Search Results for "tasks" - Page 35
Sort By:
Showing 1120 open source projects for "tasks"
View related business solutions-
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.
-
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.
-
1
nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
...It then covers TextCNN, recurrent networks, LSTM, bidirectional LSTM, sequence-to-sequence learning, and attention. Later examples implement the Transformer and BERT for translation, classification, and masked-token tasks. Paper links and Google Colab notebooks connect each implementation with its research background and an accessible runtime. -
2
pbxproj
A python module to manipulate XCode projects
This module can read, modify, and write a .pbxproj file from an Xcode 4+ project. The file is usually called project.pbxproj and can be found inside the .xcodeproj bundle. Because some tasks cannot be done by clicking on a UI or opening Xcode to do it for you, this Python module lets you automate the modification process. The typical tasks with an Xcode project are adding files to the project and setting some standard compilation flags. -
3
Practice Python
Part of my daily plan for studying Python
practice-python provides a structured set of small, focused exercises aimed at building fluency with Python fundamentals. The tasks emphasize real coding over passive reading, nudging you to write, run, and iterate on solutions. Exercises commonly target strings, lists, dictionaries, control flow, functions, classes, and common algorithms, reinforcing idiomatic Python patterns. Many problems are intentionally minimal in boilerplate so you can concentrate on logic and clarity. -
4
Old Photo Restoration
Bringing Old Photo Back to Life (CVPR 2020 oral)
We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces. ... -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
Kashgari
Kashgari is a production-level NLP Transfer learning framework
Kashgari is a simple and powerful NLP Transfer learning framework, build a state-of-art model in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS), and text classification tasks. -
6
scikit-opt
Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing
...It includes genetic algorithms, particle swarm optimization, differential evolution, simulated annealing, ant colony optimization, immune algorithms, and artificial fish swarms. The package can address continuous objectives, constrained problems, and combinatorial tasks such as the traveling salesman problem. A consistent workflow lets users define an objective, configure an optimizer, run iterations, and inspect the best solution. Genetic algorithm operators can be replaced through user-defined functions or subclassing. Runs may continue from earlier iterations instead of restarting. Vectorization, threading, multiprocessing, caching, examples, and plotting support help users experiment with performance and convergence. -
7
SimSiam
PyTorch implementation of SimSiam
...The repository provides scripts for both unsupervised pre-training and linear evaluation, using a ResNet-50 backbone by default. It is compatible with multi-GPU distributed training and can be fine-tuned or transferred to downstream tasks like object detection following the same setup as MoCo. -
8
YOLOv4-large
Scaled-YOLOv4: Scaling Cross Stage Partial Network
...This scaling strategy enables the model to adapt to different hardware environments while maintaining a strong balance between speed and detection accuracy. The repository includes multiple model variants such as YOLOv4-tiny, YOLOv4-CSP, and large-scale configurations designed for high-performance detection tasks. -
9
AliceMind
ALIbaba's Collection of Encoder-decoders from MinD
...It achieves new SOTA results in several downstream tasks. -
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.
-
10
FARM
Fast & easy transfer learning for NLP
...It's built upon transformers and provides additional features to simplify the life of developers: Parallelized preprocessing, highly modular design, multi-task learning, experiment tracking, easy debugging and close integration with AWS SageMaker. With FARM you can build fast proofs-of-concept for tasks like text classification, NER or question answering and transfer them easily into production. Easy fine-tuning of language models to your task and domain language. AMP optimizers (~35% faster) and parallel preprocessing (16 CPU cores => ~16x faster). Modular design of language models and prediction heads. Switch between heads or combine them for multitask learning. ... -
11
Footcontroller
Control your Linux PC with a standard foot pedal
...Many foot pedals come with software, often MS Windows only, which allows you to program the pedals to perform some function or other, Footcontroller does away with the proprietary software and allows you to define multiple sets of commands that can be swapped in or out at the click of a button. The advantage is that now, your foot pedal can perform different tasks in multiple situations simply by selecting the appropriate pedal set, rather than having to re-program the foot pedal from scratch. -
12
SRU
Training RNNs as Fast as CNNs
...SRU is designed to provide expressive recurrence, enable highly parallelized implementation, and comes with careful initialization to facilitate the training of deep models. We demonstrate the effectiveness of SRU on multiple NLP tasks. SRU achieves 5--9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets, and delivers stronger results than LSTM and convolutional models. We also obtain an average of 0.7 BLEU improvement over the Transformer model on the translation by incorporating SRU into the architecture. The experimental code and SRU++ implementation are available on the dev branch which will be merged into master later. -
13
TimeSformer
The official pytorch implementation of our paper
