Search Results for "high" - Page 31
Sort By:
Showing 1077 open source projects for "high"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
1
HiFi-GAN
Generative Adversarial Networks for Efficient and High Fidelity Speech
HiFi-GAN is a GAN-based neural vocoder designed to generate high-fidelity speech waveforms from mel spectrograms with exceptional efficiency. It introduces a generator architecture tailored to model the periodic structure of speech and a set of discriminators that focus on different scales and periods of the waveform to better capture naturalness. The model targets a sweet spot between sample quality and generation speed, outperforming many previous GAN vocoders while being far faster than typical autoregressive models. ... -
2
ALAE
Adversarial Latent Autoencoders
ALAE (Adversarial Latent Autoencoders) is a deep learning research implementation that combines autoencoders with generative adversarial networks to produce high-quality image synthesis models. The project implements the architecture introduced in the CVPR research paper on Adversarial Latent Autoencoders, which focuses on improving generative modeling by learning latent representations aligned with adversarial training objectives. Unlike traditional GANs that directly generate images from random noise, ALAE uses an encoder-decoder architecture that maps images into a structured latent space and then reconstructs them through adversarial training. ... -
3
pyrpl
PyRPL turns your Red Pitaya into a powerful analog feedback device.
...The graphical user interface (GUI) provides a realtime display of the various measurement instruments and allows the easy configuration of DSP signal chains and feedback controllers. At the highest abstraction level, arbitrary feedback sequences can be defined to fulfill tasks as complex as approaching and locking a resonance of a high-finesse Fabry-Perot cavity (tested up to finesse=100,000). -
4
Bitcoin Black Core
BLACK use peer-to-peer technology to operate with no central authority
Bitcoin Black Core is a peer-to-peer electronic cash system that aims to become sound global money with fast payments, micro fees, privacy, and high transaction capacity (big blocks). In the same way that physical money, such as a dollar bill, is handed directly to the person being paid, Bitcoin Black Core payments are sent directly from one person to another. As a permissionless, decentralized cryptocurrency, Bitcoin Black Core requires no trusted third parties and no central bank. ... -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
MToolBox
A bioinformatics pipeline to analyze mtDNA from NGS data
MToolBox is a highly automated bioinformatics pipeline to reconstruct and analyze human mitochondrial DNA from high throughput sequencing data. MToolBox includes an updated computational strategy to assemble mitochondrial genomes from Whole Exome and/or Genome Sequencing (PMID: 22669646) and an improved fragment-classify tool (PMID:22139932) for haplogroup assignment, functional and prioritization analysis of mitochondrial variants. MToolBox provides pathogenicity scores, profiles of genome variability and disease-associations for mitochondrial variants. ... -
6
BasicSR
Winning Solution in NTIRE19 Challenges on Video Restoration
BasicSR is a deep learning framework designed for advanced video restoration tasks such as video super-resolution, deblurring, and denoising. Unlike single-image restoration models, EDVR addresses the temporal dimension by aligning multiple video frames using deformable convolutional layers in a coarse-to-fine manner, allowing it to effectively handle large motion and complex scene dynamics. The architecture includes bespoke modules (e.g., Pyramid, Cascading and Deformable alignment and... -
7
OpenAI Glow
Copy code in "Glow: Generative Flow with Invertible 1x1 Convolutions"
...Unlike models that rely on approximate inference, Glow uses invertible transformations to directly learn the data distribution, allowing for exact likelihood computation and efficient sampling. The model is capable of producing high-quality synthetic images while maintaining interpretable latent spaces that enable meaningful manipulation of generated outputs. Glow’s architecture is based on reversible layers and efficient flow operations, which allow large-scale training while keeping memory usage manageable. The repository provides training code, pretrained models, and scripts for generating samples or reproducing key results from the original research. ... -
8
--- IMPORTANT : This project has been moved to GitHub at https://github.com/clstoulouse/motu-client-python. Download the last version from the release page https://github.com/clstoulouse/motu-client-python/releases. --- Motu is a high efficient and robust Web Server which fills the gap between heterogeneous Data Providers to End Users. Motu handles, extracts and transforms oceanographic huge volumes of data without performance collapse. This client enables to extract and download data through a python command line Indesol project sample: http://www.indeso.web.id/indeso_wp/index.php/faq/30-6-how-to-write-and-run-the-script-to-download-indeso-met-ocean-data
-
9
TFLearn
Deep learning library featuring a higher-level API for TensorFlow
...Easy and beautiful graph visualization, with details about weights, gradients, activations, and more. Effortless device placement for using multiple CPU/GPU. The high-level API currently supports the most of the recent deep learning models, such as Convolutions, LSTM, BiRNN, BatchNorm, etc. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
Metrix++
Management of source code quality is possible.
