用Lasagne來實現MLP，測試mnist

雖然Lasagne自帶的examples中帶有MNIST的例子，但是這個例子的風格更接近用Theano來寫。使用nolearn.lasagne中的NeuralNet類來寫MLP似乎更符合Lasagne的設計初衷，也更像Caffe的風格。

code

沒有比代碼更清楚地了：

# Using lasagne to fit mnist.
# show how to use NeuralNet
# Tarrega, 150611.

import lasagne
from lasagne import layers
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet
import os
from urllib import urlretrieve
import gzip
import pickle
import numpy

DATA_URL = 'http://deeplearning.net/data/mnist/mnist.pkl.gz'
DATA_FILENAME = 'mnist.pkl.gz'

def pickle_load(f, encoding):
    return pickle.load(f)

def _load_data(url=DATA_URL, filename=DATA_FILENAME):
    """Load data from `url` and store the result in `filename`."""
    print 'filename for the minist datatset:',filename
    if not os.path.exists(filename):
        print("Downloading MNIST dataset")
        urlretrieve(url, filename)

    with gzip.open(filename, 'rb') as f:
        return pickle_load(f, encoding='latin-1')


def load():
    """Get data with labels, split into training, validation and test set."""
    data = _load_data()
    X_train, y_train = data[0]
    y_train = numpy.asarray(y_train,dtype='int32')
    #X_valid, y_valid = data[1]
    #X_test, y_test = data[2]
    print 'size:',X_train.shape, y_train.shape, X_train.dtype, y_train.dtype
    return X_train,y_train


net1 = NeuralNet(
    layers=[  # three layers: one hidden layer
        ('input', layers.InputLayer),
        ('hidden', layers.DenseLayer),
        ('output', layers.DenseLayer),
        ],
    # layer parameters:
    input_shape=(None, 28*28),  # 28x28 input pixels per batch
    hidden_num_units=200,  # number of units in hidden layer
    output_nonlinearity=lasagne.nonlinearities.softmax,  # output layer
    output_num_units=10,  # 10 target values

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

    regression=False,  # 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)

output

運行結果：

  epoch    train loss    valid loss    train/val    valid acc  dur
-------  ------------  ------------  -----------  -----------  -----
      1       0.57989       0.32038      1.80998      0.91009  2.60s
      2       0.30194       0.26267      1.14949      0.92692  2.64s
      3       0.25044       0.22917      1.09281      0.93482  2.63s
      4       0.21578       0.20542      1.05046      0.94105  2.83s
      5       0.18969       0.18748      1.01177      0.94560  2.73s
      6       0.16917       0.17336      0.97585      0.94876  2.73s
      7       0.15259       0.16223      0.94059      0.95232  2.80s
      8       0.13882       0.15313      0.90655      0.95509  2.79s
      9       0.12723       0.14541      0.87498      0.95776  2.71s
     10       0.11725       0.13897      0.84373      0.96043  2.65s
     11       0.10859       0.13341      0.81392      0.96152  2.74s
     12       0.10100       0.12864      0.78511      0.96271  2.65s
     13       0.09424       0.12444      0.75735      0.96389  2.65s
     14       0.08822       0.12075      0.73056      0.96508  2.75s
     15       0.08280       0.11754      0.70446      0.96567  2.66s
     16       0.07790       0.11458      0.67988      0.96647  2.55s
     17       0.07343       0.11192      0.65606      0.96676  2.68s
     18       0.06936       0.10953      0.63324      0.96785  2.69s
     19       0.06561       0.10741      0.61082      0.96874  2.61s
     20       0.06218       0.10538      0.59000      0.96914  2.60s
     21       0.05899       0.10357      0.56959      0.96943  2.64s
     22       0.05604       0.10197      0.54953      0.96973  2.59s
     23       0.05329       0.10048      0.53033      0.97022  2.61s
     24       0.05070       0.09921      0.51105      0.97052  2.71s
     25       0.04829       0.09795      0.49296      0.97072  2.68s

Questions:

1. 爲什麼運行速度比Lasagne自帶的Example快這麼多？NeuralNet類自動把Training分爲80%Train，20%Test，可能計算量小了。