...The official implementation in PyTorch provides configurations, pretrained models, and training scripts that make it straightforward to evaluate or fine-tune on video datasets. TimeSformer was influential in showing that pure transformer architectures—without convolutional backbones—can perform strongly on video classification tasks. Its flexible attention design allows experimenting with different factoring (spatial-then-temporal, joint, etc.) to trade off compute, memory, and accuracy. -
14
jiant
jiant is an nlp toolkit
Jiant is a multitask NLP framework for fine-tuning transformer-based models on multiple natural language understanding (NLU) tasks. -
15
SimCSE
SimCSE: Simple Contrastive Learning of Sentence Embeddings
SimCSE (Simple Contrastive Learning of Sentence Embeddings) is a machine learning framework for training sentence embeddings using contrastive learning. It improves representation learning for NLP tasks. -
16
UniVL
Official implementation for UniVL video and language training models
UniVL is a video-language pretrain model. It is designed with four modules and five objectives for both video language understanding and generation tasks. It is also a flexible model for most of the multimodal downstream tasks considering both efficiency and effectiveness. -
17
Pytorch Points 3D
Pytorch framework for doing deep learning on point clouds
Torch Points 3D is a framework for developing and testing common deep learning models to solve tasks related to unstructured 3D spatial data i.e. Point Clouds. The framework currently integrates some of the best-published architectures and it integrates the most common public datasets for ease of reproducibility. It heavily relies on Pytorch Geometric and Facebook Hydra library thanks for the great work! We aim to build a tool that can be used for benchmarking SOTA models, while also allowing practitioners to efficiently pursue research into point cloud analysis, with the end goal of building models which can be applied to real-life applications. ... -
18
deep-learning-for-image-processing
deep learning for image processing including classification
...Additional sections cover object detection, semantic segmentation, instance segmentation, and keypoint detection using widely studied models. The project is designed as a learning resource for students and developers who want readable code and guided comparisons across computer vision tasks. -
19
XLM (Cross-lingual Language Model)
PyTorch original implementation of Cross-lingual Language Model
...It popularized objectives like Masked Language Modeling (MLM) across many languages and Translation Language Modeling (TLM) that jointly trains on parallel sentence pairs to tighten cross-lingual alignment. Using a shared subword vocabulary, XLM learns language-agnostic features that work well for classification and sequence labeling tasks such as XNLI, NER, and POS without target-language supervision. The repository provides preprocessing pipelines, training code, and fine-tuning scripts so you can reproduce benchmark results or adapt models to your own multilingual corpora. Pretrained checkpoints cover dozens of languages and multiple model sizes, balancing quality and compute needs. -
20
gym-pybullet-drones
PyBullet Gymnasium environments for multi-agent reinforcement
Gym-PyBullet-Drones is an open-source Gym-compatible environment for training and evaluating reinforcement learning agents on drone control and swarm robotics tasks. It leverages the PyBullet physics engine to simulate quadrotors and provides a platform for studying control, navigation, and coordination of single and multiple drones in 3D space. -
21
BMC
Notes on Scientific Computing for Biomechanics
This repository is a collection of lecture notes and code on scientific computing and data analysis for Biomechanics and Motor Control. -
22
earthengine-py-notebooks
A collection of 360+ Jupyter Python notebook examples
...These notebooks are organized into thematic areas such as image processing, machine learning, visualization, filtering, and asset management, exposing users to real geospatial analysis tasks. The repository makes it easier to explore Earth Engine’s large geospatial data catalog, interactively display map layers, and generate visual insights without the need for external GIS software by leveraging interactive widgets and mapping libraries. Many of the notebooks integrate with tools like folium, ipyleaflet, and geemap to bridge Earth Engine data with Python’s rich ecosystem for plotting and analysis. ... -
23
Keras TCN
Keras Temporal Convolutional Network
...The receptive field of the TCN can be calculated. Once keras-tcn is installed as a package, you can take a glimpse of what is possible to do with TCNs. Some tasks examples are available in the repository for this purpose. -
24
onnxt5
Summarization, translation, sentiment-analysis, text-generation, etc.
...The simplest way to get started for generation is to use the default pre-trained version of T5 on ONNX included in the package. Please note that the first time you call get_encoder_decoder_tokenizer, the models are being downloaded which might take a minute or two. Other tasks just require to change the prefix in your prompt, for instance for summarization. Run any of the T5 trained tasks in a line (translation, summarization, sentiment analysis, completion, generation) Export your own T5 models to ONNX easily. Utility functions to generate what you need quickly. Up to 4X speedup compared to PyTorch execution for smaller contexts. -
25
PORORO
Platform of neural models for natural language processing
pororo performs Natural Language Processing and Speech-related tasks. It is easy to solve various subtasks in the natural language and speech processing field by simply passing the task name. Recognized speech sentences using the trained model. Currently English, Korean and Chinese support. Get vector or find similar words and entities from pretrained model using Wikipedia.
