vinocherish Goto Github PK

3d-resnets-pytorch

3D ResNets for Action Recognition (CVPR 2018)

action-recognition-using-3d-resnet

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

activityrecognition

Information about activity recognition

algorithm_interview_notes-chinese

2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记

awesome-algorithm

LeetCode, HackRank, 剑指offer, classic algorithm implementation

c3d-pytorch

Pytorch porting of C3D network, with Sports1M weights

centernet

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

cvpr2019

cvpr2019 papers，极市团队整理

deep-learning-21-examples

《21个项目玩转深度学习———基于TensorFlow的实践详解》配套代码

dl--yolo-real-time-object-detection

Deep Learning: Real-time object detection - YOLOv3 [Python, PyTorch]

efficient_densenet_pytorch

A memory-efficient implementation of DenseNets

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

feedback-cnn

The code is an implementation of Feedback Convolutional Neural Network for Visual Localization and Segmentation.

i3d_tcc_bilinear

Attention Mechanism

kinetics-i3d

Convolutional neural network model for video classification trained on the Kinetics dataset.

ml

natural-image-classification

This project was carried out using OpenCV Python and libraries such as numpy, matplotlib and scipy. It aims at classifying the images into three categories, namely, airplanes, cars and motorcycles using an Artificial Neural Network. Similar to humans, machines, too, require to analyze the features of an image to determine its content. Hence, for helping the system with the classification, we used algorithms such as Harris Corner Detection for detection of interest points in an image and consequently applied algorithms such as Histogram of Oriented Gradients (HoG), Speeded-Up Robust Features (SURF) and Daubechies D4 Wavelet Transform to generate the subsequent feature vectors. Our project utilized 160 out of the 500 images of Cars, 160 out of the 800 images of Motorcycles and 160 out of the 900 images of airplanes for training purposes. For the testing purposes, we selected 30 images from each of the categories which were not selected for the training. The system takes a test image as an input, classifies it into one of the three categories and annotates it.

pcv-book-code

:book:Python计算机视觉中译本实例代码

pretrained-models.pytorch

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

pytorch-playground

Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

pytorch-wavenet

An implementation of WaveNet with fast generation

pytorch-yolo-v3

A PyTorch implementation of the YOLO v3 object detection algorithm

pytorch_realtime_multi-person_pose_estimation

This is a pytorch version of Realtime_Multi-Person_Pose_Estimation, origin code is here https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation

pytorchconv3d

I3D and 3D-ResNets in PyTorch

real_time_video_action_recognition

real time video action recognition based on C3D

train_arch

vgg(vgg16,vgg19), resnet(resnet_v2_50,resnet_v2_101,resnet_v2_152), inception_v4, inception_resnet_v2,.....

trn-pytorch

Temporal Relation Networks

tsn-pytorch

Temporal Segment Networks (TSN) in PyTorch

two-stream-action-recognition

Using two stream architecture to implement a classic action recognition method on UCF101 dataset