#@title Licensed under the Apache License, Version 2.0 (the "License"); { display-mode: "form" }
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import numpy as np

import tensorflow as tf

@tf.function
def simple_nn_layer(x, y):
  return tf.nn.relu(tf.matmul(x, y))


x = tf.random.uniform((3, 3))
y = tf.random.uniform((3, 3))

simple_nn_layer(x, y)

simple_nn_layer

def linear_layer(x):
  return 2 * x + 1


@tf.function
def deep_net(x):
  return tf.nn.relu(linear_layer(x))


deep_net(tf.constant((1, 2, 3)))

import timeit
conv_layer = tf.keras.layers.Conv2D(100, 3)

@tf.function
def conv_fn(image):
  return conv_layer(image)

image = tf.zeros([1, 200, 200, 100])
# warm up
conv_layer(image); conv_fn(image)
print("Eager conv:", timeit.timeit(lambda: conv_layer(image), number=10))
print("Function conv:", timeit.timeit(lambda: conv_fn(image), number=10))
print("Note how there's not much difference in performance for convolutions")


lstm_cell = tf.keras.layers.LSTMCell(10)

@tf.function
def lstm_fn(input, state):
  return lstm_cell(input, state)

input = tf.zeros([10, 10])
state = [tf.zeros([10, 10])] * 2
# warm up
lstm_cell(input, state); lstm_fn(input, state)
print("eager lstm:", timeit.timeit(lambda: lstm_cell(input, state), number=10))
print("function lstm:", timeit.timeit(lambda: lstm_fn(input, state), number=10))


@tf.function
def square_if_positive(x):
  if x > 0:
    x = x * x
  else:
    x = 0
  return x


print('square_if_positive(2) = {}'.format(square_if_positive(tf.constant(2))))
print('square_if_positive(-2) = {}'.format(square_if_positive(tf.constant(-2))))

@tf.function
def sum_even(items):
  s = 0
  for c in items:
    if c % 2 > 0:
      continue
    s += c
  return s


sum_even(tf.constant([10, 12, 15, 20]))

print(tf.autograph.to_code(sum_even.python_function))

@tf.function
def fizzbuzz(n):
  for i in tf.range(n):
    if i % 3 == 0:
      tf.print('Fizz')
    elif i % 5 == 0:
      tf.print('Buzz')
    else:
      tf.print(i)

fizzbuzz(tf.constant(15))

class CustomModel(tf.keras.models.Model):

  @tf.function
  def call(self, input_data):
    if tf.reduce_mean(input_data) > 0:
      return input_data
    else:
      return input_data // 2


model = CustomModel()

model(tf.constant([-2, -4]))

v = tf.Variable(5)

@tf.function
def find_next_odd():
  v.assign(v + 1)
  if v % 2 == 0:
    v.assign(v + 1)


find_next_odd()
v

@tf.function
def f(x):
  if x > 0:
    # Try setting a breakpoint here!
    # Example:
    #   import pdb
    #   pdb.set_trace()
    x = x + 1
  return x

tf.config.experimental_run_functions_eagerly(True)

# You can now set breakpoints and run the code in a debugger.
f(tf.constant(1))

tf.config.experimental_run_functions_eagerly(False)

def prepare_mnist_features_and_labels(x, y):
  x = tf.cast(x, tf.float32) / 255.0
  y = tf.cast(y, tf.int64)
  return x, y

def mnist_dataset():
  (x, y), _ = tf.keras.datasets.mnist.load_data()
  ds = tf.data.Dataset.from_tensor_slices((x, y))
  ds = ds.map(prepare_mnist_features_and_labels)
  ds = ds.take(20000).shuffle(20000).batch(100)
  return ds

train_dataset = mnist_dataset()

model = tf.keras.Sequential((
    tf.keras.layers.Reshape(target_shape=(28 * 28,), input_shape=(28, 28)),
    tf.keras.layers.Dense(100, activation='relu'),
    tf.keras.layers.Dense(100, activation='relu'),
    tf.keras.layers.Dense(10)))
model.build()
optimizer = tf.keras.optimizers.Adam()

compute_loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

compute_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()


def train_one_step(model, optimizer, x, y):
  with tf.GradientTape() as tape:
    logits = model(x)
    loss = compute_loss(y, logits)

  grads = tape.gradient(loss, model.trainable_variables)
  optimizer.apply_gradients(zip(grads, model.trainable_variables))

  compute_accuracy(y, logits)
  return loss


@tf.function
def train(model, optimizer):
  train_ds = mnist_dataset()
  step = 0
  loss = 0.0
  accuracy = 0.0
  for x, y in train_ds:
    step += 1
    loss = train_one_step(model, optimizer, x, y)
    if step % 10 == 0:
      tf.print('Step', step, ': loss', loss, '; accuracy', compute_accuracy.result())
  return step, loss, accuracy

step, loss, accuracy = train(model, optimizer)
print('Final step', step, ': loss', loss, '; accuracy', compute_accuracy.result())

def square_if_positive(x):
  return [i ** 2 if i > 0 else i for i in x]


square_if_positive(range(-5, 5))

@tf.function
def square_if_positive_naive(x):
  result = tf.TensorArray(tf.int32, size=x.shape[0])
  for i in tf.range(x.shape[0]):
    if x[i] > 0:
      result = result.write(i, x[i] ** 2)
    else:
      result = result.write(i, x[i])
  return result.stack()


square_if_positive_naive(tf.range(-5, 5))

def square_if_positive_vectorized(x):
  return tf.where(x > 0, x ** 2, x)


square_if_positive_vectorized(tf.range(-5, 5))

import timeit


@tf.function
def f(x, y):
  return tf.matmul(x, y)

print(
    "First invocation:",
    timeit.timeit(lambda: f(tf.ones((10, 10)), tf.ones((10, 10))), number=1))

print(
    "Second invocation:",
    timeit.timeit(lambda: f(tf.ones((10, 10)), tf.ones((10, 10))), number=1))

@tf.function
def f():
  print('Tracing!')
  tf.print('Executing')

print('First invocation:')
f()

print('Second invocation:')
f()

@tf.function
def f(n):
  print(n, 'Tracing!')
  tf.print(n, 'Executing')

f(1)
f(1)

f(2)
f(2)

@tf.function
def f(x):
  print(x.shape, 'Tracing!')
  tf.print(x, 'Executing')

f(tf.constant([1]))
f(tf.constant([2]))

f(tf.constant([1, 2]))
f(tf.constant([3, 4]))

def f():
  print('Tracing!')
  tf.print('Executing')

tf.function(f)()
tf.function(f)()

def outer():
  @tf.function
  def f():
    print('Tracing!')
    tf.print('Executing')
  f()

outer()
outer()