CashewMIC

models

Models and examples built with TensorFlow

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Dive-into-DL-PyTorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

PyTorch-YOLOv3

Minimal PyTorch implementation of YOLOv3

tensorflow-yolov3

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

a-PyTorch-Tutorial-to-Object-Detection

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

a-PyTorch-Tutorial-to-Image-Captioning

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

Deep-Tutorials-for-PyTorch

In-depth tutorials for implementing deep learning models on your own with PyTorch.

SysDVR

Stream switch games to your PC via USB or network

coco-caption

awesome-image-captioning

A curated list of image captioning and related area resources. :-)

KnowledgeGraph

knowledge graph知识图谱,从零开始构建知识图谱

K-BERT

Source code of K-BERT (AAAI2020)

SpeedTorch

Library for faster pinned CPU <-> GPU transfer in Pytorch

Fewshot_Detection

Few-shot Object Detection via Feature Reweighting

NeuralBabyTalk

Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"

One-Shot-Object-Detection

Implementation of One-Shot Object Detection with Co-Attention and Co-Excitation in Pytorch

transE

pycocoevalcap

Python 3 support for the MS COCO caption evaluation tools

a-PyTorch-Tutorial-to-Transformers

Attention Is All You Need | a PyTorch Tutorial to Transformers

asg2cap

Code accompanying the paper "Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs" (Chen et al., CVPR 2020, Oral).

CopyNet

An implementation of "Incorporating copying mechanism in sequence-to-sequence learning"

FewShotVision

Code for Master research internship report : https://arxiv.org/abs/1909.13579

DCC

Implementation of CVPR 2016 paper

starsem18-multimodalKB

Decoupled-Novel-Object-Captioner

Code for Decoupled Novel Object Captioner

pytorch_image_caption

Image Caption, Show and Tell.

MKGC

MKGC is a method of fusion multimodal information to enhance knowledge graphs completion

KGA

Knowledge Guided Attention and Inference for Describing Images containing Unseen Visual Object Categories.