GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → naoto0804 → Pytorch Inpainting With Partial Conv

naoto0804 / Pytorch Inpainting With Partial Conv

Licence: mit
Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions' [Liu+, ECCV2018]

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchcnn

Projects that are alternatives of or similar to Pytorch Inpainting With Partial Conv

Pulp Dronet
A deep learning-powered visual navigation engine to enables autonomous navigation of pocket-size quadrotor - running on PULP
Stars: ✭ 374 (-15%)
Mutual labels:  cnn
Neuralnetwork.net
A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN
Stars: ✭ 392 (-10.91%)
Mutual labels:  cnn
Asrt speechrecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Stars: ✭ 4,943 (+1023.41%)
Mutual labels:  cnn
Espnetv2
A light-weight, power efficient, and general purpose convolutional neural network
Stars: ✭ 377 (-14.32%)
Mutual labels:  cnn
Learning Deep Learning
Paper reading notes on Deep Learning and Machine Learning
Stars: ✭ 388 (-11.82%)
Mutual labels:  cnn
Tf Pose Estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+776.36%)
Mutual labels:  cnn
Cnn handwritten chinese recognition
CNN在线识别手写中文。
Stars: ✭ 365 (-17.05%)
Mutual labels:  cnn
Numpycnn
Building Convolutional Neural Networks From Scratch using NumPy
Stars: ✭ 436 (-0.91%)
Mutual labels:  cnn
Nmtpytorch
Sequence-to-Sequence Framework in PyTorch
Stars: ✭ 392 (-10.91%)
Mutual labels:  cnn
Tsai
Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai
Stars: ✭ 407 (-7.5%)
Mutual labels:  cnn
Flownet2 Tf
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Stars: ✭ 378 (-14.09%)
Mutual labels:  cnn
Deeplogo
A brand logo detection system using tensorflow object detection API.
Stars: ✭ 388 (-11.82%)
Mutual labels:  cnn
Deepface
Deep Learning Models for Face Detection/Recognition/Alignments, implemented in Tensorflow
Stars: ✭ 409 (-7.05%)
Mutual labels:  cnn
Rmdl
RMDL: Random Multimodel Deep Learning for Classification
Stars: ✭ 375 (-14.77%)
Mutual labels:  cnn
Fast Srgan
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
Stars: ✭ 417 (-5.23%)
Mutual labels:  cnn
Video obj
基于视频的目标检测算法研究
Stars: ✭ 372 (-15.45%)
Mutual labels:  cnn
Pytorch classification
利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码
Stars: ✭ 395 (-10.23%)
Mutual labels:  cnn
Sknet
Code for our CVPR 2019 paper: Selective Kernel Networks; See zhihu：https://zhuanlan.zhihu.com/p/59690223
Stars: ✭ 443 (+0.68%)
Mutual labels:  cnn
Tensorflow Tutorial
Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学
Stars: ✭ 4,122 (+836.82%)
Mutual labels:  cnn
Multi Class Text Classification Cnn
Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.
Stars: ✭ 410 (-6.82%)
Mutual labels:  cnn
View All Similar Projects ➔

pytorch-inpainting-with-partial-conv

Official implementation is released by the authors.

Note that this is an ongoing re-implementation and I cannot fully reproduce the results. Suggestions and PRs are welcome!

This is an unofficial pytorch implementation of a paper, Image Inpainting for Irregular Holes Using Partial Convolutions [Liu+, arXiv2018].

Requirements

  • Python 3.6+
  • Pytorch 0.4.1+
pip install -r requirements.txt

Usage

Preprocess

  • download Places2 and place it somewhere. The dataset should contain data_large, val_large, and test_large as the subdirectories. Don't forget to specify the root of the dataset by --root ROOT when using train.py or test.py

  • Generate masks by following [1] (saved under ./masks by default). Note that the way of the mask generation is different from the original work

python generate_data.py

Train

CUDA_VISIBLE_DEVICES=<gpu_id> python train.py

Fine-tune

CUDA_VISIBLE_DEVICES=<gpu_id> python train.py --finetune --resume <checkpoint_name>

Test

CUDA_VISIBLE_DEVICES=<gpu_id> python test.py --snapshot <snapshot_path>

Results

Here are some results from the test set after the training of 500,000 iterations and fine-tuning (freezing BN in encoder) of 500,000 iterations. The model is available here, but I don't ensure the quality. (Top to bottom: input, mask, image generated by the network, image which is combined with the original non-masked region of image, ground truth) Results

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].