Rainyfish

2D-sparse-dictionary-learning

2D-sparse-dictionary-learning

2D_sparse_dictionary_learning

2D-sparse-dictionary-learning

2E-VRP-ABC

In the process of solving the 2E-VRP problem, the large-scale destruction and repair algorithm is used to ensure that the algorithm does not fall into the local optimal solution. The process of the initialization process uses the greedy strategy to cluster the customers. The large-scale destruction process is to randomly remove the customer nodes on the satellite into the customer pool. The repair process is based on the reciprocal of the customer's distance to each customer in the customer pool. Gambling Select the satellite to which the customer belongs and engage in greedy insertion. For the second layer of path planning, you need to use multiple search operators, such as random sequence reversal exchange operator, crossover operator, damage and repair operator, and crossover operator variants, etc. to improve the artificial bee group algorithm Of the local search ability. To ensure that the global optimal situation can be found, the neighborhood of large-scale search. The improved artificial bee colony algorithm incorporates the idea of ​​simulated annealing and improves the global optimization ability of artificial bee colony algorithm. For the artificial bee colony algorithm, the combination of global optimization ability and local optimization ability improves the possibility that the algorithm can find a better solution than the existing method. Multi - operator artificial bee colony algorithm, which extends the search range of the food source 's neighborhood, and more possibilities to find the global optimal solution. The experimental results show that the algorithm can get better path planning results

aedat4tomat

Convert AEDAT4 files from DV into .mat files for matlab

DELM-SR

Decision Tree and Extreme Learning Machine based Single Image Super-resolution

DELM_SR

Decision Tree and Extreme Learning Machine for Single image Super-resolution

ELM_super

ELM_super_resolution

FASRGAN-and-Fs-SRGAN

Fine-grained Attention and Feature-sharing Generative Adversarial Networksfor Single Image Super-Resolution

MS-RHDN

Multi-scale Residual Hierarchical Dense Networks for Single Image Super-Resolution

Rainyfish/FASRGAN-and-Fs-SRGAN

Fine-grained Attention and Feature-sharing Generative Adversarial Networksfor Single Image Super-Resolution

Rainyfish/2E-VRP-ABC

In the process of solving the 2E-VRP problem, the large-scale destruction and repair algorithm is used to ensure that the algorithm does not fall into the local optimal solution. The process of the initialization process uses the greedy strategy to cluster the customers. The large-scale destruction process is to randomly remove the customer nodes on the satellite into the customer pool. The repair process is based on the reciprocal of the customer's distance to each customer in the customer pool. Gambling Select the satellite to which the customer belongs and engage in greedy insertion. For the second layer of path planning, you need to use multiple search operators, such as random sequence reversal exchange operator, crossover operator, damage and repair operator, and crossover operator variants, etc. to improve the artificial bee group algorithm Of the local search ability. To ensure that the global optimal situation can be found, the neighborhood of large-scale search. The improved artificial bee colony algorithm incorporates the idea of ​​simulated annealing and improves the global optimization ability of artificial bee colony algorithm. For the artificial bee colony algorithm, the combination of global optimization ability and local optimization ability improves the possibility that the algorithm can find a better solution than the existing method. Multi - operator artificial bee colony algorithm, which extends the search range of the food source 's neighborhood, and more possibilities to find the global optimal solution. The experimental results show that the algorithm can get better path planning results

Rainyfish/MS-RHDN

Multi-scale Residual Hierarchical Dense Networks for Single Image Super-Resolution

Rainyfish/DELM-SR

Decision Tree and Extreme Learning Machine based Single Image Super-resolution

Rainyfish/2D-sparse-dictionary-learning

2D-sparse-dictionary-learning

Rainyfish/2D_sparse_dictionary_learning

2D-sparse-dictionary-learning

Rainyfish/DELM_SR

Decision Tree and Extreme Learning Machine for Single image Super-resolution

Rainyfish/ELM_super

Rainyfish/ELM_super_resolution

Rainyfish/aedat4tomat

Convert AEDAT4 files from DV into .mat files for matlab

Rainyfish/libcaer

Minimal C library to access, configure and get data from neuromorphic sensors and processors. Currently supported devices are the Dynamic Vision Sensor (DVS), the DAVIS cameras, and the Dynap-SE neuromorphic processor. THIS IS A MIRROR. ORIGINAL PROJECT LIVES AT https://gitlab.com/inivation/libcaer

Rainyfish/MARDN

Multi-resolution Space-attended Residual Dense Network for Single Image Super-Resolution

Rainyfish/reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Rainyfish/rpg_esim

ESIM: an Open Event Camera Simulator

Rainyfish/sisr-irl

Official Pytorch implementation of "Improving Super-Resolution Methods via Incremental Residual Learning"

Rainyfish/VideoSuperResolution

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

Rainyfish/VisualDL

Deep Learning Visualization Toolkit（『飞桨』深度学习可视化工具 ）