def test_softmax(self):
"""Test invoking SoftMax in eager mode."""
with context.eager_mode():
input = np.random.rand(5, 10).astype(np.float32)
result = layers.SoftMax()(input)
expected = tf.nn.softmax(input)
assert np.allclose(result, expected)
conv2d_1 = layers.Conv2D(num_outputs=32,
activation_fn=tf.nn.relu,
in_layers=make_image)
conv2d_2 = layers.Conv2D(num_outputs=64,
activation_fn=tf.nn.relu,
in_layers=conv2d_1)
flatten = layers.Flatten(in_layers=conv2d_2)
dense1 = layers.Dense(out_channels=1024,
activation_fn=tf.nn.relu,
in_layers=flatten)
dense2 = layers.Dense(out_channels=10, activation_fn=None, in_layers=dense1)
# Computes the loss for every sample
smce = layers.SoftMaxCrossEntropy(in_layers=[label, dense2])
# Average all the losses
loss = layers.ReduceMean(in_layers=smce)
model.set_loss(loss)
# Convert the output from logits to probs
output = layers.SoftMax(in_layers=dense2)
model.add_output(output)
model.fit(train_dataset, nb_epoch=1) # nb_epoch=10
# Use as metric accuracy: the fraction of labels that are correctly predicted
metric = dc.metrics.Metric(dc.metrics.accuracy_score)
train_scores = model.evaluate(train_dataset, [metric])
test_scores = model.evaluate(test_dataset, [metric])
def __init__(self, n_generators=1, n_discriminators=1, **kwargs):
"""Construct a GAN.
In addition to the parameters listed below, this class accepts all the
keyword arguments from TensorGraph.
Parameters
----------
n_generators: int
the number of generators to include
n_discriminators: int
the number of discriminators to include
"""
super(GAN, self).__init__(use_queue=False, **kwargs)
self.n_generators = n_generators
self.n_discriminators = n_discriminators
# Create the inputs.
self.noise_input = layers.Feature(shape=self.get_noise_input_shape())
self.data_inputs = []
for shape in self.get_data_input_shapes():
self.data_inputs.append(layers.Feature(shape=shape))
self.conditional_inputs = []
for shape in self.get_conditional_input_shapes():
self.conditional_inputs.append(layers.Feature(shape=shape))
# Create the generators.
self.generators = []
for i in range(n_generators):
generator = self.create_generator(self.noise_input,
self.conditional_inputs)
if not isinstance(generator, Sequence):
raise ValueError(
'create_generator() must return a list of Layers')
if len(generator) != len(self.data_inputs):
raise ValueError(
'The number of generator outputs must match the number of data inputs'
)
for g, d in zip(generator, self.data_inputs):
if g.shape != d.shape:
raise ValueError(
'The shapes of the generator outputs must match the shapes of the data inputs'
)
for g in generator:
self.add_output(g)
self.generators.append(generator)
# Create the discriminators.
self.discrim_train = []
self.discrim_gen = []
for i in range(n_discriminators):
discrim_train = self.create_discriminator(self.data_inputs,
self.conditional_inputs)
self.discrim_train.append(discrim_train)
# Make a copy of the discriminator that takes each generator's output as
# its input.
for generator in self.generators:
replacements = {}
for g, d in zip(generator, self.data_inputs):
replacements[d] = g
for c in self.conditional_inputs:
replacements[c] = c
discrim_gen = discrim_train.copy(replacements, shared=True)
self.discrim_gen.append(discrim_gen)
# Make a list of all layers in the generators and discriminators.
def add_layers_to_set(layer, layers):
if layer not in layers:
layers.add(layer)
for i in layer.in_layers:
add_layers_to_set(i, layers)
gen_layers = set()
for generator in self.generators:
for layer in generator:
add_layers_to_set(layer, gen_layers)
discrim_layers = set()
for discriminator in self.discrim_train:
add_layers_to_set(discriminator, discrim_layers)
discrim_layers -= gen_layers
# Compute the loss functions.
gen_losses = [self.create_generator_loss(d) for d in self.discrim_gen]
discrim_losses = []
for i in range(n_discriminators):
for j in range(n_generators):
discrim_losses.append(
self.create_discriminator_loss(
self.discrim_train[i],
self.discrim_gen[i * n_generators + j]))
if n_generators == 1 and n_discriminators == 1:
total_gen_loss = gen_losses[0]
total_discrim_loss = discrim_losses[0]
else:
