Running Google MoveNet Single Pose models on OpenVINO

MoveNet Single Pose tracking on OpenVINO A convolutional neural network model that runs on RGB images and predicts human joint locations of a single person. Two variant: Lightning and Thunder, the latter being slower but more accurate. MoveNet uses an smart cropping based on detections from the previous frame when the input is a sequence of frames. This allows the model to devote its attention and resources to the main subject, resulting in much better prediction quality without sacrificing the […]

Read more

State-of-the-art self-supervised methods for learning representations from images

Abstract Large-scale unlabeled data has allowed recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (MoCo and BYOL) use an inductive bias that different augmentations (e.g. random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks where an attacker poisons a part of the unlabeled data by adding a small trigger (known to the attacker) to the images. The model performance […]

Read more

A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency

Portrait Photo Retouching with PPR10K PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level ConsistencyJie Liang*, Hui Zeng*, Miaomiao Cui, Xuansong Xie and Lei Zhang. The proposed Portrait Photo Retouching dataset (PPR10K) is a large-scale and diverse dataset that contains: 11,161 high-quality raw portrait photos (resolutions from 4K to 8K) in 1,681 groups; 3 versions of manual retouched targets of all photos given by 3 expert retouchers; full resolution human-region masks of all photos. Samples Two example […]

Read more

Privacy-Preserving Federated Learning Applied to Decentralized Data

federated federated is the source code for the Bachelor’s Thesis. Privacy-Preserving Federated Learning Applied to Decentralized Data (Spring 2021, NTNU) Federated learning (also known as collaborative learning) is a machine learning technique that trains an algorithm across multiple decentralized edge devices or servers holding local data samples, without exchanging them. In this project, the decentralized data is the MIT-BIH Arrhythmia Database. Features ML pipelines using centralized learning or federated learning. Support for the following aggregation methods: Federated Stochastic Gradient Descent […]

Read more

Created to speed up the GUI-development process in Python

Tkinter Designer Tkinter Designer was created to speed up the GUI-development process in Python. It uses the well-known design software Figma to make creating beautiful Tkinter GUIs in Python a piece of cake. Tkinter Designer uses the Figma API to analyse a design file and create the respective code and files needed for the GUI. Even Tkinter Designer’s GUI is created using Tkinter Designer. ☄️ Advantages of Tkinter Designer Drag and Drop Interfaces Significantly faster than creating code manually. Ability […]

Read more

A multilingual multispeaker expressive speech synthesis framework

ERISHA ERISHA is a multilingual multispeaker expressive speech synthesis framework. It can transfer the expressivity to the speaker’s voice for which no expressive speech corpus is available. The term ERISHA means speech in Sanskrit. The framework of ERISHA includes various deep learning architectures such as Global Style Token (GST), Variational Autoencoder (VAE), and Gaussian Mixture Variational Autoencoder (GMVAE), and X-vectors for building prosody encoder. Currently, the library is in its initial stage of development and will be updated frequently in […]

Read more

A heraldry-related bot for the Heraldry Community

Heraldtron A heraldry-related bot, designed for the Heraldry Community. Requirements cchardet and aiodns are also recommended to improve performance. For convenience, these can all be installed with pip install -r requirements/main.txt. Setup As one may expect, this bot requires a bot account to run. Refer to the discord.py instructions on creating one for more information. For some functionality, a Google Cloud Platform account is required, with the Custom Search and Google Drive APIs enabled. Custom search features additionally require a […]

Read more

Fearless interactivity for Jupyter notebooks

nbsafety nbsafety adds a layer of protection to computational notebooks by solving the stale dependency problem when executing cells out-of-order. Here’s an example in action: Step 0: modify cell 1 Step 1: rerun cell 1 Step 2: rerun cell 2 Step 3: rerun cell 3 When the first cell is rerun, the second cell now contains a reference to an updated f and is suggested for re-execution with a turquoise highlight. The third cell contains a reference to a stale […]

Read more

Percolation simulation using python

PythonPercolation Percolation simulation using python. Exemple de percolation : Etude statistique sur le pourcentage de remplissage jusqu’à percolation dépendament de la largeur de la matrice (percolation gauche-droite): Percolation 3D : GitHub https://github.com/TonyChouteau/PythonPercolation    

Read more

A wonderful automated command line app for organizing your film media

Fylm Fylm is a wonderful automated command line app for organizing your film media. You can pronounce it Film or File ’em, whichever you like! It uses (highly suspect) heuristics to identify film files (or folders), then looks them up on TMDb to get all the correct details. Once that’s over and done with, it’ll rename them according to your OCD standards, and move them. Features Fylm can: Rename messy files and folders and make them pretty, like high.noon.1952.1080p.this.OTHER-JUNK » […]

Read more
1 632 633 634 635 636 928