from tinyflow.datasets import get_mnist
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
y = tf.nn.softmax(tf.matmul(x, W))
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
learning_rate = 0.5
W_grad = tf.gradients(cross_entropy, [W])[0]
train_step = tf.assign(W, W - learning_rate * W_grad)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
# get the mnist dataset
mnist = get_mnist(flatten=True, onehot=True)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_:batch_ys})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(correct_prediction)
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
cross_entropy = tf.nn.mean_sparse_softmax_cross_entropy_with_logits(fc2, label)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session(device='gpu')
# Automatic variable shape inference API, infers the shape and initialize the weights.
known_shape = {x: [100, 28 * 28], label: [100]}
init_step = []
for v, name, shape in tf.infer_variable_shapes(
cross_entropy, feed_dict=known_shape):
init_step.append(tf.assign(v, tf.normal(shape)))
print("shape[%s]=%s" % (name, str(shape)))
sess.run(init_step)
# get the mnist dataset
mnist = get_mnist(flatten=True, onehot=False)
print_period = 1000
for epoch in range(10):
sum_loss = 0.0
num_batch = 600
for i in range(num_batch):
batch_xs, batch_ys = mnist.train.next_batch(100)
loss, _ = sess.run([cross_entropy, train_step], feed_dict={x: batch_xs, label:batch_ys})
sum_loss += loss
print("epoch[%d] cross_entropy=%g" % (epoch, sum_loss /num_batch))
correct_prediction = tf.equal(tf.argmax(fc2, 1), label)
accuracy = tf.reduce_mean(correct_prediction)
print(sess.run(accuracy, feed_dict={x: mnist.test.images, label: mnist.test.labels}))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session(device='gpu')
# Auromatic variable shape inference API, infers the shape and initialize the weights.
known_shape = {x: [100, 1, 28, 28], label: [100]}
stdev = 0.01
init_step = []
for v, name, shape in tf.infer_variable_shapes(cross_entropy,
feed_dict=known_shape):
init_step.append(tf.assign(v, tf.normal(shape, stdev)))
print("shape[%s]=%s" % (name, str(shape)))
sess.run(init_step)
# get the mnist dataset
mnist = get_mnist(flatten=False, onehot=False)
print_period = 1000
for epoch in range(10):
sum_loss = 0.0
num_batch = 600
for i in range(num_batch):
batch_xs, batch_ys = mnist.train.next_batch(100)
loss, _ = sess.run([cross_entropy, train_step],
feed_dict={
x: batch_xs,
label: batch_ys
})
sum_loss += loss
print("epoch[%d] cross_entropy=%g" % (epoch, sum_loss / num_batch))
def softmax(x):
x = x - np.max(x, axis=1, keepdims=True)
x = np.exp(x)
x = x / np.sum(x, axis=1, keepdims=True)
return x
def evaluate(x, y_, W):
y = softmax(np.dot(x, W))
return np.mean(np.argmax(y, 1) == np.argmax(y_, 1))
# get the mnist dataset
mnist = get_mnist(flatten=True, onehot=True)
learning_rate = 0.5 / 100
W = np.zeros((784, 10))
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
# forward
y = softmax(np.dot(batch_xs, W))
# backward
y_grad = y - batch_ys
W_grad = np.dot(batch_xs.T, y_grad)
# update
W = W - learning_rate * W_grad
# evaluate