Content Overview

TF NumPy and TensorFlow

TensorFlow NumPy is built on top of TensorFlow and hence interoperates seamlessly with TensorFlow.

tf.Tensor and ND array

ND array is an alias to tf.Tensor, so obviously they can be intermixed without triggering actual data copies.

x = tf.constant([1, 2])
print(x)

# `asarray` and `convert_to_tensor` here are no-ops.
tnp_x = tnp.asarray(x)
print(tnp_x)
print(tf.convert_to_tensor(tnp_x))

# Note that tf.Tensor.numpy() will continue to return `np.ndarray`.
print(x.numpy(), x.numpy().__class__)


tf.Tensor([1 2], shape=(2,), dtype=int32)
tf.Tensor([1 2], shape=(2,), dtype=int32)
tf.Tensor([1 2], shape=(2,), dtype=int32)
[1 2] <class 'numpy.ndarray'>

TensorFlow interoperability

An ND array can be passed to TensorFlow APIs, since ND array is just an alias to tf.Tensor. As mentioned earlier, such interoperation does not do data copies, even for data placed on accelerators or remote devices.

Conversely, tf.Tensor objects can be passed to tf.experimental.numpy APIs, without performing data copies.

# ND array passed into TensorFlow function.
tf_sum = tf.reduce_sum(tnp.ones([2, 3], tnp.float32))
print("Output = %s" % tf_sum)

# `tf.Tensor` passed into TensorFlow NumPy function.
tnp_sum = tnp.sum(tf.ones([2, 3]))
print("Output = %s" % tnp_sum)


Output = tf.Tensor(6.0, shape=(), dtype=float32)
Output = tf.Tensor(6.0, shape=(), dtype=float32)

Gradients and Jacobians: tf.GradientTape

TensorFlow's GradientTape can be used for backpropagation through TensorFlow and TensorFlow NumPy code.

Use the model created in Example Model section, and compute gradients and jacobians.

def create_batch(batch_size=32):
  """Creates a batch of input and labels."""
  return (tnp.random.randn(batch_size, 32).astype(tnp.float32),
          tnp.random.randn(batch_size, 2).astype(tnp.float32))

def compute_gradients(model, inputs, labels):
  """Computes gradients of squared loss between model prediction and labels."""
  with tf.GradientTape() as tape:
    assert model.weights is not None
    # Note that `model.weights` need to be explicitly watched since they
    # are not tf.Variables.
    tape.watch(model.weights)
    # Compute prediction and loss
    prediction = model.predict(inputs)
    loss = tnp.sum(tnp.square(prediction - labels))
  # This call computes the gradient through the computation above.
  return tape.gradient(loss, model.weights)

inputs, labels = create_batch()
gradients = compute_gradients(model, inputs, labels)

# Inspect the shapes of returned gradients to verify they match the
# parameter shapes.
print("Parameter shapes:", [w.shape for w in model.weights])
print("Gradient shapes:", [g.shape for g in gradients])
# Verify that gradients are of type ND array.
assert isinstance(gradients[0], tnp.ndarray)


Parameter shapes: [TensorShape([32, 64]), TensorShape([64]), TensorShape([64, 2])]
Gradient shapes: [TensorShape([32, 64]), TensorShape([64]), TensorShape([64, 2])]


# Computes a batch of jacobians. Each row is the jacobian of an element in the
# batch of outputs w.r.t. the corresponding input batch element.
def prediction_batch_jacobian(inputs):
  with tf.GradientTape() as tape:
    tape.watch(inputs)
    prediction = model.predict(inputs)
  return prediction, tape.batch_jacobian(prediction, inputs)

inp_batch = tnp.ones([16, 32], tnp.float32)
output, batch_jacobian = prediction_batch_jacobian(inp_batch)
# Note how the batch jacobian shape relates to the input and output shapes.
print("Output shape: %s, input shape: %s" % (output.shape, inp_batch.shape))
print("Batch jacobian shape:", batch_jacobian.shape)


Output shape: (16, 2), input shape: (16, 32)
Batch jacobian shape: (16, 2, 32)

Trace compilation: tf.function

TensorFlow's tf.function works by "trace compiling" the code and then optimizing these traces for much faster performance. See the Introduction to Graphs and Functions.

tf.function can be used to optimize TensorFlow NumPy code as well. Here is a simple example to demonstrate the speedups. Note that the body of tf.function code includes calls to TensorFlow NumPy APIs.

