MisakiTaro0414

bark

🔊 Text-Prompted Generative Audio Model

bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

BUTD

CCT

chept-2

Second iteration of the ChePT Neural Chess Engine. ChePT is a deep neural transformer based chess engine that not only plays moves learned from observing millions of high-level chess games, but presents cogent multilingual commentary describing the current game state, and intuition behind move choices.

Deep-Learning-Specialization-vol-1

Deep-Learning-Specialization-vol-2

Deep-Learning-Specialization-vol-4

GML

lps

[NeurIPS'23] Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

MisakiTaro0414/bark

🔊 Text-Prompted Generative Audio Model

MisakiTaro0414/bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

MisakiTaro0414/BUTD

MisakiTaro0414/CCT

MisakiTaro0414/chept-2

Second iteration of the ChePT Neural Chess Engine. ChePT is a deep neural transformer based chess engine that not only plays moves learned from observing millions of high-level chess games, but presents cogent multilingual commentary describing the current game state, and intuition behind move choices.

MisakiTaro0414/Deep-Learning-Specialization-vol-1

MisakiTaro0414/Deep-Learning-Specialization-vol-2

MisakiTaro0414/Deep-Learning-Specialization-vol-4

MisakiTaro0414/Deep-Learning-Specialization-vol-5

MisakiTaro0414/GML

MisakiTaro0414/lps

[NeurIPS'23] Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

MisakiTaro0414/ejtos-react_budget_app

react_budget_app

MisakiTaro0414/Game-Depression-Detection

MisakiTaro0414/image-captioning-bottom-up-top-down

PyTorch implementation of Image captioning with Bottom-up, Top-down Attention

MisakiTaro0414/MisakiTaro0414

MisakiTaro0414/SoftRL_GFlowNets

MisakiTaro0414/TensorFlow-Develepor-Specialization

MisakiTaro0414/uqwxd-react_labs

react_todolist

MisakiTaro0414/yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors