Jim Fleming jimfleming

What the BookCorpus?

So in the midst of all these Sesame Streets characters and robots transforming automobile era of "contextualize" language models, there is this "Toronto Book Corpus" that points to this kinda recently influential paper:

Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. "Aligning books and movies: Towards story-like visual explanations by watching movies and reading books." In Proceedings of the IEEE international conference on computer vision, pp. 19-27.

Why do I even care, there's no translations there?

Some might know my personal pet peeve on collecting translation datasets but this BookCorpus has no translations, so why do I even care about it?

How to setup a practically free CDN using Backblaze B2 and Cloudflare

⚠️ Note 2023-01-21
Some things have changed since I originally wrote this in 2016. I have updated a few minor details, and the advice is still broadly the same, but there are some new Cloudflare features you can (and should) take advantage of. In particular, pay attention to Trevor Stevens' comment here from 22 January 2022, and Matt Stenson's useful caching advice. In addition, Backblaze, with whom Cloudflare are a Bandwidth Alliance partner, have published their own guide detailing how to use Cloudflare's Web Workers to cache content from B2 private buckets. That is worth reading,

Fractional Max-Pooling (FMP)

Introduction

Link to Paper
Spatial pooling layers are building blocks for Convolutional Neural Networks (CNNs).
Input to pooling operation is a N_in x N_in matrix and output is a smaller matrix N_out x N_out.
Pooling operation divides N_in x N_in square into N²_out pooling regions P_{i, j}.
P_{i, j} ⊂ {1, 2, . . . , N_in} ∀ (i, j) ∈ {1, . . . , N_out}²

This gist has been superceded by Meta Graph functionality that has since been added to tensorflow core.

See: https://www.tensorflow.org/versions/master/api_docs/python/state_ops.html#exporting-and-importing-meta-graphs

The code remains posted for archival purposes only.

	import cdk = require('@aws-cdk/core');
	import greengrass = require('@aws-cdk/aws-greengrass');
	import lambda = require('@aws-cdk/aws-lambda');

	import { CfnCustomResource } from '@aws-cdk/aws-cloudformation';
	import { PolicyStatement, Role, ServicePrincipal, CompositePrincipal } from '@aws-cdk/aws-iam';

	import { group_deployment_reset_code } from '../lib/code/group_deployment_reset';
	import { thing_vendor_code } from '../lib/code/thing_vendor';

	import torch
	import torch.nn as nn
	import torch.nn.parallel

	class DCGAN_D(nn.Container):
	def __init__(self, isize, nz, nc, ndf, ngpu, n_extra_layers=0):
	super(DCGAN_D, self).__init__()
	self.ngpu = ngpu
	assert isize % 16 == 0, "isize has to be a multiple of 16"

	""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
	import numpy as np
	import cPickle as pickle
	import gym

	# hyperparameters
	H = 200 # number of hidden layer neurons
	batch_size = 10 # every how many episodes to do a param update?
	learning_rate = 1e-4
	gamma = 0.99 # discount factor for reward

	#!/usr/bin/env python2
	import os
	import gym
	import sys
	import random
	import itertools
	from time import time
	from copy import copy
	from math import sqrt, log

	# from https://cloud.google.com/solutions/machine-learning-with-financial-time-series-data
	def tf_confusion_metrics(model, actual_classes, session, feed_dict):
	predictions = tf.argmax(model, 1)
	actuals = tf.argmax(actual_classes, 1)

	ones_like_actuals = tf.ones_like(actuals)
	zeros_like_actuals = tf.zeros_like(actuals)
	ones_like_predictions = tf.ones_like(predictions)
	zeros_like_predictions = tf.zeros_like(predictions)