| import numpy as np | |
| import gym | |
| import tensorflow as tf | |
| import matplotlib.pyplot as plt | |
| def weight_variable(shape): | |
| initial = tf.truncated_normal(shape, stddev=0.1) | |
| return tf.Variable(initial) | |
| def bias_variable(shape): |
| """ | |
| Easy-to-understand implementation of Beam Search algorithm used in decoder of | |
| seq2seq models (e.g. NMT). Results compared with tensorflow implementation | |
| (1.5.0) (`tf.contrib.seq2seq.BeamSearchDecoder`) | |
| """ | |
| import tensorflow as tf | |
| import numpy as np | |
| import heapq | |
| import collections |
| brew install autoconf automake libtool protobuf | |
| git clone --depth=1 https://github.com/google/sentencepiece.git /tmp/sentencepiece | |
| cd /tmp/sentencepiece | |
| ./autogen.sh | |
| ./configure | |
| make | |
| make check | |
| sudo make install |
| import math | |
| import numpy as np | |
| def f(x): | |
| return ( | |
| float(3*x*x*x-x*x+2*x-4)/ | |
| float(math.sqrt(x*x-3*x+2))) | |
| def montecarlo_integration( | |
| floor_value, |
This is a short post that explains how to write a high-performance matrix multiplication program on modern processors. In this tutorial I will use a single core of the Skylake-client CPU with AVX2, but the principles in this post also apply to other processors with different instruction sets (such as AVX512).
Matrix multiplication is a mathematical operation that defines the product of
| # source : https://www.electricmonk.nl/log/2011/09/28/evolutionary-algorithm-evolving-hello-world/ | |
| import random | |
| import string | |
| source = "jijvdvnmertnj" | |
| target = "Hello, World!" | |
| def calc_fitness(source, target): | |
| fitval = 0 | |
| for i in range(0, len(source)): |
| # REINFORCE: Monte Carlo Policy Gradient Implementation | |
| # Learn more from Reinforcement Learning: An Introduction (p271) | |
| # by Sutton & Barto | |
| import tensorflow as tf | |
| import gym | |
| import numpy as np | |
| from gym import wrappers | |
| # coding: utf-8 | |
| """ | |
| シンプルなパストレーサー | |
| cf. http://www.kevinbeason.com/smallpt/ | |
| """ | |
| import shutil | |
| import numpy as np | |
| import tensorflow as tf | |
| import gym | |
| import numpy as np | |
| from keras.models import Model | |
| from keras.layers import * | |
| from keras import backend as K | |
| from collections import deque | |
| def one_hot(index, categories): |
| '''Solves Pong with Policy Gradients in Tensorflow.''' | |
| # written October 2016 by Sam Greydanus | |
| # inspired by karpathy's gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5 | |
| import numpy as np | |
| import gym | |
| import tensorflow as tf | |
| # hyperparameters | |
| n_obs = 80 * 80 # dimensionality of observations | |
| h = 200 # number of hidden layer neurons |