gordicaleksa/pytorch-neural-style-transfer-johnson
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.
PythonMIT
Issues
- 0
Training with custom training data?
#7 opened by dflateau - 0
Is it possible to also load from the last saved checkpoint in case the training failed at some point?
#6 opened by tdbe - 1
High resolution
#5 opened by robertgoacher - 3
- 0
Resolution Question
#3 opened by DeepThread - 2
- 1
Add Dockerfile to speedup setup.
#1 opened by DavidWiesner