Search Results for "dataset" - Page 13
Sort By:
Showing 341 open source projects for "dataset"
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.
-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
1
The GAN Zoo
A list of all named GANs
...Because new GAN models are frequently introduced in research publications, the repository serves as a convenient catalog that organizes them in one location. The list includes references to many GAN variants along with links to their original research papers and sometimes implementation code. Users can browse the dataset or explore a tabular version that allows filtering by year or searching for specific model names. The repository encourages contributions from the community so that newly published GAN architectures can be added to the list. -
2
BossSensor
Hide screen when boss is approaching
...The software relies on libraries such as OpenCV, TensorFlow, and Python-based machine learning tools to perform face detection and classification. Training the system requires a dataset of labeled images representing the boss and other people so that the model can learn to differentiate between them. -
3
reNamer
Rename files depending on their .extension
If you want to rename your dataset samples for ML and you might have a lot of them (you should btw) or maybe you need to set different enumeration for every .extension you have or you just want to rename some personal stuff I am glad you are here. This is how you can rename your files: - For every .extension in the target folder reNamer sets unique enumeration -
4
Exposure
Learning infinite-resolution image processing with GAN and RL
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model. ACM Transactions on Graphics (presented at SIGGRAPH 2018) Exposure is originally designed for RAW photos, which assumes 12+ bit color depth and linear "RGB" color space (or whatever we get after demosaicing). jpg and png images typically have only 8-bit color depth (except 16-bit pngs) and the lack of information (dynamic range/activation resolution) may... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
3D ResNets for Action Recognition
3D ResNets for Action Recognition (CVPR 2018)
We uploaded the pretrained models described in this paper including ResNet-50 pretrained on the combined dataset with Kinetics-700 and Moments in Time. We significantly updated our scripts. If you want to use older versions to reproduce our CVPR2018 paper, you should use the scripts in the CVPR2018 branch. -
6
Mixup-CIFAR10
mixup: Beyond Empirical Risk Minimization
...By interpolating both data and labels, the model learns smoother decision boundaries and becomes more robust to noise and adversarial examples. This repository implements mixup for the CIFAR-10 dataset, showcasing its effectiveness in improving generalization, stability, and calibration of neural networks. The approach acts as a regularizer, encouraging linear behavior in the feature space between samples, which helps reduce overfitting and enhance performance on unseen data. -
7
mzitu
Python crawler that downloads image galleries and analyzes titles
...It focuses on automating the collection of large sets of images by programmatically parsing page content and iterating through gallery entries. mzitu also includes a simple analysis script that processes downloaded folder names to generate statistics and visualizations. Using text segmentation and frequency analysis, the project can create a word cloud representing common keywords found in the dataset. This makes the repository both a scraping example and a small data analysis experiment built around the collected content. Overall, mzitu serves as a learning-oriented implementation of Python web scraping, data processing, and visualization techniques. -
8
ECDICT
Free English to Chinese Dictionary Database
...Because it’s offline and local, it avoids network latency and licensing hurdles that come with calling proprietary dictionary APIs. The dataset is large enough to support general-purpose lookup while being manageable to ship with desktop or mobile apps. For builders, it’s a pragmatic foundation for dictionary apps, pop-up translators, flashcard tools, or NLP preprocessing. -
9
Charting tools, backtesting tools, and data visualization tools for the most popular cryptocurrencies.
-
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
10
Zhao
A compilation of "The Princely Party Relationship Network"
...Because it aggregates content associated with Zhao, the repository functions as a personal or shared knowledge base for readers who want insight into a body of research rather than a traditional software library. Depending on the specific subfolders, it could offer implementations of algorithms, dataset processing utilities, or notebooks that illustrate concepts. Users interested in reading academic work or numerical demonstrations can use the content to deepen understanding of advanced topics. -
11
Gensim-data
Data repository for pretrained NLP models and NLP corpora
...Downloads are cached in a local gensim-data directory for later reuse. The collection includes corpora such as text8 and 20 Newsgroups alongside pretrained word-vector resources such as GloVe. Every dataset retains its own licensing terms, so users must review individual usage conditions. -
12
EvalAI
Evaluating state of the art in AI
EvalAI is an open-source platform for evaluating and comparing machine learning (ML) and artificial intelligence (AI) algorithms at scale. We allow the creation of an arbitrary number of evaluation phases and dataset splits, compatibility using any programming language, and organizing results in both public and private leaderboards. Certain large-scale challenges need special computing capabilities for evaluation. If the challenge needs extra computational power, challenge organizers can easily add their own cluster of worker nodes to process participant submissions while we take care of hosting the challenge, handling user submissions, and maintaining the leaderboard. ... -
13
xmgrace python interface
xmgrace and qtgrace plotting interface in python
This is a python module providing a nearly complete interface to the graphing program xmgrace and the new qtgrace (great project... grace works under windows, too, now!). It allows creation of grace plots from within python, which can be customized using python, or through grace after creation. -