inputs, labels = create_batch(512)
print("Eager performance")
compute_gradients(model, inputs, labels)
print(timeit.timeit(lambda: compute_gradients(model, inputs, labels),
                    number=10) * 100, "ms")

print("\ntf.function compiled performance")
compiled_compute_gradients = tf.function(compute_gradients)
compiled_compute_gradients(model, inputs, labels)  # warmup
print(timeit.timeit(lambda: compiled_compute_gradients(model, inputs, labels),
                    number=10) * 100, "ms")


Eager performance
2.710705300000882 ms

tf.function compiled performance
0.7041131000050882 ms

Vectorization: tf.vectorized_map

TensorFlow has inbuilt support for vectorizing parallel loops, which allows speedups of one to two orders of magnitude. These speedups are accessible via the tf.vectorized_map API and apply to TensorFlow NumPy code as well.

It is sometimes useful to compute the gradient of each output in a batch w.r.t. the corresponding input batch element. Such computation can be done efficiently using tf.vectorized_map as shown below.

@tf.function
def vectorized_per_example_gradients(inputs, labels):
  def single_example_gradient(arg):
    inp, label = arg
    return compute_gradients(model,
                             tnp.expand_dims(inp, 0),
                             tnp.expand_dims(label, 0))
  # Note that a call to `tf.vectorized_map` semantically maps
  # `single_example_gradient` over each row of `inputs` and `labels`.
  # The interface is similar to `tf.map_fn`.
  # The underlying machinery vectorizes away this map loop which gives
  # nice speedups.
  return tf.vectorized_map(single_example_gradient, (inputs, labels))

batch_size = 128
inputs, labels = create_batch(batch_size)

per_example_gradients = vectorized_per_example_gradients(inputs, labels)
for w, p in zip(model.weights, per_example_gradients):
  print("Weight shape: %s, batch size: %s, per example gradient shape: %s " % (
      w.shape, batch_size, p.shape))


Weight shape: (32, 64), batch size: 128, per example gradient shape: (128, 32, 64) 
Weight shape: (64,), batch size: 128, per example gradient shape: (128, 64) 
Weight shape: (64, 2), batch size: 128, per example gradient shape: (128, 64, 2)


# Benchmark the vectorized computation above and compare with
# unvectorized sequential computation using `tf.map_fn`.
@tf.function
def unvectorized_per_example_gradients(inputs, labels):
  def single_example_gradient(arg):
    inp, label = arg
    return compute_gradients(model,
                             tnp.expand_dims(inp, 0),
                             tnp.expand_dims(label, 0))

  return tf.map_fn(single_example_gradient, (inputs, labels),
                   fn_output_signature=(tf.float32, tf.float32, tf.float32))

print("Running vectorized computation")
print(timeit.timeit(lambda: vectorized_per_example_gradients(inputs, labels),
                    number=10) * 100, "ms")

print("\nRunning unvectorized computation")
per_example_gradients = unvectorized_per_example_gradients(inputs, labels)
print(timeit.timeit(lambda: unvectorized_per_example_gradients(inputs, labels),
                    number=10) * 100, "ms")


Running vectorized computation
0.659675699989748 ms

Running unvectorized computation
29.259711299982882 ms

Device placement

TensorFlow NumPy can place operations on CPUs, GPUs, TPUs and remote devices. It uses standard TensorFlow mechanisms for device placement. Below a simple example shows how to list all devices and then place some computation on a particular device.

TensorFlow also has APIs for replicating computation across devices and performing collective reductions which will not be covered here.

List devices

tf.config.list_logical_devices and tf.config.list_physical_devices can be used to find what devices to use.

print("All logical devices:", tf.config.list_logical_devices())
print("All physical devices:", tf.config.list_physical_devices())

# Try to get the GPU device. If unavailable, fallback to CPU.
try:
  device = tf.config.list_logical_devices(device_type="GPU")[0]
except IndexError:
  device = "/device:CPU:0"


All logical devices: [LogicalDevice(name='/device:CPU:0', device_type='CPU'), LogicalDevice(name='/device:GPU:0', device_type='GPU'), LogicalDevice(name='/device:GPU:1', device_type='GPU'), LogicalDevice(name='/device:GPU:2', device_type='GPU'), LogicalDevice(name='/device:GPU:3', device_type='GPU')]
All physical devices: [PhysicalDevice(name='/physical_device:CPU:0', device_type='CPU'), PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU'), PhysicalDevice(name='/physical_device:GPU:1', device_type='GPU'), PhysicalDevice(name='/physical_device:GPU:2', device_type='GPU'), PhysicalDevice(name='/physical_device:GPU:3', device_type='GPU')]

