manu3193

--------- beginning of main
12-05 22:31:52.891  1206  1826 D libsensor-B2SNotifier: Backlight2SlpiNotifier brightness = 198
12-05 22:31:52.891   819  3314 D FOD     : updateHBMOverlayTarget brightness=198, mSupportMulExpo=0
12-05 22:31:52.891   819  3314 D FOD     : getHBMOverlayAlpha=0.703112 mBrightnessBackup=198, mTargetBrightness=1 mode = 2
12-05 22:31:52.891   819  3314 D SurfaceFlinger: enter
12-05 22:31:52.891   819  3314 D SurfaceFlinger: successfully write 179 into /sys/class/drm/card0-DSI-1/dim_alpha
12-05 22:31:52.891   819  3314 D FOD     : brightness=198; alpha=0.000000; mSupportMulExpo=0
12-05 22:31:53.017  1206  1826 D libsensor-B2SNotifier: Backlight2SlpiNotifier brightness = 197
12-05 22:31:53.017   819  3314 D FOD     : updateHBMOverlayTarget brightness=197, mSupportMulExpo=0
12-05 22:31:53.017   819  3314 D FOD     : getHBMOverlayAlpha=0.703795 mBrightnessBackup=197, mTargetBrightness=1 mode = 2

manu3193

'''
Using Bottleneck Features for Multi-Class Classification in Keras

We use this technique to build powerful (high accuracy without overfitting) Image Classification systems with small
amount of training data.

The full tutorial to get this code working can be found at the "Codes of Interest" Blog at the following link,
http://www.codesofinterest.com/2017/08/bottleneck-features-multi-class-classification-keras.html

Please go through the tutorial before attempting to run this code, as it explains how to setup your training data.