# Create learnable weights for the generators and discriminators.
gen_alpha = layers.Variable(np.ones((1, n_generators)))
gen_weights = layers.SoftMax(gen_alpha)
discrim_alpha = layers.Variable(np.ones((1, n_discriminators)))
discrim_weights = layers.SoftMax(discrim_alpha)
# Compute the weighted errors
weight_products = layers.Reshape(
(n_generators * n_discriminators, ),
in_layers=layers.Reshape(
(n_discriminators, 1), in_layers=discrim_weights) *
layers.Reshape((1, n_generators), in_layers=gen_weights))
total_gen_loss = layers.WeightedError(
(layers.Stack(gen_losses, axis=0), weight_products))
total_discrim_loss = layers.WeightedError(
(layers.Stack(discrim_losses, axis=0), weight_products))
gen_layers.add(gen_alpha)
discrim_layers.add(gen_alpha)
discrim_layers.add(discrim_alpha)
# Add an entropy term to the loss.
entropy = -(layers.ReduceSum(layers.Log(gen_weights)) /
n_generators + layers.ReduceSum(
layers.Log(discrim_weights)) / n_discriminators)
total_discrim_loss += entropy
# Create submodels for training the generators and discriminators.
self.generator_submodel = self.create_submodel(layers=gen_layers,
loss=total_gen_loss)
self.discriminator_submodel = self.create_submodel(
layers=discrim_layers, loss=total_discrim_loss)
def create_model():
"""
Create our own MNIST model from scratch
:return:
:rtype:
"""
mnist = input_data.read_data_sets("MNIST_DATA/", one_hot=True)
# the layers from deepchem are the building blocks of what we will use to make our deep learning architecture
# now we wrap our dataset into a NumpyDataset
train_dataset = dc.data.NumpyDataset(mnist.train.images,
mnist.train.labels)
test_dataset = dc.data.NumpyDataset(mnist.test.images, mnist.test.labels)
# we will create a model that will take an input, add multiple layers, where each layer takes input from the
# previous layers.
model = dc.models.TensorGraph(model_dir='mnist')
# 784 corresponds to an image of size 28 X 28
# 10 corresponds to the fact that there are 10 possible digits (0-9)
# the None indicates that we can accept any size input (e.g. an empty array or 500 items each with 784 features)
# our data is also categorical so we must one hot encode, set single array element to 1 and the rest to 0
feature = layers.Feature(shape=(None, 784))
labels = layers.Label(shape=(None, 10))
# in order to apply convolutional layers to our input, we convert flat vector of 785 to 28X28
# in_layers means it takes our feature layer as an input
make_image = layers.Reshape(shape=(None, 28, 28), in_layers=feature)
# now that we have reshaped the input, we pass to convolution layers
conv2d_1 = layers.Conv2D(num_outputs=32,
activation_fn=tf.nn.relu,
in_layers=make_image)
conv2d_2 = layers.Conv2D(num_outputs=64,
activation_fn=tf.nn.relu,
in_layers=conv2d_1)
# we want to end by applying fully connected (Dense) layers to the outputs of our convolutional layer
# but first, we must flatten the layer from a 2d matrix to a 1d vector
flatten = layers.Flatten(in_layers=conv2d_2)
dense1 = layers.Dense(out_channels=1024,
activation_fn=tf.nn.relu,
in_layers=flatten)
# note that this is final layer so out_channels of 10 represents the 10 outputs and no activation_fn
dense2 = layers.Dense(out_channels=10,
activation_fn=None,
in_layers=dense1)
# next we want to connect this output to a loss function, so we can train the output
# compute the value of loss function for every sample then average of all samples to get final loss (ReduceMean)
smce = layers.SoftMaxCrossEntropy(in_layers=[labels, dense2])
loss = layers.ReduceMean(in_layers=smce)
model.set_loss(loss)
# for MNIST we want the probability that a given sample represents one of the 10 digits
# we can achieve this using a softmax function to get the probabilities, then cross entropy to get the labels
output = layers.SoftMax(in_layers=dense2)
model.add_output(output)
# if our model takes long to train, reduce nb_epoch to 1
model.fit(train_dataset, nb_epoch=10)
# our metric is accuracy, the fraction of labels that are accurately predicted
metric = dc.metrics.Metric(dc.metrics.accuracy_score)
train_scores = model.evaluate(train_dataset, [metric])
test_scores = model.evaluate(test_dataset, [metric])
print('train_scores', train_scores)
print('test_scores', test_scores)
