for ML image captioning

I want to write a web plugin that will analyze a video (or more realistically some frames from a video) and output what happens on the video (what items there are, how many people there, where people ...
Igor's user avatar
  • 21
0 votes
0 answers
22 views

Deep learning-enhanced audio slowdown filter

Is there a pre-trained accessible open source audio transfomer powered be deep learning that slows down audio/speech (like ffmpeg atempo=.5), but with higher quality compared to usual algorithms? For ...
Vi.'s user avatar
  • 1,003
1 vote
0 answers
23 views

Looking for a Geotiff image browser and labelling tool

We have large sets of classified satellite image tiles to train a convolutional neural network and looking for a tool to browse our dataset mainly for visual quality checks, ideally with an option to ...
auralbee's user avatar
  • 111
0 votes
1 answer
15 views

Web based tool to explore how different machine learning models perform on my dataset

I'm new to machine learning and want to try a few models on my dataset. I'm looking for a web based tool where I can upload my data (in my case images), select a pre-trained model and then view its ...
Tom's user avatar
  • 121
1 vote
0 answers
17 views

Is there a good program/method to use personalized deep learning object detection models to locate objects on image orthomosaics?

For some graduate work, I am collecting data and using it to train AI object detection models (such as Faster R-CNNs, EfficientDet series, and others that can be found on the Tensorflow 2 Detection ...
ihb's user avatar
  • 111
1 vote
0 answers
6 views

I looking for a software package for dubbing with source voices

I'm looking for a software package for dubbing a movie. I have part 1 of the movie done by letting al the voiceovers speak every sentence in. Now we have part 2 finished but would like to dubb the ...
Mitchell's user avatar
1 vote
0 answers
8 views

Framework/Tool for real-time inference with large input flow using Tensorflow

I'm working on a part of a project, that detects fraud from sensors' data using deep learning. Current steps are: Receiving sensors' data (I'm currently receiving data from Kafka). Predicting ...
Tung's user avatar
  • 11
1 vote
0 answers
36 views

Possible algorithms or libraries for training for text similarity and matching

I have a big database that contains two table CLIENT_DESCRIPTION and REPORTER_DESCRIPTIPN. This database is for a study on how people answer a specific question How do you describe your experience ...
Abozanona's user avatar
0 votes
0 answers
12 views

Extracting pieces of information from faces

I need to extract person features from photos. Features that I care about: sex race age hair color* eye color* (Features with * is nice to have but it's not necessary)
Fejor's user avatar
  • 1
1 vote
1 answer
243 views

Pre-built Ubuntu setup for deep learning

I want to work on deep learning and computer vision in Linux, say Ubuntu. I know there are pre-built images in AWS, Azure for this purpose. But I want to install it on my PC to VirtualBox or to hard ...
Igor P.'s user avatar
  • 11
0 votes
0 answers
32 views

Is there any alternative to Tensorflow in Python which requires less storage space?

I've been trying to reduce the storage space needed to operate my company's wake-word detector such that it could fit into Raspberry Pi 3. The wake-word detector is using Mycroft Precise to automate ...
light42's user avatar
1 vote
0 answers
13 views

C++ for Deep Learning

I am working about a project in Deep learning, it's about images classification but the problem is I should work with C++ and I don't have any idea about what libraries or software should I choose to ...
user62294's user avatar
0 votes
0 answers
18 views

Automatic recognizing of the proprietary files type

I would like have sw/utility/library, what is able to recognize file structures of uknown (proprietary or not so usual) file types. So I have bunch of files of some proprietary file type (some ...
Jii's user avatar
  • 109
1 vote
0 answers
79 views

Tool that generates a mindmap for a given text

Hey I am looking at a tool or software(open source preferred) that does provide me a mindmap of any text provided I don't have any preferences for the language. For example, I would like to pass a ...
Mr Jack's user avatar
  • 11
1 vote
0 answers
12 views

Reproduce network architectures with Java from a trained keras .h5 model

I’m trying to open an already trained model from Keras (python) with Java and use it to analyze new images. My model is saved in HDF5 format which contains the architecture of the network as a .json ...
eLearner's user avatar
0 votes
2 answers
121 views

Image Labelling Application for Deep Learning

I'm looking for some offline software that can be used for labelling many images with rectangular bounding boxes for the purposes of object detection. It needs to be able to import pre-generated ...
ezekiel's user avatar
  • 101
3 votes
0 answers
38 views

OCR Deep Learning Software

I have a question about a possible software solution for a problem. I work in a very busy psychiatric private practice that handles large amounts of paperwork. We would like to create a more efficient ...
NeoMoneyX's user avatar
2 votes
0 answers
22 views

Library for deep learning on images with multiple GPUs

There are many libraries available for deep learning these days: Keras (A wrapper around Tensorflow, CNTK, and Theano) TensorFlow (from Google) CNTK (from Microsoft) Theano (discontinued late 2017) ...
Josiah Yoder's user avatar