apaszke

PyTorch IR

This document presents the IR as of October 17th 2018. Future changes like mutability might render parts of this document outdated.

PyTorch uses an SSA-based IR, which is built of multiple entities:

• Graph is generally the outermost container for the program representation. At the moment all programs are mostly pure (modulo special operators like prim::Print or prim::PythonOp), but this will change in the future.
• Then, there are Blocks, which you can treat as functions. They have a list of inputs and outputs, and a (topologically ordered) list of Nodes. Every Graph has a top-level Block which is (using C lingo) like a main function.
• Nodes, in turn, represent calls to functions (with possibly multiple arguments and returns).
• Finally, every single intermediate value that appears in the program is represented using a Value - the root Blocks have a list of input values, and every Node takes them as inputs, and returns some more as outputs. Every Value has a Type a

cassiozen

Pixelbook Setup

Change your channel

Some of the features mentioned in this document only work on the beta or Dev channel. To change your channel:

1. chrome://help in a browser window
2. Click Detailed Build Information
3. Change Channel
4. Select Beta (Or Dev, if you're feeling adventurous)

daien

import numpy as np

def regular_multidim_digitize(data, n_bins=3, lbes=None, rbes=None):
    """ Build a regular grid and assigns each data point to a cell

    Parameters
    ----------
    data: (n_points, n_dims) array,
          the data that we which to digitize

tebeka

#!/usr/bin/env python

import sqlite3

def sumtuples(data, key_index):
    cur = sqlite3.connect(':memory:').cursor()
    cols = ['i{0}'.format(i) for i, _ in enumerate(data[0])]

    schema = 'CREATE TABLE items ({0})'.format(','.join(cols))
    cur.execute(schema)

evansd

# For more explanation and usage examples, see:
# http://www.drhevans.com/blog/posts/331-comparing-large-data-sets-in-python/

from itertools import imap, izip, count, repeat, tee
import heapq

def full_outer_join(*iterables, **kwargs):
    """
    Perform a full outer join on a sequence of sorted iterables, where the
    key function supplies the join condition.

CerebralMastication

## Joshua Ulrich's pivot function
## This code is alpha and is in development. 
## please test all results to ensure accuracy 

pivot <- function(x, rows, cols, FUN=NULL) {
   clean <- function(xx, dd) {
     cd <- merge(dd,xx,by=0,all=TRUE)
     rownames(cd) <- cd$Row.names
     cd$Row.names <- NULL
     return(cd)

huyng

### MATPLOTLIBRC FORMAT

# This is a sample matplotlib configuration file - you can find a copy
# of it on your system in
# site-packages/matplotlib/mpl-data/matplotlibrc.  If you edit it
# there, please note that it will be overridden in your next install.
# If you want to keep a permanent local copy that will not be
# over-written, place it in HOME/.matplotlib/matplotlibrc (unix/linux
# like systems) and C:\Documents and Settings\yourname\.matplotlib
# (win32 systems).