Placing operations: tf.device

Operations can be placed on a device by calling it in a tf.device scope.

print("Using device: %s" % str(device))
# Run operations in the `tf.device` scope.
# If a GPU is available, these operations execute on the GPU and outputs are
# placed on the GPU memory.
with tf.device(device):
  prediction = model.predict(create_batch(5)[0])

print("prediction is placed on %s" % prediction.device)


Using device: LogicalDevice(name='/device:GPU:0', device_type='GPU')
prediction is placed on /job:localhost/replica:0/task:0/device:GPU:0

Copying ND arrays across devices: tnp.copy

A call to tnp.copy, placed in a certain device scope, will copy the data to that device, unless the data is already on that device.

with tf.device("/device:CPU:0"):
  prediction_cpu = tnp.copy(prediction)
print(prediction.device)
print(prediction_cpu.device)


/job:localhost/replica:0/task:0/device:GPU:0
/job:localhost/replica:0/task:0/device:CPU:0

Performance comparisons

TensorFlow NumPy uses highly optimized TensorFlow kernels that can be dispatched on CPUs, GPUs and TPUs. TensorFlow also performs many compiler optimizations, like operation fusion, which translate to performance and memory improvements. See TensorFlow graph optimization with Grappler to learn more.

However TensorFlow has higher overheads for dispatching operations compared to NumPy. For workloads composed of small operations (less than about 10 microseconds), these overheads can dominate the runtime and NumPy could provide better performance. For other cases, TensorFlow should generally provide better performance.

Run the benchmark below to compare NumPy and TensorFlow NumPy performance for different input sizes.

def benchmark(f, inputs, number=30, force_gpu_sync=False):
  """Utility to benchmark `f` on each value in `inputs`."""
  times = []
  for inp in inputs:
    def _g():
      if force_gpu_sync:
        one = tnp.asarray(1)
      f(inp)
      if force_gpu_sync:
        with tf.device("CPU:0"):
          tnp.copy(one)  # Force a sync for GPU case

    _g()  # warmup
    t = timeit.timeit(_g, number=number)
    times.append(t * 1000. / number)
  return times


def plot(np_times, tnp_times, compiled_tnp_times, has_gpu, tnp_times_gpu):
  """Plot the different runtimes."""
  plt.xlabel("size")
  plt.ylabel("time (ms)")
  plt.title("Sigmoid benchmark: TF NumPy vs NumPy")
  plt.plot(sizes, np_times, label="NumPy")
  plt.plot(sizes, tnp_times, label="TF NumPy (CPU)")
  plt.plot(sizes, compiled_tnp_times, label="Compiled TF NumPy (CPU)")
  if has_gpu:
    plt.plot(sizes, tnp_times_gpu, label="TF NumPy (GPU)")
  plt.legend()


# Define a simple implementation of `sigmoid`, and benchmark it using
# NumPy and TensorFlow NumPy for different input sizes.

def np_sigmoid(y):
  return 1. / (1. + np.exp(-y))

def tnp_sigmoid(y):
  return 1. / (1. + tnp.exp(-y))

@tf.function
def compiled_tnp_sigmoid(y):
  return tnp_sigmoid(y)

sizes = (2 ** 0, 2 ** 5, 2 ** 10, 2 ** 15, 2 ** 20)
np_inputs = [np.random.randn(size).astype(np.float32) for size in sizes]
np_times = benchmark(np_sigmoid, np_inputs)

with tf.device("/device:CPU:0"):
  tnp_inputs = [tnp.random.randn(size).astype(np.float32) for size in sizes]
  tnp_times = benchmark(tnp_sigmoid, tnp_inputs)
  compiled_tnp_times = benchmark(compiled_tnp_sigmoid, tnp_inputs)

has_gpu = len(tf.config.list_logical_devices("GPU"))
if has_gpu:
  with tf.device("/device:GPU:0"):
    tnp_inputs = [tnp.random.randn(size).astype(np.float32) for size in sizes]
    tnp_times_gpu = benchmark(compiled_tnp_sigmoid, tnp_inputs, 100, True)
else:
  tnp_times_gpu = None
plot(np_times, tnp_times, compiled_tnp_times, has_gpu, tnp_times_gpu)

Further reading

Originally published on the TensorFlow website, this article appears here under a new headline and is licensed under CC BY 4.0. Code samples shared under the Apache 2.0 License.