zhangjunyi1225054736 Goto Github PK

--object-detection

-sample_disequilibrium

acdt

This is the codes of ICCV workshop paper "How to Fully Exploit The Abilities of Aerial Image Detectors". Our model is based on detectron.pytorch.

adaptsegnet

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

awesome-semantic-segmentation

:metal: awesome-semantic-segmentation

bicyclegan

[NIPS 2017] Toward Multimodal Image-to-Image Translation

cadlab

Imaging Biomarkers and Computer-Aided Diagnosis Laboratory

caffe_3d_pose_estimation

from the image to estimate the human pose

chinese_ocr

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

convnetdraw

Draw multi-layer neural network in your browser

cornernet

db

A PyToch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

deep-learning-models

Keras code and weights files for popular deep learning models.

diffusion-models

A collection of diffusion models based on MindSpore

drone-object-detection

east

Implementation of EAST scene text detector in Keras

faster_rcnn-opencv_-visualization

A little change has been made to the visual parts of the faster_rcnn (pytorch) version of demo.py. The original code is to use Matplotlib to show every object in one picture in different picture. After the improvement of the opencv, all the object frames are presented in a picture.

fdass

few-shor-domain-adaptation

The code of ICCV workshop paper "Few-Shot Structured Domain Adaptation for Virtual-to-Real Scene Parsing"

few-shot-domain-adaptation

This is the codes of iccv workshop paper "Few-Shot Structured Domain Adaptation for Virtual-to-Real Scene Parsing"

fots

implement FOTS and apply it on real scenario.

fots.pytorch

an unofficial implementation of FOTS: Fast Oriented Text Spotting with a Unified Network

fsda

fsdaf

gan-tensorflow

Implementation of GAN in tensorflow

ganhacks

starter from "How to Train a GAN?" at NIPS2016

gradient_descent

题目描述： 1.Generate n = 2,000 points uniformly at random in the two-dimensional unit square.Which point do you expect the centroid to be? 2.What objective does the centroid of the points optimize? 3.Apply gradient descent to find the centroid. 4.Apply stochastic gradient descent to find the centroid. Can you say in simple words,what the algorithm is doing? 1、所谓质心，就是找到到所有点距离之和最小的点。由于点的生成都是随机的，所以期望的点是 : (0.5，0.5)。

icnet-tensorflow

An implementation of ICNet (Real-time image segmentation) in tensorflow, containing train/test phase, see tutorial at:

lsd-seg

Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation

mindformers