karpathy

""" 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

bayesian_neural_network.ipynb

dennybritz

# Install build tools
sudo apt-get update
sudo apt-get install -y build-essential git python-pip libfreetype6-dev libxft-dev libncurses-dev libopenblas-dev  gfortran python3-matplotlib libblas-dev liblapack-dev libatlas-base-dev python3-dev python3-pydot linux-headers-generic linux-image-extra-virtual unzip python3-numpy swig python3-pandas python-sklearn unzip python3-pip python3-venv

# Install CUDA 7
# wget http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1410/x86_64/cuda-repo-ubuntu1410_7.0-28_amd64.deb
wget http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1504/x86_64/cuda-repo-ubuntu1504_7.5-18_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1504_7.5-18_amd64.deb && rm cuda-repo-ubuntu1504_7.5-18_amd64.deb
sudo apt-get update
sudo apt-get install -y cuda

EderSantana

Code for Keras plays catch blog post

Train

python qlearn.py

Test

1. Generate figures

DSA101

# Time series forecasting based on multiple time series, including the original one
# This script is based on the following examples and discussions:
# https://gist.github.com/lukovkin/1aefa4509e066690b892
# https://groups.google.com/forum/#!topic/keras-users/9GsDwkSdqBg

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import random
import theano

valiant-falstaff

from ib.opt import Connection, message
from ib.ext.Contract import Contract
from ib.ext.Order import Order

from random import randint
import time

def error_handler(msg):
    print ("Server Error: %s" % msg)

hnykda

import pandas as pd  
from random import random

flow = (list(range(1,10,1)) + list(range(10,1,-1)))*100
pdata = pd.DataFrame({"a":flow, "b":flow})  
pdata.b = pdata.b.shift(9)  
data = pdata.iloc[10:] * random()  # some noise  

import numpy as np

hnykda

""" From:  http://danielhnyk.cz/predicting-sequences-vectors-keras-using-rnn-lstm/ """
from keras.models import Sequential  
from keras.layers.core import TimeDistributedDense, Activation, Dropout  
from keras.layers.recurrent import GRU
import numpy as np

def _load_data(data, steps = 40):  
    docX, docY = [], []
    for i in range(0, data.shape[0]/steps-1):
        docX.append(data[i*steps:(i+1)*steps,:])

baraldilorenzo

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

ebressert

import seaborn as sns
from scipy.optimize import curve_fit

# Function for linear fit
def func(x, a, b):
    return a + b * x

# Seaborn conveniently provides the data for
# Anscombe's quartet.
df = sns.load_dataset("anscombe")