...Every metric has got 'turn-on' and other configuration options. There are no predefined thresholds for metrics or rules. You can choose and configure any limit you want. - High-performance. Processes thousands of files per minutes. - Seamless application to legacy code due to embedded capability to differentiate new code, modified and legacy. -
11
surpriver
Find big moving stocks before they move using machine learning
surpriver is a machine learning project designed to identify unusual stock market activity that may precede large price movements. The system analyzes historical stock price and volume data to detect anomalies that could indicate potential trading opportunities. By applying machine learning techniques to market indicators, the tool attempts to identify patterns in trading behavior that deviate significantly from normal market activity. These anomalies are interpreted as signals that a stock... -
12
Frontend Regression Validator (FRED)
Visual regression tool used to compare baseline and updated instances
...The visual analysis computes the Normalized Mean Squared error and the Structural Similarity Index on the screenshots of the baseline and updated sites, while the visual AI looks at layout and content changes independently by applying image segmentation Machine Learning techniques to recognize high-level text and image visual structures. This reduces the impact of dynamic content yielding false positives. FRED is designed to be scalable. It has an internal queue and can process websites in parallel depending on the amount of RAM and CPUs (or GPUs) available. -
13
AdaNet
Fast and flexible AutoML with learning guarantees
AdaNet is a TensorFlow framework for fast and flexible AutoML with learning guarantees. AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention. AdaNet builds on recent AutoML efforts to be fast and flexible while providing learning guarantees. Importantly, AdaNet provides a general framework for not only learning a neural network architecture but also for learning to the ensemble to obtain even better models. At each iteration, it measures the ensemble loss for each candidate, and selects the best one to move onto the next iteration. ... -
14
Forecasting Best Practices
Time Series Forecasting Best Practices & Examples
Time series forecasting is one of the most important topics in data science. Almost every business needs to predict the future in order to make better decisions and allocate resources more effectively. This repository provides examples and best practice guidelines for building forecasting solutions. The goal of this repository is to build a comprehensive set of tools and examples that leverage recent advances in forecasting algorithms to build solutions and operationalize them. Rather than... -
15
StellarGraph
Machine Learning on Graphs
...For example, a graph can contain people as nodes and friendships between them as links, with data like a person’s age and the date a friendship was established. StellarGraph supports the analysis of many kinds of graphs. StellarGraph is built on TensorFlow 2 and its Keras high-level API, as well as Pandas and NumPy. It is thus user-friendly, modular and extensible. It interoperates smoothly with code that builds on these, such as the standard Keras layers and scikit-learn. -
16
ENAS in PyTorch
PyTorch implementation of "Efficient Neural Architecture Search
ENAS in PyTorch is a PyTorch implementation of Efficient Neural Architecture Search (ENAS), a method that automates the design of neural network architectures through reinforcement learning and parameter sharing. The repository demonstrates how a controller network can explore a large search space and discover high-performing architectures while dramatically reducing the computational cost traditionally associated with neural architecture search. It is primarily intended as a research and educational codebase, helping practitioners understand how ENAS works in practice and how to reproduce results on benchmark datasets. The project includes training scripts, model definitions, and search procedures that show the full workflow from architecture sampling to evaluation. ... -
17
Super-résolution via CNN
Super resolution using a CNN, based on the work of the DGtal team
...This program will generate "model_epoch_ .pth" files corresponding to the model at epoch n, in a folder saved_model_u t_bs bs_tbs tbs_lr lr, where corresponds to the scale factor, bsthe size of the training batch, tbsthe size of the test batch and lrto the learning rate. Low res images should be located in a "dataset/input" folder, and high res targets in a "dataset/target" folder, where each different quality image has the same name in both folders. -