14
DC-TTS
TensorFlow Implementation of DC-TTS: yet another text-to-speech model
...Training scripts, data loaders, and hyperparameter configurations are provided to reproduce results on several datasets, including LJ Speech for English, a Korean single-speaker dataset, and audiobook data from Nick Offerman and Kate Winslet. -
15
Siamese and triplet learning
Siamese and triplet networks with online triplet mining in PyTorch
Siamese and triplet learning is a PyTorch implementation of Siamese and triplet neural network architectures designed for learning embedding representations in machine learning tasks. These types of networks learn to map images into a compact feature space where the distance between vectors reflects the similarity between inputs. Such embeddings are commonly used in applications like face recognition, image similarity search, and few-shot learning. The repository demonstrates how to train... -
16
FastPhotoStyle
Style transfer, deep learning, feature transform
...It is computationally efficient due to its closed-form solution, allowing fast processing compared to iterative optimization-based methods. The framework is particularly useful in applications such as photo editing, film post-processing, and dataset augmentation where realism is critical. By preserving structural details and avoiding distortions, it produces results that are visually consistent with natural images. -
17
House3D
A Realistic and Rich 3D Environment
House3D is a large-scale virtual 3D simulation environment designed to support research in embodied AI, reinforcement learning, and vision-language navigation. It provides more than 45,000 richly annotated indoor scenes sourced from the SUNCG dataset, covering diverse architectural layouts such as studios, multi-floor homes, and spaces with detailed furnishings and room types. Each environment includes fully labeled 3D objects, allowing agents to perceive and interact with their surroundings through multiple sensory modalities including RGB images, depth maps, semantic segmentation masks, and top-down maps. ... -
18
BlockSparse
Efficient GPU kernels for block-sparse matrix multiplication
...The repo implements both blocksparse and blockwise convolution/transpose-convolution primitives, with support for preparing, executing, and verifying those ops on NVIDIA GPUs. In addition to low-level kernels, it includes wrapper code for integrating with TensorFlow, example scripts (e.g. a transformer on the enwik8 dataset), transformer logic that uses blocksparse operations, and debugging helpers. -
19
WikiSQL
A large annotated semantic parsing corpus for developing NL interfaces
A large crowd-sourced dataset for developing natural language interfaces for relational databases. WikiSQL is the dataset released along with our work Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. Regarding tokenization and Stanza, when WikiSQL was written 3-years ago, it relied on Stanza, a CoreNLP python wrapper that has since been deprecated. -
20
auto_ml
Automated machine learning for analytics & production
...You can pass in your own function to perform feature engineering on the data. This will be called as the first step in the pipeline that auto_ml builds out. You will be passed the entire X dataset (not the y dataset), and are expected to return the entire X dataset. The advantage of including it in the pipeline is that it will then be applied to any data you want predictions on later. -
21
Seq2seq Chatbot for Keras
This repository contains a new generative model of chatbot
This repository contains a new generative model of chatbot based on seq2seq modeling. The trained model available here used a small dataset composed of ~8K pairs of context (the last two utterances of the dialogue up to the current point) and respective response. The data were collected from dialogues of English courses online. This trained model can be fine-tuned using a closed-domain dataset to real-world applications. The canonical seq2seq model became popular in neural machine translation, a task that has different prior probability distributions for the words belonging to the input and output sequences since the input and output utterances are written in different languages. ... -
22
X-SOCS
X-ray Strain Orientation Calculation Software
...Chahine), follow the instruction in the following link: https://gitlab.esrf.fr/kmap/xsocs You can find on youtube video tutorials explaining the main steps to follow for a standard KMAP data analysis. In the folder XSOCS_tutorials_data of the Files tab, you can download the dataset used in the tutorials. Make sure to read the readme file. -
23
PyCosmic is a tool to detect and clean single images from the disturbing cosmic ray hits. It was designed and tested specifically for CALIFA and other fiber-fed integral-field spectroscopy dataset. It is written in Python and can be executed from the command line. New release is version v0.5. Updated to be compatible with numpy version 1.12. New release is version v0.4. It's now compatible with astropy for fits I/O and computation time is reduced by a factor of 2.
-
24
Question Answering Corpus
Question answering dataset in "Teaching Machines to Read & Comprehend"
RC-Data is a dataset generation framework created by Google DeepMind to produce large-scale reading comprehension question-answer pairs from CNN and Daily Mail news articles. The dataset, introduced in the 2015 paper “Teaching Machines to Read and Comprehend” (Hermann et al., NIPS 2015), was among the first large corpora designed to train and evaluate machine reading and comprehension models. -
25
2DFLT
Program for Normalization, Averaging and Editing of In Situ Data Sets
2DFLT it is first out of two programs which allows implementation of Phase Sensitive Detection (PSD) and/or Modulated Enhanced Diffraction (MED) techniques on the in situ data. This software allows collecting individual data files from in situ experiment into one dataset. After that this data set can be visualized, edited, normalized and averaged. Resulted data can be saved as one flat file (FLT-format) which can be used for PSD/MED calculations via 2DMED software (http://sourceforge.net/projects/twodmed/?source=directory). 2DFLT specifically was written to target in situ X-ray Powder Diffraction data from synchrotron measurements. ...