Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models
#462 corrected the label of the "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" from JAFF2016 to JAL2016, but failed to apply this change to all other places in the library. This is at least true for
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the image - for better understanding of how NST works.
Reconstruction of the fast neural style transfer (Johnson et al.). Some portions of the paper have been improved by the follow-up work like the instance normalization, etc. Checkout transformer_net.py's header for details.
Code for "Jhamtani H.*, Gangal V.*, Hovy E. and Nyberg E. Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models" Workshop on Stylistic Variation, EMNLP 2017
ncnnRay++ is a CMake based integration of raylib and the very popular Tencent ncnn Deep Learning library. ncnn is written in C++ and designed (but not only) for edge computing devices. The project depends on the Vulkan SDK (Vulakn is Khronos' API for Graphics and Compute on GPUs).
Create naive (no temporal loss) NST for videos with person segmentation. Just place your videos in data/, run and you get your stylized and segmented videos.
#462 corrected the label of the "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" from
JAFF2016toJAL2016, but failed to apply this change to all other places in the library. This is at least true forhttps://github.com/pystiche/pystiche/blob/5c38c6805aec72d57f831ef3e529fde772eafc07/pystiche/loss/_comparison.py#L55-L59
but might also be the case in other parts.