18
CBMPy
PySCeS Constraint Based Modelling
...CBMPy supports user interaction via: - interactive console or as a library for advanced use - GUI, visual representation of the model, analysis methods - a SOAP based webAPI exposes high level functionality via web services -
19
DeepFaceLab
The leading software for creating deepfakes
...It offers an imperative and easy-to-use pipeline that even those without a comprehensive understanding of the deep learning framework or model implementation can use; and yet also provides a flexible and loose coupling structure for those who want to strengthen their own pipeline with other features without having to write complicated boilerplate code. DeepFaceLab can achieve results with high fidelity that are indiscernible by mainstream forgery detection approaches. Apart from seamlessly swapping faces, it can also de-age faces, replace the entire head, and even manipulate speech (though this will require some skill in video editing). -
20
End-to-End Negotiator
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
...The framework provides code for both supervised learning (training from human dialogue data) and reinforcement learning (via self-play and rollout-based planning). It introduces a hierarchical latent model, where high-level intents are first clustered and then translated into coherent language, improving dialogue diversity and goal consistency. The repository also includes the Negotiate dataset, comprising over 5,800 dialogues across 2,200 unique scenarios. -
21
GROWbox Supervisor System (GROWSS)
Automated Plant Environment Growing System using Raspberry Pi
...The environmental values are saved to the local storage every 15 minutes and when an alarm is present. Hi & low values are also saved. The LEDs on the case & the mobile application indicate if there is a high/low temp alarm, hi/low humidity alarm, soil moisture alarm, or smoke alarm. A speaker (buzzer) is activated on the case if there is a smoke alarm. 2 other LEDs indicate if either the exhaust fan is on or if the humidifier is on. -
22
TensorNets
High level network definitions with pre-trained weights in TensorFlow
High level network definitions with pre-trained weights in TensorFlow (tested with 2.1.0 >= TF >= 1.4.0). Applicability. Many people already have their own ML workflows and want to put a new model on their workflows. TensorNets can be easily plugged together because it is designed as simple functional interfaces without custom classes. -
23
HyLiTE
Hybrid Lineage Transcriptome Explorer
HyLiTE (Hybrid Lineage Transcriptome Explorer) analyzes high-throughput transcriptome data from allopolyploid species. Allopolyploidy describes the formation of a new hybrid organism from the union of two or more different parents. Allopolyploid species carry multiple copies of each gene (homeologs), which often exhibit unusual expression patterns. Homeolog expression levels can technically be determined from next generation sequencing data (RNA-seq), but in practice, assigning reads to one homeolog over another is extremely challenging, particularly on a whole-genome scale. ... -
24
TensorFlow Object Counting API
The TensorFlow Object Counting API is an open source framework
The TensorFlow Object Counting API is an open source framework built on top of TensorFlow and Keras that makes it easy to develop object counting systems. Please contact if you need professional object detection & tracking & counting project with super high accuracy and reliability! You can train TensorFlow models with your own training data to built your own custom object counter system! If you want to learn how to do it, please check one of the sample projects, which cover some of the theory of transfer learning and show how to apply it in useful projects. The development is on progress! ... -
25
BytePS
A high performance and generic framework for distributed DNN training
BytePS is a high-performance and generally distributed training framework. It supports TensorFlow, Keras, PyTorch, and MXNet, and can run on either TCP or RDMA networks. BytePS outperforms existing open-sourced distributed training frameworks by a large margin. For example, on BERT-large training, BytePS can achieve ~90% scaling efficiency with 256 GPUs (see below), which is much higher than Horovod+NCCL.
