def check_ewise(ufunc):
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
z = ufunc(x, y)
ax = np.ones((2, 3))
ay = np.ones((2, 3)) * 4
sess = tf.Session()
az = sess.run(z, feed_dict={x:ax, y:ay})
np.testing.assert_almost_equal(az, ufunc(ax, ay))
def check_ewise(ufunc):
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
z = ufunc(x, y)
ax = np.ones((2, 3))
ay = np.ones((2, 3)) * 4
sess = tf.Session()
az = sess.run(z, feed_dict={x:ax, y:ay})
np.testing.assert_almost_equal(az, ufunc(ax, ay))
def test_bias_add():
x = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.nn.bias_add(x, b)
ax = np.random.uniform(size=(2, 3))
ab = np.random.uniform(size=(3, ))
sess = tf.Session()
ay = sess.run(y, feed_dict={x: ax, b: ab})
np.testing.assert_almost_equal(ay, ax + ab)
def test_matmul():
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
ay = np.ones((3, 4)) * 4
z = tf.matmul(x, y) * 4
sess = tf.Session()
az = sess.run(z, feed_dict={x: ax, y: ay})
np.testing.assert_almost_equal(az, np.dot(ax, ay) * 4)
def test_add_grad():
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
ay = np.ones((2, 3)) * 4
z = x + y
gx, gy = tf.gradients(z, [x, y])
sess = tf.Session()
agx = sess.run(gx, feed_dict={x:ax, y:ay})
np.testing.assert_almost_equal(agx, np.ones((2,3)))
def test_add_grad():
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
ay = np.ones((2, 3)) * 4
z = x + y
gx, gy = tf.gradients(z, [x, y])
sess = tf.Session()
agx = sess.run(gx, feed_dict={x: ax, y: ay})
np.testing.assert_almost_equal(agx, np.ones((2, 3)))
def test_matmul():
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
ay = np.ones((3, 4)) * 4
z = tf.matmul(x, y) * 4
sess = tf.Session()
az = sess.run(z, feed_dict={x:ax, y:ay})
np.testing.assert_almost_equal(
az, np.dot(ax, ay) * 4)
def test_matmul_grad():
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
ay = np.ones((3, 4)) * 4
z = tf.matmul(x, y) * 4
gx, gy = tf.gradients(z, [x, y])
sess = tf.Session()
agx = sess.run(gx, feed_dict={x: ax, y: ay})
agy = sess.run(gy, feed_dict={x: ax, y: ay})
np.testing.assert_almost_equal(agx, np.dot(np.ones((2, 4)), ay.T) * 4)
np.testing.assert_almost_equal(agy, np.dot(ax.T, np.ones((2, 4))) * 4)
def test_sqrt():
x = tf.placeholder(tf.float32)
y = tf.sqrt(x)
ax = np.ones((2, 3)) * 2
sess = tf.Session()
ay = sess.run(y, feed_dict={x: ax})
np.testing.assert_almost_equal(ay, np.sqrt(ax))
def test_softmax():
x = tf.placeholder(tf.float32)
y = tf.nn.softmax(x)
ax = np.ones((2, 4))
sess = tf.Session()
ay = sess.run(y, feed_dict={x: ax})
np.testing.assert_almost_equal(ay, ax / np.sum(ax, axis=1, keepdims=True))
def test_matmul_grad():
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
ay = np.ones((3, 4)) * 4
z = tf.matmul(x, y) * 4
gx, gy = tf.gradients(z, [x, y])
sess = tf.Session()
agx = sess.run(gx, feed_dict={x:ax, y:ay})
agy = sess.run(gy, feed_dict={x:ax, y:ay})
np.testing.assert_almost_equal(
agx,
np.dot(np.ones((2,4)), ay.T) * 4)
np.testing.assert_almost_equal(
agy,
np.dot(ax.T, np.ones((2,4))) * 4)
def test_sqrt():
x = tf.placeholder(tf.float32)
y = tf.sqrt(x)
ax = np.ones((2, 3)) * 2
sess = tf.Session()
ay = sess.run(y, feed_dict={x:ax})
np.testing.assert_almost_equal(ay, np.sqrt(ax))
def check_ewise_rscalar(ufunc):
x = 10
y = tf.placeholder(tf.float32)
z = ufunc(x, y)
ay = np.ones((2, 3))
sess = tf.Session()
az = sess.run(z, feed_dict={y: ay})
np.testing.assert_almost_equal(az, ufunc(x, ay))
def check_ewise_scalar(ufunc):
x = tf.placeholder(tf.float32)
y = 10;
z = ufunc(x, y)
ax = np.ones((2, 3))
sess = tf.Session()
az = sess.run(z, feed_dict={x:ax})
np.testing.assert_almost_equal(az, ufunc(ax, y))
def check_ewise_rscalar(ufunc):
x = 10;
y = tf.placeholder(tf.float32)
z = ufunc(x, y)
ay = np.ones((2, 3))
sess = tf.Session()
az = sess.run(z, feed_dict={y:ay})
np.testing.assert_almost_equal(az, ufunc(x, ay))
def check_ewise_scalar(ufunc):
x = tf.placeholder(tf.float32)
y = 10
z = ufunc(x, y)
ax = np.ones((2, 3))
sess = tf.Session()
az = sess.run(z, feed_dict={x: ax})
np.testing.assert_almost_equal(az, ufunc(ax, y))
def test_mean_grad():
x = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
z = -tf.reduce_mean(x) * 14
gx = tf.gradients(z, [x])[0]
