aitechnology Goto Github PK

deformable-convnets

Deformable Convolutional Networks

deformable-convolution-pytorch

PyTorch implementation of Deformable Convolution

detect-track

detectorch

Detectorch - detectron for PyTorch

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

detectron.pytorch

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

detectron2_backbone

detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn

dink

🚕点云深度学习自动驾驶框架 | Point cloud DeepLearning Autonomous Driving Framework🚕

django-blog-tutorial

基于 python3.4 和 django1.9 的 Blog 项目

effective-python-ex

Effective Python程式碼練習-與-相關筆記-

effectivetensorflow

TensorFlow tutorials and best practices.

facenet

Face recognition using Tensorflow

faceswap-gan

A denoising autoencoder + adversarial loss for face swapping.

fashion-mnist

A MNIST-like fashion product database. Benchmark :point_right:

fastmask

FastMask: Segment Multi-scale Object Candidates in One Shot

fastmaskrcnn

Mask RCNN in TensorFlow

fttl-with-keras

Transfer Learning and Fine Tuning for Cross Domain Image Classification with Keras

hyperface-with-squeezenet

Two multitasking CNNs for simultaneous face detection, landmarks estimation and visibility, pose estimation and gender recognition. hyperface.py concatenates feature maps from initial, mid and final layers of the network and then branches out to different heads. multiout.py branches from the final layer of the network to different heads. DataGen2.py is the Data Generator used for reading multiple labels from json files. It is a modified version of Keras's default Data Generator. The idea is based on the following paper - [1] R. Ranjan, V. M. Patel, and R. Chellappa. Hyperface: A deep multitask learning framework for face detection, landmark localization, pose estimation, and gender recognition. CoRR, abs/1603.01249, 2016. The implementation is slightly different. The original HyperFace architecture is built on top of AlexNet while the implementation here uses another architecture called SqueezeNet.

image-retrieval-demo

基于tensorflow & servering & flask 的图像检索系统。

image_utility

Handy python scripts for image data-set processing.

imgaug

Image augmentation for machine learning experiments.

isc2021

Code for the Image similarity challenge.

jigsawpuzzlesolver

keras_realtime_multi-person_pose_estimation

Keras version of Realtime Multi-Person Pose Estimation project

kitti_ssd

SSD detection for KITTI

kittibox

A car detection model implemented in Tensorflow.

knn_cuda

Fast K-Nearest Neighbor search with GPU

lane-finding

pipeline that annotates front-facing car video with lane lines. used color transforms, edge detection, Hough feature extraction, and line segment analysis.

light_head_rcnn

Light-Head R-CNN

lightnet

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)