kfkd.py

# file kfkd.py
import os

import numpy as np
from pandas.io.parsers import read_csv
from sklearn.utils import shuffle

# Implicit import needed in newer theano versions
# https://groups.google.com/forum/#!msg/lasagne-users/gEtFrC8mkms/0oNCDbSKbTkJ
import lasagne.layers.cuda_convnet

FTRAIN = '~/data/training.csv'
FTEST = '~/data/test.csv'


def load(test=False, cols=None):
    """Loads data from FTEST if *test* is True, otherwise from FTRAIN.
    Pass a list of *cols* if you're only interested in a subset of the
    target columns.
    """
    fname = FTEST if test else FTRAIN
    df = read_csv(os.path.expanduser(fname))  # load pandas dataframe

    # The Image column has pixel values separated by space; convert
    # the values to numpy arrays:
    df['Image'] = df['Image'].apply(lambda im: np.fromstring(im, sep=' '))

    if cols:  # get a subset of columns
        df = df[list(cols) + ['Image']]

    print(df.count())  # prints the number of values for each column
    df = df.dropna()  # drop all rows that have missing values in them

    X = np.vstack(df['Image'].values) / 255.  # scale pixel values to [0, 1]
    X = X.astype(np.float32)

    if not test:  # only FTRAIN has any target columns
        y = df[df.columns[:-1]].values
        y = (y - 48) / 48  # scale target coordinates to [-1, 1]
        X, y = shuffle(X, y, random_state=42)  # shuffle train data
        y = y.astype(np.float32)
    else:
        y = None

    return X, y


from lasagne import layers
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet

net1 = NeuralNet(
    layers=[  # three layers: one hidden layer
        ('input', layers.InputLayer),
        ('hidden', layers.DenseLayer),
        ('output', layers.DenseLayer),
        ],
    # layer parameters:
    input_shape=(128, 9216),  # 128 images per batch times 96x96 input pixels
    hidden_num_units=100,  # number of units in hidden layer
    output_nonlinearity=None,  # output layer uses identity function
    output_num_units=30,  # 30 target values

    # optimization method:
    update=nesterov_momentum,
    update_learning_rate=0.01,
    update_momentum=0.9,

    regression=True,  # flag to indicate we're dealing with regression problem
    max_epochs=400,  # we want to train this many epochs
    verbose=1,
    )

#X, y = load()
#net1.fit(X, y)

def load2d(test=False, cols=None):
    X, y = load(test=test)
    X = X.reshape(-1, 1, 96, 96)
    return X, y


# use the cuda-convnet implementations of conv and max-pool layer
Conv2DLayer = layers.cuda_convnet.Conv2DCCLayer
MaxPool2DLayer = layers.cuda_convnet.MaxPool2DCCLayer

net2 = NeuralNet(
    layers=[
        ('input', layers.InputLayer),
        ('conv1', Conv2DLayer),
        ('pool1', MaxPool2DLayer),
        ('conv2', Conv2DLayer),
        ('pool2', MaxPool2DLayer),
        ('conv3', Conv2DLayer),
        ('pool3', MaxPool2DLayer),
        ('hidden4', layers.DenseLayer),
        ('hidden5', layers.DenseLayer),
        ('output', layers.DenseLayer),
        ],
    input_shape=(128, 1, 96, 96),
    conv1_num_filters=32, conv1_filter_size=(3, 3), pool1_ds=(2, 2),
    conv2_num_filters=64, conv2_filter_size=(2, 2), pool2_ds=(2, 2),
    conv3_num_filters=128, conv3_filter_size=(2, 2), pool3_ds=(2, 2),
    hidden4_num_units=500, hidden5_num_units=500,
    output_num_units=30, output_nonlinearity=None,

    update_learning_rate=0.01,
    update_momentum=0.9,

    regression=True,
    max_epochs=1000,
    verbose=1,
    )

X, y = load2d()  # load 2-d data
net2.fit(X, y)

# Training for 1000 epochs will take a while.  We'll pickle the
# trained model so that we can load it back later:
import cPickle as pickle
with open('net2.pickle', 'wb') as f:
    pickle.dump(net2, f, -1)