btbujiangjun’s gists

btbujiangjun / nes.py

Created July 6, 2019 13:36 — forked from karpathy/nes.py

Natural Evolution Strategies (NES) toy example that optimizes a quadratic function

	"""
	A bare bones examples of optimizing a black-box function (f) using
	Natural Evolution Strategies (NES), where the parameter distribution is a
	gaussian of fixed standard deviation.
	"""

	import numpy as np
	np.random.seed(0)

	# the function we want to optimize

btbujiangjun / pg-pong.py

Created July 6, 2019 13:35 — forked from karpathy/pg-pong.py

Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels

	""" 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

btbujiangjun / min-char-rnn.py

Created July 6, 2019 13:35 — forked from karpathy/min-char-rnn.py

Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy

	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)

btbujiangjun / gist:fdc9aea62b19cfa24f966ea99f18021b

Created July 6, 2019 13:34 — forked from karpathy/gist:f3ee599538ff78e1bbe9

Batched L2 Normalization Layer for Torch nn package


	--[[
	This layer expects an [n x d] Tensor and normalizes each
	row to have unit L2 norm.
	]]--
	local L2Normalize, parent = torch.class('nn.L2Normalize', 'nn.Module')
	function L2Normalize:__init()
	parent.__init(self)
	end
	function L2Normalize:updateOutput(input)

btbujiangjun / gist:740e845dd8addd1d443b754343f41f58

Created July 6, 2019 13:34 — forked from karpathy/gist:7bae8033dcf5ca2630ba

Efficient LSTM cell in Torch

	--[[
	Efficient LSTM in Torch using nngraph library. This code was optimized
	by Justin Johnson (@jcjohnson) based on the trick of batching up the
	LSTM GEMMs, as also seen in my efficient Python LSTM gist.
	--]]

	function LSTM.fast_lstm(input_size, rnn_size)
	local x = nn.Identity()()
	local prev_c = nn.Identity()()
	local prev_h = nn.Identity()()

btbujiangjun / gist:497ea04cb422aaef4b2f8d4dda20873e

Created July 6, 2019 13:33 — forked from karpathy/gist:587454dc0146a6ae21fc

An efficient, batched LSTM.

	"""
	This is a batched LSTM forward and backward pass
	"""
	import numpy as np
	import code

	class LSTM:

	@staticmethod
	def init(input_size, hidden_size, fancy_forget_bias_init = 3):