Je suis à jouer avec une ANN qui est une partie de Udacity DeepLearning cours.
J'ai une mission qui consiste à introduire la généralisation du réseau avec un caché ReLU calque à l'aide de L2 perte. Je me demande comment l'introduire, de sorte que TOUS les poids sont pénalisés, non seulement le poids de la couche de sortie.
Code pour réseau sans généralisation est au bas de la poste (code pour exécuter la formation est hors de la portée de la question).
De manière évidente de l'introduction de la L2 est de remplacer le calcul de la perte de quelque chose comme ceci (si le bêta est de 0,01):
loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(out_layer, tf_train_labels) + 0.01*tf.nn.l2_loss(out_weights))
Mais, dans ce cas, il prendra en compte les valeurs de la couche de sortie du poids. Je ne suis pas sûr, comment pouvons-nous correctement pénaliser le poids qui entrent DANS le caché ReLU couche. Est-il nécessaire ou de l'introduction de la pénalisation de la couche de sortie, sera en quelque sorte de garder cachés poids à vérifier aussi?
#some importing
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
#loading data
pickle_file = '/home/maxkhk/Documents/Udacity/DeepLearningCourse/SourceCode/tensorflow/examples/udacity/notMNIST.pickle'
with open(pickle_file, 'rb') as f:
save = pickle.load(f)
train_dataset = save['train_dataset']
train_labels = save['train_labels']
valid_dataset = save['valid_dataset']
valid_labels = save['valid_labels']
test_dataset = save['test_dataset']
test_labels = save['test_labels']
del save # hint to help gc free up memory
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
#prepare data to have right format for tensorflow
#i.e. data is flat matrix, labels are onehot
image_size = 28
num_labels = 10
def reformat(dataset, labels):
dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)
# Map 0 to [1.0, 0.0, 0.0 ...], 1 to [0.0, 1.0, 0.0 ...]
labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
#now is the interesting part - we are building a network with
#one hidden ReLU layer and out usual output linear layer
#we are going to use SGD so here is our size of batch
batch_size = 128
#building tensorflow graph
graph = tf.Graph()
with graph.as_default():
# Input data. For the training data, we use a placeholder that will be fed
# at run time with a training minibatch.
tf_train_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size * image_size))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
#now let's build our new hidden layer
#that's how many hidden neurons we want
num_hidden_neurons = 1024
#its weights
hidden_weights = tf.Variable(
tf.truncated_normal([image_size * image_size, num_hidden_neurons]))
hidden_biases = tf.Variable(tf.zeros([num_hidden_neurons]))
#now the layer itself. It multiplies data by weights, adds biases
#and takes ReLU over result
hidden_layer = tf.nn.relu(tf.matmul(tf_train_dataset, hidden_weights) + hidden_biases)
#time to go for output linear layer
#out weights connect hidden neurons to output labels
#biases are added to output labels
out_weights = tf.Variable(
tf.truncated_normal([num_hidden_neurons, num_labels]))
out_biases = tf.Variable(tf.zeros([num_labels]))
#compute output
out_layer = tf.matmul(hidden_layer,out_weights) + out_biases
#our real output is a softmax of prior result
#and we also compute its cross-entropy to get our loss
loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(out_layer, tf_train_labels))
#now we just minimize this loss to actually train the network
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#nice, now let's calculate the predictions on each dataset for evaluating the
#performance so far
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(out_layer)
valid_relu = tf.nn.relu( tf.matmul(tf_valid_dataset, hidden_weights) + hidden_biases)
valid_prediction = tf.nn.softmax( tf.matmul(valid_relu, out_weights) + out_biases)
test_relu = tf.nn.relu( tf.matmul( tf_test_dataset, hidden_weights) + hidden_biases)
test_prediction = tf.nn.softmax(tf.matmul(test_relu, out_weights) + out_biases)