weilheim Goto Github PK

3dvideos2stereo

Code to extract stereo frame pairs from 3D videos, as used in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, arXiv:1907.01341"

centernet

Object detection, 3D detection, and pose estimation using center point detection:

course-description-computer-science

course-description-machine-learning

dppnet

DPPnet: Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

eeg

PyTorch EEG emotion analysis using DEAP dataset

esm-tracker

fairseq-py

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

feature-extraction

Code used to extract 2d and 3d CNN features

genetic-algorithm-for-tsp

C++ code that solves travelling salesman problem

hosts

镜像：https://coding.net/u/scaffrey/p/hosts/git

i3d-pytorch

Pytorch implementation of I3D

label_smoothing

Corrupted labels and label smoothing

random-visual-phrase

selfattentive

Implementation of A Structured Self-attentive Sentence Embedding

sibling-convolutional-video-encoder

sst

SST: Single-Stream Temporal Action Proposal

structured-self-attentive-sentence-embedding

An open-source implementation of the paper ``A Structured Self-Attentive Sentence Embedding'' published by IBM and MILA.

tensor2tensor

A library for generalized sequence to sequence models

tensorflow

Computation using data flow graphs for scalable machine learning

torchtexttutorial

A short tutorial for Torchtext, the NLP-specific add-on for Pytorch.

transformer

Video captioning with Goolge's Transformer model.

turn-tap

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

uvp

video-to-image

C++ function that extract all the frames of a video or create video using a set of images.