David Bau davidbau

## index.js
// require() some stuff from npm (like you were using browserify)
// and then hit Run Code to run it on the right
var seedrandom = require('seedrandom');
var rng = seedrandom.xor4096('hello.');
console.log(rng());

## index.js
// require() some stuff from npm (like you were using browserify)
// and then hit Run Code to run it on the right
var $ = require('jquery');
var seedrandom = require('seedrandom');
var rng = seedrandom.xor4096('hello.');
for (var j = 0; j < 20; ++j) {
	$('body').append('<p>' + rng() + '</p>');
}

## index.js
var Parser = require('parse5').Parser;

//Instantiate parser
var parser = new Parser(null, {locationInfo: true});

//Then feed it with an HTML document
var d = parser.parseFragment('<p>hello<p>hello')

var info = ['<pre>', 'fragment has ' + d.childNodes.length + ' top-level nodes'];
for (var j = 0; j < d.childNodes.length; ++j) {

## .block
license: mit

## download_mp.py
#!/usr/bin/env python2.7

# Script to create simple flat pytorch ImageFolder folder hierarchy
# of training and validation images for miniplaces.  Each category
# name is just a folder name (numbered in alphabetical order as in
# the original miniplaces), and both train and val images are places
# directly inside a single level of folders with the flat cateogry names.

import shutil, os, tarfile

## autoimport.py
 from collections import defaultdict
 from importlib import import_module

 def autoimport_eval(term):
    '''
    Used to eval any expression containing fully-qualified names, such as
    'torchvision.models.alexnet(pretrained=True)' with automatic import of
    global module names.
    '''

## featurefolder.py
import os
import torch.utils.data as data
from torchvision.datasets.folder import default_loader, is_image_file
from PIL import Image

def grayscale_loader(path):
    with open(path, 'rb') as f:
        return Image.open(f).convert('L')

class FeatureFolder(data.Dataset):

## fooling.html
<!DOCTYPE html>
<html>
<!-- an example vue HTML file that displays images and metadata -->
<head>
<script src="https://cdn.jsdelivr.net/npm/vue@2.5.16/dist/vue.js"
  integrity="sha256-CMMTrj5gGwOAXBeFi7kNokqowkzbeL8ydAJy39ewjkQ="
  crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/npm/lodash@4.17.10/lodash.js"
  integrity="sha256-qwbDmNVLiCqkqRBpF46q5bjYH11j5cd+K+Y6D3/ja28="
  crossorigin="anonymous"></script>

## explorefeaturebyclick.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                davidbau
                / explorefeaturebyclick.ipynb
            
            
              Created
              October 20, 2019 22:14
            
              
                ExploreFeatureByClick.ipynb
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## nethook.py
"""
Utilities for instrumenting a torch model. (David Bau)

Trace will hook one layer at a time.
TraceDict will hook multiple layers at once.
subsequence slices intervals from Sequential modules.
get_module, replace_module, get_parameter resolve dotted names.
set_requires_grad recursively sets requires_grad in module parameters.
"""
	// require() some stuff from npm (like you were using browserify)
	// and then hit Run Code to run it on the right
	var seedrandom = require('seedrandom');
	var rng = seedrandom.xor4096('hello.');
	console.log(rng());
	// require() some stuff from npm (like you were using browserify)
	// and then hit Run Code to run it on the right
	var $ = require('jquery');
	var seedrandom = require('seedrandom');
	var rng = seedrandom.xor4096('hello.');
	for (var j = 0; j < 20; ++j) {
	$('body').append('<p>' + rng() + '</p>');
	}
	var Parser = require('parse5').Parser;

	//Instantiate parser
	var parser = new Parser(null, {locationInfo: true});

	//Then feed it with an HTML document
	var d = parser.parseFragment('<p>hello<p>hello')

	var info = ['<pre>', 'fragment has ' + d.childNodes.length + ' top-level nodes'];
	for (var j = 0; j < d.childNodes.length; ++j) {
	#!/usr/bin/env python2.7

	# Script to create simple flat pytorch ImageFolder folder hierarchy
	# of training and validation images for miniplaces. Each category
	# name is just a folder name (numbered in alphabetical order as in
	# the original miniplaces), and both train and val images are places
	# directly inside a single level of folders with the flat cateogry names.

	import shutil, os, tarfile
	from collections import defaultdict
	from importlib import import_module

	def autoimport_eval(term):
	'''
	Used to eval any expression containing fully-qualified names, such as
	'torchvision.models.alexnet(pretrained=True)' with automatic import of
	global module names.
	'''
	import os
	import torch.utils.data as data
	from torchvision.datasets.folder import default_loader, is_image_file
	from PIL import Image

	def grayscale_loader(path):
	with open(path, 'rb') as f:
	return Image.open(f).convert('L')

	class FeatureFolder(data.Dataset):
	<!DOCTYPE html>
	<html>
	<!-- an example vue HTML file that displays images and metadata -->
	<head>
	<script src="https://cdn.jsdelivr.net/npm/vue@2.5.16/dist/vue.js"
	integrity="sha256-CMMTrj5gGwOAXBeFi7kNokqowkzbeL8ydAJy39ewjkQ="
	crossorigin="anonymous"></script>
	<script src="https://cdn.jsdelivr.net/npm/lodash@4.17.10/lodash.js"
	integrity="sha256-qwbDmNVLiCqkqRBpF46q5bjYH11j5cd+K+Y6D3/ja28="
	crossorigin="anonymous"></script>
	"""
	Utilities for instrumenting a torch model. (David Bau)

	Trace will hook one layer at a time.
	TraceDict will hook multiple layers at once.
	subsequence slices intervals from Sequential modules.
	get_module, replace_module, get_parameter resolve dotted names.
	set_requires_grad recursively sets requires_grad in module parameters.
	"""