domluna

# User configuration
export PATH="$HOME/.linuxbrew/bin:$PATH"
export MANPATH="$HOME/.linuxbrew/share/man:$MANPATH"
export INFOPATH="$HOME/.linuxbrew/share/info:$INFOPATH"

# add cuda tools to command path
export PATH=/usr/local/cuda/bin:${PATH}
export MANPATH=/usr/local/cuda/man:${MANPATH}

# add cuda libraries to library path

domluna

struct CPolygon
    vertexlist::Ptr{Cint}
    numberofvertices::Cint
end

struct CFacet{T}
    polygonlist::Ptr{CPolygon}
    numberofpolygons::Cint

domluna

export @esc, isexpr, isline, rmlines, unblock, block, inexpr, namify, isdef,
  longdef, shortdef, @expand, makeif, prettify, splitdef, splitarg

"""
    assoc!(d, k, v)

is the same as `d[k] = v` but returns `d` rather than `v`.
"""
assoc!(d, k, v) = (d[k] = v; d)

domluna

Transformer notes

• current models have trouble learning dependencies over distance (i.e. between characters/words), # ops scale O(n) or O(log n).

• transformer is O(1) in number of ops

• encoder-decoder with residual conns. Encoder/decodes feed into themselves N times.

• We also modify the self-attention sub-layer in the decoder stack to prevent positions from attending to subsequent positions. This masking, combined with fact that the output embeddings are offset by one position, **ensures that the predictions for position i can depend only on the known outputs at positions less than i **.

def subsequent_mask(size):

domluna

import tensorflow as tf

def main():
    files = ['model-' + str(x) for x in range(20000, 70000, 10000)]
    for f in files:
        with tf.Graph().as_default():
            sess = tf.Session()
            saver = tf.train.import_meta_graph('./test_graph_size/' + f + '.meta')
            saver.restore(sess, './test_graph_size/' + f)
            print(sess.graph_def.ByteSize())

domluna

Run with defaults

python vpg.py

domluna

To replicate run

python cem.py --algorithm pcem --outdir CartPole-v0-pcem

The --outdir argument is optional. If left as is results will be written to /tmp/CartPole-v0-pcem.

domluna

import tensorflow as tf
import numpy as np


x = tf.constant(np.random.randn(1, 4, 4, 2), dtype=tf.float32)
# TODO: Use `tf.layers.conv2d_transpose` to return a tensor
# with the shape (1, 8, 8, 5)
conv = 0

with tf.Session() as sess:

domluna

 
def iou(img, y, c):
    intersection = 0.
    union = 0.
    img = img.reshape(-1)
    y = y.reshape(-1)
    for i in range(len(img)):
         intersection += img[i] == c and y[i] == c
         union += img[i] == c or y[i] == c
    return intersection / union

domluna

"""
Load SavedModel

Output graphdef and checkpoint files
"""

import tensorflow as tf
import argparse
import sys