summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2016-10-25Crop images from display.cam
2016-10-25Merge branch 'master' of https://github.com/cysmith/neural-style-tfcam
2016-10-25Added original colors examplecam
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Update README.mdCameron
2016-10-25Merge branch 'master' of https://github.com/cysmith/neural-style-tfcam
2016-10-25Added initialization imagescam
2016-10-24Update README.mdCameron
2016-10-24Update README.mdCameron
2016-10-24Merge branch 'master' of https://github.com/cysmith/neural-style-tfcam
2016-10-24Added error checking for input images as per request.cam
2016-10-24Update README.mdCameron
2016-10-23Update README.mdCameron
2016-10-23Update README.mdCameron
2016-10-22Added LAB colorspacecam
2016-10-22Simplified color conversioncam
2016-10-22Added more colorspaces for color conversioncam
2016-10-20Changed default style weight to 1e4Cameron
2016-10-20Changed default style weight to 1e4Cameron
2016-10-20Update README.mdCameron
2016-10-19Update README.mdCameron
2016-10-18Update README.mdCameron
2016-10-17Added multiple content layerscam
2016-10-15Fixed bug between tensorflow builds 0.9, 0.10rc, 0.10cam
2016-10-15Fixed typoscam
2016-10-15Merge pull request #7 from kootenpv/patch-1Cameron
Update README.md
2016-10-15Update README.mdPascal van Kooten
2016-10-14Update README.mdCameron
2016-10-13Update README.mdCameron
2016-10-13Update README.mdCameron
2016-10-13Merge pull request #4 from deepxiangfa/masterCameron
Update neural_style.py
2016-10-13Update neural_style.pydeepxiangfa
fix the tv_loss bug
2016-10-12Delete consistencyChecker.cpp~Cameron
2016-10-12Merge pull request #3 from gtoderici/patch-2Cameron
Change interpolation method from bicubic to area.
2016-10-12Change interpolation method from bicubic to area.gtoderici
Change interpolation method from bicubic to area. This is necessary because when downsizing high resolution images, the bicubic algorithm generates high frequency noise (for example, try resizing an image containing gravel with bicubic vs. area). I guess ideally there should be a check to determine whether it's upsampling/downsampling and choose Lanczos for upsampling. However, given how slow this is... maybe we only need to worry about downsampling?
2016-10-11Added verbose to usage scriptCameron
2016-10-11Modified READMECameron
2016-10-11Modified READMECameron
2016-10-11Modified READMECameron
2016-10-11Modified READMECameron
2016-10-11Modified READMECameron
2016-10-11Update README.mdCameron