396 Open source projects that are alternatives of or similar to Tdd

Training Toolbox for Caffe

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data

Surveillance System Against Violence

Some tools and examples for pyCaffe including LMDB I/O, custom Python layers and monitoring training error and loss.

FeatherCNN is a high performance inference engine for convolutional neural networks.

🏭 Collaboratively build, visualize, and design neural nets in browser

Repository of my fashion-parsing project. This project is put on hold since I am doing another project now, but will debug if bugs are reported.

Caffe models (including classification, detection and segmentation) and deploy files for famouse networks

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

Paperspace API for python

Head Pose Estimator on Caffe

TensorRT Net Wrapper

An online GUI tool used to visualize prototxt and generate prototxt for caffe(current version).

Video Classification based on PyTorch

Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models

HAKE-Action in PyTorch

Convert Darknet model to Caffe's

MobileNet-v2 experimental network description for caffe

Transform the caffe model to pytorch model for Temporal Segment Network

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

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

Add-on package for ONNX format support in Chainer

face detection and alignment with mtcnn

convert model from mxnet to caffe without lossing precision

A collection of Audio and Speech pre-trained models.

To keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper

AI智能审查，支持色情识别、暴恐识别、语言识别、敏感文字检测和视频检测等功能，以及各种OCR识别能力，如身份证、驾照、行驶证、营业执照、银行卡、手写体、车牌和名片识别等功能，可以访问网站体验功能。

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

Caffe to VHDL

Caffe Implementation of Google's MobileNets (v1 and v2)

Active Convolution

Combine Baidu Research warpctc with Caffe

Convert a matcaffe model (column major) to a pycaffe or c++ caffe (row major) model

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

ResGCN: an efficient baseline for skeleton-based human action recognition.

A one stop shop for all of your activity recognition needs.

Detects Chinese traffic police commanding poses 检测中国交警指挥手势

This repo allocate DAPs code of our ECCV 2016 publication

A deep convolutional neural network system for live emotion detection

3D ResNets for Action Recognition

Self Maintained Caffe. In this version Faster-RCNN, RFCN needs layer are fully supported!

As a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).

Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

MobileNet-SSD(MobileNetSSD) + Neural Compute Stick(NCS) Faster than YoloV2 + Explosion speed by RaspberryPi · Multiple moving object detection with high accuracy.

This repository stores the files used for my summer internship's work on "teacher-student learning", an experimental method for training deep neural networks using a trained teacher model.

EPIC-KITCHENS-55 baselines for Action Recognition

This is an implementation of very deep two stream CNNs for action recognition. The implementation is inspired by Wang et. al., https://github.com/yjxiong/caffe. Some improvements from Wang's implementation include reading videos from LDMB database, faster testing using LDMB interface. The aim is to work better with big dataset such as UCF101, HMDB51, Sports1M and ActivityNet easily.

Generic PyTorch Dataset Implementation for Loading, Preprocessing and Augmenting Video Datasets

faster-rcnn c++ python model

Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition

《深度学习与计算机视觉》配套代码

Video classification tools using 3D ResNet

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

convert between pytorch, caffe prototxt/weights and darknet cfg/weights

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

MobilNet-SSD object detection in opencv 3.4.1

Reference caffe implementation of LSUV initialization

A Computation Graph Virtual Machine Based Deep Learning Framework