lizhengwei1992 / Residualdensenetwork Pytorch
Pytorch implement: Residual Dense Network for Image Super-Resolution
Stars: ✭ 107
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Residualdensenetwork Pytorch
Tfoptflow
Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)
Stars: ✭ 415 (+287.85%)
Mutual labels: cvpr2018
Polyrnn Pp Pytorch
PyTorch training/tool code for Polygon-RNN++ (CVPR 2018)
Stars: ✭ 672 (+528.04%)
Mutual labels: cvpr2018
Pwc Net
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
Stars: ✭ 1,142 (+967.29%)
Mutual labels: cvpr2018
Liteflownet
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
Stars: ✭ 474 (+342.99%)
Mutual labels: cvpr2018
Stargan
StarGAN - Official PyTorch Implementation (CVPR 2018)
Stars: ✭ 4,946 (+4522.43%)
Mutual labels: cvpr2018
Ffnet
Implementation of our CVPR 2018 Paper (FFNet: Video Fast-Forwarding via Reinforcement Learning)
Stars: ✭ 17 (-84.11%)
Mutual labels: cvpr2018
Siamese Rpn Pytorch
This is a re-implementation of Siamese-RPN with pytorch, which is CVPR2018 spotlight.
Stars: ✭ 345 (+222.43%)
Mutual labels: cvpr2018
Dhf1k
Revisiting Video Saliency: A Large-scale Benchmark and a New Model (CVPR18, PAMI19)
Stars: ✭ 96 (-10.28%)
Mutual labels: cvpr2018
Gibsonenv
Gibson Environments: Real-World Perception for Embodied Agents
Stars: ✭ 666 (+522.43%)
Mutual labels: cvpr2018
Facekit
Implementations of PCN (an accurate real-time rotation-invariant face detector) and other face-related algorithms
Stars: ✭ 1,028 (+860.75%)
Mutual labels: cvpr2018
Awesome Cvpr Paper
CVPR 论文收集，包含但不限于2021、2020、2019、2018、2017文章
Stars: ✭ 493 (+360.75%)
Mutual labels: cvpr2018
Lemniscate.pytorch
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Stars: ✭ 532 (+397.2%)
Mutual labels: cvpr2018
Vc
Code for CVPR'18 "Grounding Referring Expressions in Images by Variational Context"
Stars: ✭ 26 (-75.7%)
Mutual labels: cvpr2018
Atlasnet
This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.
Stars: ✭ 450 (+320.56%)
Mutual labels: cvpr2018
Super Slowmo
An attempt at a PyTorch implimentation of "Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation"
Stars: ✭ 73 (-31.78%)
Mutual labels: cvpr2018
Deraindrop
Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018)
Stars: ✭ 365 (+241.12%)
Mutual labels: cvpr2018
Polyrnn Pp
Inference Code for Polygon-RNN++ (CVPR 2018)
Stars: ✭ 704 (+557.94%)
Mutual labels: cvpr2018
Idn Caffe
Caffe implementation of "Fast and Accurate Single Image Super-Resolution via Information Distillation Network" (CVPR 2018)
Stars: ✭ 104 (-2.8%)
Mutual labels: cvpr2018
Surfacenetworks
Source code for CVPR 2018 Oral paper "Surface Networks"
Stars: ✭ 83 (-22.43%)
Mutual labels: cvpr2018
Lab
[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm
Stars: ✭ 956 (+793.46%)
Mutual labels: cvpr2018
ResidualDenseNetwork-Pytorch
Pytorch implement: Residual Dense Network for Image Super-Resolution
Two advantage ideas of the paper:
- join denese connect layer to ResNet
- concatenation of hierarchical features
Different with the paper, I just use there RDBs(Residual dense block), every RDB has three dense layers. So ,this is a sample implement the RDN(Residual Dense Network) proposed by the author.
Requirements
- python3.5 / 3.6
- pytorch >= 0.2
- opencv
Usage
you need prepare DIV2K dataset (./data/)
train model :
python3 main.py --model_name 'RDN' --load demo_x3_RDN --dataDir ./DIV2K/ --need_patch True --patchSize 144 --nDenselayer 3 --nFeat 64 --growthRate 32 --scale 3 --epoch 10000 --lrDecay 2000 --lr 1e-4 --batchSize 16 --nThreads 4 --lossType 'L1'
References
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].