sess = tf.Session()
agx = sess.run(gx, feed_dict={x:ax})
np.testing.assert_almost_equal(agx, -np.ones((2,3)) * 14 / 6.0)
def test_mean_grad():
x = tf.placeholder(tf.float32)
ax = np.ones((2, 3))
z = -tf.reduce_mean(x) * 14
gx = tf.gradients(z, [x])[0]
sess = tf.Session()
agx = sess.run(gx, feed_dict={x: ax})
np.testing.assert_almost_equal(agx, -np.ones((2, 3)) * 14 / 6.0)
def test_softmax():
x = tf.placeholder(tf.float32)
y = tf.nn.softmax(x)
ax = np.ones((2, 4))
sess = tf.Session()
ay = sess.run(y, feed_dict={x:ax})
np.testing.assert_almost_equal(
ay, ax / np.sum(ax, axis=1, keepdims=True))
def test_argmax():
x = tf.placeholder(tf.float32)
y = tf.argmax(x, 1)
ax = np.random.uniform(size=(700, 10))
sess = tf.Session()
ay = sess.run(y, feed_dict={x:ax})
npy = np.argmax(ax, 1)
assert(np.mean(np.abs(ay - npy))) < 1e-6
def test_argmax():
x = tf.placeholder(tf.float32)
y = tf.argmax(x, 1)
ax = np.random.uniform(size=(700, 10))
sess = tf.Session()
ay = sess.run(y, feed_dict={x:ax})
npy = np.argmax(ax, 1)
assert(np.mean(np.abs(ay - npy))) < 1e-6
def test_mean():
axis = [1, 3]
x = tf.placeholder(tf.float32)
y = tf.reduce_mean(x, reduction_indices=axis)
ax = np.random.uniform(size=(2, 4, 8, 7))
sess = tf.Session()
ay = sess.run(y, feed_dict={x:ax})
npy = ax.mean(axis=tuple(axis))
assert(np.mean(np.abs(ay - npy))) < 1e-6
def test_mean():
axis = [1, 3]
x = tf.placeholder(tf.float32)
y = tf.reduce_mean(x, reduction_indices=axis)
ax = np.random.uniform(size=(2, 4, 8, 7))
sess = tf.Session()
ay = sess.run(y, feed_dict={x:ax})
npy = ax.mean(axis=tuple(axis))
assert(np.mean(np.abs(ay - npy))) < 1e-6
def test_pad():
out_filter = 10
in_filter = 4
pad_width = (out_filter-in_filter)//2
x = tf.placeholder(tf.float32)
y = tf.pad(x, dim=1, pad=-pad_width)
z = tf.pad(y, dim=1, pad=pad_width)
nx = np.random.randn(100, 4, 28, 28)
npy = np.pad(nx, ((0, 0), (pad_width, pad_width), (0, 0), (0, 0)),
mode='constant', constant_values=0)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
ay = sess.run(z, feed_dict={x : nx})
assert(np.mean(np.abs(ay - npy))) < 1e-6
"""Tinyflow example code.
Minimum softmax code that exposes the optimizer.
"""
import tinyflow as tf
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})
"""TinyFlow Example: LeNet for Digits classification.
This code uses automatic variable shape inference for shorter code.
"""
import tinyflow as tf
from tinyflow.datasets import get_mnist
# Create the model
x = tf.placeholder(tf.float32)
conv1 = tf.nn.conv2d(x,
num_filter=20,
ksize=[1, 5, 5, 1],
name="conv1",
no_bias=False)
tanh1 = tf.tanh(conv1)
pool1 = tf.nn.max_pool(tanh1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1])
conv2 = tf.nn.conv2d(pool1,
num_filter=50,
ksize=[1, 5, 5, 1],
name="conv2",
no_bias=False)
tanh2 = tf.tanh(conv2)
pool2 = tf.nn.max_pool(tanh2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1])
flatten = tf.nn.flatten_layer(pool2)
fc1 = tf.nn.linear(flatten, num_hidden=500, name="fc1")
tanh3 = tf.tanh(fc1)
fc2 = tf.nn.linear(tanh3, num_hidden=10, name="fc2")
# define loss
label = tf.placeholder(tf.float32)
cross_entropy = tf.nn.mean_sparse_softmax_cross_entropy_with_logits(fc2, label)
"""TinyFlow Example code.
Automatic variable creation and shape inductions.
The network structure is directly specified via forward node numbers
The variables are automatically created, and their shape infered by tf.infer_variable_shapes
"""
import tinyflow as tf
from tinyflow.datasets import get_mnist
# Create the model
x = tf.placeholder(tf.float32)
fc1 = tf.nn.linear(x, num_hidden=100, name="fc1", no_bias=False)
relu1 = tf.nn.relu(fc1)
fc2 = tf.nn.linear(relu1, num_hidden=10, name="fc2")
# define loss
label = tf.placeholder(tf.float32)
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)
"""Tinyflow example code.
This code is adapted from Tensorflow's MNIST Tutorial with minimum code changes.
"""
import tinyflow as tf
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]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
# get the mnist dataset
mnist = get_mnist(flatten=True, onehot=True)
print("minist download is completed!")
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})
