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
A long long time ago, I was fed up that PyTorch didn't provide an solution for testing two tensors for approximate equality. To overcome this I started pytorch_testing_utils, which is still used in our test suite:
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
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.
A long long time ago, I was fed up that PyTorch didn't provide an solution for testing two tensors for approximate equality. To overcome this I started
pytorch_testing_utils
, which is still used in our test suite:https://github.com/pystiche/pystiche/blob/74d7bc51b73e33c98135ee8bd721a34bc8c6137f/tox.ini#L19-L20
Since
torch==1.9.0
we have