Kyle McDonald

i also got `TypeError: a bytes-like object is required, not 'str'` but i think it's because i was testing with python 3.6 and not python 2.7.

Those are the labels of the input image. In this case, I'm predicted 73 attributes from the LFWA+ dataset. "True" means "smiling" and "False" means "not smiling". I provided example...

Here is an h5 file and the notebook I used for training, and export. Sorry it's so messy! https://www.dropbox.com/s/tdv8jgor4gl9jnm/checkpoint-2.42-04.h5?dl=0 https://www.dropbox.com/s/ggt68cod8qzu1pp/SEResNet-train%2Bexport.zip?dl=0

Sorry, it's my fault! Here is the correct .h5 file: https://www.dropbox.com/s/lm7k336mt6vqfhz/checkpoint-0.29-04.h5?dl=0 The other one uses the same input data, but has a softmax output across a different distribution.

I’m still trying to get this to work, but I feel like I must have made some simple mistake... :(

@jvcleave thanks for the suggestion. unfortunately, commenting that out doesn't seem to change the behavior for the better for me.. the orientation still changes when i rotate the iPad. edit:...

@arturoc yes the image is being drawn at its original size with `img.draw(0,0);` by disabling antialiasing I mean `ofxiOSWindowSettings::enableAntiAliasing` and `ofxiOSWindowSettings::numOfAntiAliasingSamples` which I think controls how everything is drawn, not...

i made this and some other changes to get the generation example looking more like the char-rnn architecture https://gist.github.com/kylemcdonald/2d06dc736789f0b329e11d504e8dee9f some of this is specific to the direction i'm going, but...

thank you. i tried to get pattern running on mac with this: ``` brew install mysql-client pip3 install pattern ``` But I couldn't get it to work. This works though:...

The model link now points to a 404 page.