这次的作业是把logistics regression改成一个简单的神经网络
激活函数是一个ReLU函数,实现非线性化,之后输出的值传递给普通的logistics regression的输入即可
batch_size = 128
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)
# Variables.
weights1 = tf.Variable(
tf.truncated_normal([image_size * image_size, 1024]))
biases1 = tf.Variable(tf.zeros([1024]))
weights2 = tf.Variable(
tf.truncated_normal([1024, num_labels]))
biases2 = tf.Variable(tf.zeros([num_labels]))
# Training computation.
#input to hidden layer
z1 = tf.matmul(tf_train_dataset, weights1) + biases1
h1 = tf.nn.relu(z1)
#hidden layer to output
logits = tf.matmul(h1, weights2) + biases2
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits))
# Optimizer.
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(logits)
valid_z1 = tf.matmul(tf_valid_dataset, weights1) + biases1
valid_h1 = tf.nn.relu(valid_z1)
#hidden layer to output
valid_logits = tf.matmul(valid_h1, weights2) + biases2
valid_prediction = tf.nn.softmax(valid_logits)
test_z1 = tf.matmul(tf_test_dataset, weights1) + biases1
test_h1 = tf.nn.relu(test_z1)
#hidden layer to output
test_logits = tf.matmul(test_h1, weights2) + biases2
test_prediction = tf.nn.softmax(test_logits)
训练
num_steps = 3001
with tf.Session(graph=graph) as session:
tf.global_variables_initializer().run()
print("Initialized")
for step in range(num_steps):
# Pick an offset within the training data, which has been randomized.
# Note: we could use better randomization across epochs.
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
# Generate a minibatch.
batch_data = train_dataset[offset:(offset + batch_size), :]
batch_labels = train_labels[offset:(offset + batch_size), :]
# Prepare a dictionary telling the session where to feed the minibatch.
# The key of the dictionary is the placeholder node of the graph to be fed,
# and the value is the numpy array to feed to it.
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run(
[optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 500 == 0):
print("Minibatch loss at step %d: %f" % (step, l))
print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
print("Validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))
结果