Search Results for "ground truth"
Sort By:
Showing 29 open source projects for "ground truth"
View related business solutions-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
1
Image Harmonization Dataset iHarmony4
The first large-scale public benchmark dataset for image harmonization
...The iHarmony4 dataset comprises four sub-datasets (HCOCO, HAdobe5k, HFlickr, Hday2night), each making composite images by combining a foreground from one image with a background from another, along with associated ground truth harmonized images and foreground masks. The dataset is intended as a benchmark resource to enable and standardize research in image harmonization. Each composite sample has: composite image, foreground mask, and corresponding real harmonized image. -
2
Face Alignment
2D and 3D Face alignment library build using pytorch
...For numerical evaluations, it is highly recommended to use the lua version which uses identical models with the ones evaluated in the paper. More models will be added soon. By default, the package will use the SFD face detector. However, the users can alternatively use dlib, BlazeFace, or pre-existing ground truth bounding boxes. While not required, for optimal performance(especially for the detector) it is highly recommended to run the code using a CUDA-enabled GPU. While here the work is presented as a black box, if you want to know more about the intrisecs of the method please check the original paper either on arxiv or my webpage. -
3
TTRL
Test-Time Reinforcement Learning
TTRL is an open-source framework for test-time reinforcement learning in large language models, with a particular focus on reasoning tasks where ground-truth labels are not available during inference. The project addresses the problem of how to generate useful reward signals from unlabeled test-time data, and its central insight is that common test-time scaling practices such as majority voting can be repurposed into reward estimates for online reinforcement learning. This makes the framework especially interesting for scenarios where models must keep adapting during evaluation or deployment instead of relying only on fixed pretraining and static fine-tuning. ... -
4
Patch-NetVLAD
Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
This repository contains code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition". -
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
Indoor Camera Positioning Datasets
Datasets generated for Large Scale Indoor Camera Positioning project
...Like the artificial datasets, they include ground truth data, images, and camera parameters. -
6
SAHI
A lightweight vision library for performing large object detection
A lightweight vision library for performing large-scale object detection & instance segmentation. Object detection and instance segmentation are by far the most important fields of applications in Computer Vision. However, detection of small objects and inference on large images are still major issues in practical usage. Here comes the SAHI to help developers overcome these real-world problems with many vision utilities. Detection of small objects and objects far away in the scene is a major... -
7
Robyn
Experimental, AI/ML-powered and open sourced Marketing Mix Modeling
Robyn is an open-source, AI/ML-powered Marketing Mix Modeling (MMM) toolkit developed by Meta Marketing Science under the “facebookexperimental” GitHub umbrella. Its goal is to democratize rigorous MMM: what traditionally required expert statisticians and expensive consulting becomes accessible to any company with data. Robyn takes in historical data (spends on different marketing channels, conversions, or revenue, and optional context or organic-media variables) and uses a combination of... -
8
Ghost of Death is an app to spoof your OS. It's meant to spoof scanning apps, like nmap or Metasploit. You must be admin/root. 2-28-26: Addressed a couple of bugs. Totally reworked Linux version. This app won't get a perfect match in the spoof, but it won't let them know your OS. 3-1-26: Tweaked on the Linux version some more. 3-2-26: That last Linux version was messed up, new one works, theoretically. 3-3-26: After much labor it's done. It has Windows, Mac and Android now. Windows...
-
9
tdsft
TDSFT (Two-Dimensional Segmentation Fusion Tool)
Given multiple segmentations related to the same tumor, statistical metrics could be exploited to determine the most reliable one, from there identified as ground truth. Numerous algorithms have been developed over time, but to date, there is no validated method for this procedure. Therefore, research is still active in this area. Two-Dimensional Segmentation Fusion Tool (TDSFT) is an open-source tool developed in MATLAB and distributed as a standalone application for MAC, Linux, and Windows, which offers a simple and extensible interface where numerous algorithms are proposed to "mediate" (e.g., process and fuse) multiple segmentations. ... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Keras Attention Mechanism
Attention mechanism Implementation for Keras
...The attention is expected to be the highest after the delimiters. An overview of the training is shown below, where the top represents the attention map and the bottom the ground truth. As the training progresses, the model learns the task and the attention map converges to the ground truth. We consider many 1D sequences of the same length. The task is to find the maximum of each sequence. We give the full sequence processed by the RNN layer to the attention layer. We expect the attention layer to focus on the maximum of each sequence. -
11
WaveRNN
WaveRNN Vocoder + TTS
WaveRNN is a PyTorch implementation of DeepMind’s WaveRNN vocoder, bundled with a Tacotron-style TTS front end to form a complete text-to-speech stack. As a vocoder, WaveRNN models raw audio with a compact recurrent neural network that can generate high-quality waveforms more efficiently than many traditional autoregressive models. The repository includes scripts and code for preprocessing datasets such as LJSpeech, training Tacotron to produce mel spectrograms, training WaveRNN on those... -
12
VAD
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM
This repository is a voice activity detection (VAD) toolkit that implements multiple models (DNN, bDNN, LSTM, ACAM) for detecting speech versus non-speech in audio. It also provides a recorded dataset in varied real-world settings (e.g. bus stop, construction site, park, room) with ground truth labeling. Acoustic feature extraction (multi-resolution cochleagram, MRCG). Post-processing modules (e.g. smoothing, thresholds). The toolkit supports both MATLAB and Python/TensorFlow components (for feature extraction, classification, postprocessing). Acoustic feature extraction (multi-resolution cochleagram, MRCG). Provided real-world dataset with manual annotations. -
13
miRSim
Seed-based RNA-Seq Simulator
The miRSim tool can generate the synthetic RNA-Seq data in standard fastq/fasta format by utilizing the sequence-specific properties (i.e., seed and xseed (remaining part of the sequence after removing seed)). Additionally, miRSim also generates the ground truth in CSV format that provides information about genomic location, CIGAR string, sequence, and expression counts. -
14
...For each one of them is provided: - List of names, taxonomy ID and taxonomic level of the genomes of the organisms that make up the dataset (genomes.csv) - Set of sequences extracted from the respective selected genomes (sequences.fasta) - Ground truth for each of the extracted ORFs (groundtruth.csv) For information about download, see the documentation.
