artem-gorodetskii Goto Github PK

a-pytorch-tutorial-to-sequence-labeling

Empower Sequence Labeling with Task-Aware Neural Language Model | a PyTorch Tutorial to Sequence Labeling

binary-classifier-with-transfer-learning

CNN Binary Classification Model.

cat-predictor

This project represents the integration of TensorFlow Lite into Android application. The application allows to take photos and predict probability of cats.

connect-x-competition

My project from Kaggle competition Connect X (https://www.kaggle.com/c/connectx).

examples

TensorFlow examples

face-encoder-decoder

Autoencoder for face encoding and decoding.

fill-missed-spaces

HTTP service that receives text with missing spaces and returns a corrected sentence and a list of missed spaces positions.

flowseq

Generative Flow based Sequence-to-Sequence Toolkit written in Python.

glow-pytorch

PyTorch implementation of Glow

graph-convolution-on-structured-documents

This repo contains code to convert Structured Documents to Graphs and implement a Graph Convolution Neural Network for node classification

keypoint-extraction-server-for-insurance-certificates

llm-finetuning

LLM Finetuning with peft

long-form-voice-cloning

Audio samples from "Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attention"

lunar-lander-openai-problem

Current project represents a solution of Lunar-Lander problem from OpenAI GYM library of environments. The training of agent was performed using Actor-Critic DQN model.

medical-domain-adaptation-with-transformer

ml-design-patterns

Source code accompanying O'Reilly book: Machine Learning Design Patterns

nutrient-deficiency-stress-segmentation

Application of a self-normalizing network for object segmentation.

pytorch-vae

A Collection of Variational Autoencoders (VAE) in PyTorch.

tacotron

Audio samples accompanying publications related to Tacotron, an end-to-end speech synthesis model.

tap-net

TAP-Net: Transport-and-Pack using Reinforcement Learning

transpix2pix

Rethinking the Pix2Pix architecture with attention mechanisms and transformers.

vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

wikiart-latent-diffusion

Conditional denoising diffusion probabilistic model trained in latent space.