Gene Kogan

i got this error as well and was able to fix it by renaming the tensor names using the code found here: https://github.com/tensorflow/models/issues/466#issuecomment-391240675

thanks for the tips! relatedly -- is my intuition about using larger inputs incorrect? i.e. in the image examples, each element is an 8-bit int (0-255). if i use binary...

hey @kocica @schwittlick. we've had trouble maintaining ofxDarknet because of the complex dependencies and need to extern darknet's C code into openframeworks C++. in general it's a pain to maintain...

@johanjohan no you do not need the beta -- this is using the backend models only. essentially, ofxRunway is an openframeworks replacement for the runway client application (which is what...

yes, sorry, i have the same problems on my side as well. have to rebuild darknet for linux, the library we have now is giving these linker errors. if you...

i'd be interested also in participating in this. ofxLearn is wrapping dlib but it's an old version, and by now it makes sense to have all dlib stuff in one...

this sounds like a good strategy to me. i'm curious how the [video tracking](http://dlib.net/video_tracking_ex.cpp.html) would compare to the ContourTracker in openCV. right now with the deep learning examples, i don't...

@bakercp yeah darknet sometimes does not adapt well to a laptop, at least not with the big models. Lowering the batch size and subdivisions (sometimes to just 1) in the...

yep this is roughly what i was getting. it should be expected that the quality is much less than the original style transfer unfortunately because it uses a fast method...

interesting, give it a shot. here's the original:  yes, definitely models would be great. we can host them somewhere and i'd link to it from the repo, or you...