Caffe: a fast open framework for deep learning.

Other

caffe

Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE

deepdetect

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

MIT License

MMdnn

Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.

data-science-ipython-notebooks

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

mtcnn-caffe

caffe-tensorflow

Visual-Memorability-through-Caffe

DeepPyramid

Not Suitable for Work (NSFW) classification using deep neural network Caffe models.

BSD 2-Clause "Simplified" License

open_nsfw

A DSL for deep neural networks, supporting Caffe and Torch

dnngraph

hipCaffe


Description


This is macOS version of the iOS app waifu2x.This app can scale and/or denoise images, GIFs and videos using various advanced on-device AI algorithms. Note that this app is not affiliated with the original waifu2x project.Privacy is one of the top priorities of this app. Your images and videos will never leave your device to be processed. Additionally, we don't collect any personal information because there are no ADs even if you only use free models. Therefore, if you encounter any problems, please send us a feedback email or create a GitHub issue so that we can work together to fix them.Try additional models and custom models on your own images for free before you purchase!macOS exclusive features:1. Command line interface (CLI) support.2. Advanced video processing via CLI.3. Accelerate batch processing using multiple GPUs and ANE in parallel (advanced mode required). All models except for CUnet are supported.Highlight features:1. Unlimited number of imported images, GIFs and videos.2. Supports both SRCNN and CUnet models from the original waifu2x project.3. Supports Real-ESRGAN models for both illustrations and photos.4. Supports Real-CUGAN models for anime illustrations. Also supports customizable intensity.5. Supports Anime4K models for anime videos.6. Supports custom Core ML models. Import any model to process images for your specific needs.7. Custom scale modes. You have options to scale images up to 128x, 1.5x, fixed size and more.8. Supports multiple ways of importing images and videos: the album, files, folders, drag and drop, other apps, Shortcuts.9. Supports images with alpha channel.10. Multiple output formats: PNG, JPEG, HEIF, WebP, MP4, MOV, GIF, APNG, AWebP.11. Multiple processing backends. You can choose between highest quality or highest speed.12. Write output images and videos directly to an external path (including network drives like SMB).13. End-to-end support for 16-bit color and color spaces. Color accuracy will not be compromised after processing.14. Highly optimized RAM usage. You can easily produce images that don't even fit inside your device RAM.15. Supports deleting or replacing original images and videos if they come from the album.16. Supports downscaling images before processing, which is useful while processing some photos.SRCNN and CUnet models are converted from waifu2x-caffe.All the models are running on device, so it doesn't need to upload images or videos to any server.Source code of core function is available on GitHub:https://github.com/imxieyi/waifu2x-iosUsage of images in screenshots is granted by the original author Kurumi:https://twitter.com/0115_kurumiThe primary app icon is illustrated by Kapuru:https://twitter.com/KaPuRu_0410


