| # required: ffmpeg (e.g. from homebrew), terminal-notifier from https://github.com/alloy/terminal-notifier | |
| # you can schedule this with launchd to run e.g. weekly | |
| # Specify in seconds how long the script should record (default here is 1 hour). | |
| seconds=3600 | |
| # Date format for the recording file name | |
| DATE=`date "+%d-%m-%y_%H-%M"` | |
| # start ffmpeg recording |
##VGG19 model for Keras
This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
| # The following must be executed in a jupyter notebook rather than a shell environment. | |
| # Use numpy to work with arrays | |
| import numpy as np | |
| # Use scipy.stats to do plot some statistical data | |
| import scipy.stats as stats | |
| import holoviews as hv | |
| # Holoviews builds on top of either the Matplotlib or Bokeh plotting library. Choose to use Bokeh | |
| # in these plots as interactive plots work very well with Bokeh | |
| hv.notebook_extension('bokeh') |
| # Combine multiple images into one. | |
| # | |
| # To install the Pillow module on Mac OS X: | |
| # | |
| # $ xcode-select --install | |
| # $ brew install libtiff libjpeg webp little-cms2 | |
| # $ pip install Pillow | |
| # | |
| from __future__ import print_function |