Skip to content

Instantly share code, notes, and snippets.

View brainstormot's full-sized avatar

Hyuck Kang brainstormot

View GitHub Profile
import os
import csv
searchKeywords = ["P2P","금융"]
def main():
for dirname, dirnames, filenames in os.walk('.'):
for subdirname in dirnames:
if subdirname == "news":
print("in " + os.path.join(dirname, subdirname))
brainstormot / solarized-dark.xcs
Created May 19, 2017 06:44 — forked from ichaos/solarized-dark.xcs
xshell solarized dark color theme
[Solarized Dark]
brainstormot /
Created February 14, 2017 11:25 — forked from gabrieleangeletti/
Restricted Boltzmann Machine implementation in TensorFlow, before and after code refactoring. Blog post:
import tensorflow as tf
import numpy as np
import os
import zconfig
import utils
class RBM(object):
brainstormot /
Created February 14, 2017 11:23 — forked from myme5261314/
RBM procedure using tensorflow
import tensorflow as tf
import numpy as np
import input_data
import Image
from util import tile_raster_images
def sample_prob(probs):
return tf.nn.relu(
brainstormot /
Created July 13, 2016 09:52 — forked from karpathy/
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