Gating is ??? a discrete, sparse choice of ... Limiting of information flow!? Why is it important? It can provide differentiable sparsity? Sparsity is the real goal?
Gating allows us to choose (at run time) which computations to apply. This means we can save ... (somewhat like attention).
Specifically I am interested in applying this to gating/heirarchical/... for image processing.
| import tensorflow as tf | |
| from tensorflow.contrib.tensorboard.plugins import projector | |
| from tensorflow.examples.tutorials.mnist import input_data | |
| from sklearn.utils import shuffle | |
| import numpy as np | |
| import os | |
| tf.app.flags.DEFINE_string('logdir', '/tmp/test', 'location for saved embeedings') | |
| tf.app.flags.DEFINE_string('datadir', '/tmp/mnist', 'location for data') | |
| tf.app.flags.DEFINE_integer('batchsize', 500, 'batch size.') |
| #!/bin/bash | |
| DATE=$(date +"%Y%m%d%H%M") | |
| gnome-screenshot -f "/home/act65/repos/capture/images/$DATE.jpg" | |
| # then add */2 * * * * /{path_to_this_file} to crontab using crontab -e |
| import os | |
| import json | |
| import requests | |
| import argparse | |
| from bs4 import BeautifulSoup as bs | |
| def fetch(url): | |
| page = requests.get(url) | |
| return bs(page.content, "html.parser") |
| import os | |
| import csv | |
| import time | |
| import argparse | |
| import subprocess | |
| def parse_args(): | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("--search_terms", type=str) | |
| return parser.parse_args() |