-
15
SPIKE dataset
Images and models for detection of wheat spikes in the field
The SPIKE dataset contains images with manually annotated ground truth labels for training and testing convolutional neural networks for spike detection of wheat in the field. The model files available here are to be used with the Faster R-CNN implementation of the freely available Microsoft Cognitive Toolkit, found at the following link https://www.microsoft.com/en-us/cognitive-toolkit/ Futhermore, an additional software tool will soon be available for using the models with an executable program requiring less setup and more visual steps of the process. -
16
mAP
Evaluates the performance of your neural net for object recognition
In practice, a higher mAP value indicates a better performance of your neural net, given your ground truth and set of classes. The performance of your neural net will be judged using the mAP criteria defined in the PASCAL VOC 2012 competition. We simply adapted the official Matlab code into Python (in our tests they both give the same results). First, your neural net detection-results are sorted by decreasing confidence and are assigned to ground-truth objects. ... -
17
CavBench, a generic and extensible benchmark to compare diferent cavity detection methods relative to diverse ground truth datasets (e.g., PDBsum) using statistical classi cation methods.
-
18
Devanagari OCR
Devanagari Optical Character Recognition, Annotation tool
...An interface that has transilteration and a soft-keyboard using which multiple languages can be input. The UI also enables users to view the word and character level ground truth of images. To cite this work, please use: "Devanagari OCR using a recognition driven segmentation framework and stochastic language models", Suryaprakash Kompalli, Srirangaraj Setlur, Venu Govindaraju, IJDAR, 2009, Volume: 12, Pg.: 123–138 -
19
GENUA PESTO Usage Code
Usage code for the stereoscopic image database GENUA PESTO
This is the code necessary for a proper usage of GENUA PESTO - GENoa hUman Active fixation database: PEripersonal space STereoscopic images and grOund truth disparity. GENUA PESTO is a database of stereoscopic natural images rendered mimicking the posture of human eyes. The database provides: - stereoscopic pair - ground-truth depth - ground-truth retinal disparity - depth edges - occlusions The database is downloadable at: Canessa A., Gibaldi A., Chessa M., Fato M., Solari F., Sabatini S.P. ... -
20
CMMSD_GroundTruth
Ground truth data for segmentation of monophonic music.
Data for the CMMSD segmentation ground truth. The package contains the Sonic Visualiser files and the segmentation markers as .txt files. -
21
Sanskrit / Hindi - Tesseract OCR
Devanagari fonts traineddata for Tesseract OCR
Read https://sourceforge.net/projects/tesseracthindi/files/OCRHindi_using_VietOCR_and_Tesseract.pdf/download for how to use vietocr gui for OCR of Hindi and Sanskrit texts using tesseract-ocr ***** Please see https://github.com/Shreeshrii/ imagessan and imageshin for newer box/tiff pairs, traineddata files, ocr evaluation statistics and ground truth files with images for Sanskrit and Hindi. ***** Following is OLD information - saved only for archival purposes. Tesseract OCR 3.02 provides hin.traineddata for recognizing texts in devanagari scripts. However the Hindi training texts, images and box files are not provided, so it is difficult to improve the accuracy by further improving the traineddata. ... -
22
SnowMicroPyn
Python based reader for SnowMicroPen® .pnt measurements
...It is capable of measuring the bonding force between snow grains, with both high spatial resolution and high speed. The SMP can be used in different application areas as snow profiling (avalanche forecasting, snow stratigraphy, remote sensing ground truth), ski track characterization (ski racing) or snow runway characterization (stability testing). -
23
Botnet Detectors Comparer
Compares botnet detection methods
Compares botnet detection methods by computing the error metrics by reading the labels on a NetFlow file. The original NetFlow should have a new column for the ground-truth label, and a new column with the prediction label for each botnet detection method. This program computes all the error metrics (TPR, TNR, FPR, FNR, Precision, Accuracy, ErrorRate, FMeasure1, FMeasure2, FMeasure0.5) and output the comparison results. It also ouputs a png plot. The program can compare in a flow-by-flow basis, or it can apply our new botnet detection error metrics, that is time-based, detects IP addresses instead of flows and it is weighted to favor sooner detections. ... -
24
This project aims to provide a ground truth generator for visual hand tracking and full pose-recovery problems. The system generates ground truths based on virtual models, and provides as an output depth, full segmentation of joints, and much more.
-
25
A library implementing various quality metrics used in research to compare processed images to their ground truth.
