def test_conv_2d(self):
"""Test invoking Conv2D in eager mode."""
with context.eager_mode():
with tfe.IsolateTest():
length = 4
width = 5
in_channels = 2
filters = 3
kernel_size = 2
batch_size = 10
input = np.random.rand(batch_size, length, width,
in_channels).astype(np.float32)
layer = layers.Conv2D(filters, kernel_size=kernel_size)
result = layer(input)
assert result.shape == (batch_size, length, width, filters)
assert len(layer.variables) == 2
# Creating a second layer should produce different results, since it has
# different random weights.
layer2 = layers.Conv2D(filters, kernel_size=kernel_size)
result2 = layer2(input)
assert not np.allclose(result, result2)
# But evaluating the first layer again should produce the same result as before.
result3 = layer(input)
assert np.allclose(result, result3)
def __init__(self,
seq_length,
use_RNN=False,
num_tasks=1,
num_filters=15,
kernel_size=15,
pool_width=35,
L1=0,
dropout=0.0,
verbose=True,
**kwargs):
super(SequenceDNN, self).__init__(**kwargs)
self.num_tasks = num_tasks
self.verbose = verbose
self.add(layers.Conv2D(num_filters, kernel_size=kernel_size))
self.add(layers.Dropout(dropout))
self.add(layers.Flatten())
self.add(layers.Dense(self.num_tasks, activation_fn=tf.nn.relu))
files.append(os.path.join(image_dir, fname))
labels.append(os.path.join(label_dir, f))
loader = dc.data.ImageLoader()
dataset = loader.featurize(files, labels)
splitter = dc.splits.RandomSplitter()
train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
dataset, seed=123)
# Create the model.
learning_rate = dc.models.optimizers.ExponentialDecay(0.01, 0.9, 250)
model = dc.models.TensorGraph(learning_rate=learning_rate,
model_dir='models/segmentation')
features = layers.Feature(shape=(None, 520, 696, 1)) / 255.0
labels = layers.Label(shape=(None, 520, 696, 1)) / 255.0
# Downsample three times.
conv1 = layers.Conv2D(16, kernel_size=5, stride=2, in_layers=features)
conv2 = layers.Conv2D(32, kernel_size=5, stride=2, in_layers=conv1)
conv3 = layers.Conv2D(64, kernel_size=5, stride=2, in_layers=conv2)
# Do a 1x1 convolution.
conv4 = layers.Conv2D(64, kernel_size=1, stride=1, in_layers=conv3)
# Upsample three times.
concat1 = layers.Concat(in_layers=[conv3, conv4], axis=3)
deconv1 = layers.Conv2DTranspose(32,
kernel_size=5,
stride=2,
in_layers=concat1)
concat2 = layers.Concat(in_layers=[conv2, deconv1], axis=3)
deconv2 = layers.Conv2DTranspose(16,
kernel_size=5,
stride=2,
in_layers=concat2)
# Transfor dataset into format readable by deepchem
train_dataset = dc.data.NumpyDataset(mnist.train.images, mnist.train.labels)
test_dataset = dc.data.NumpyDataset(mnist.test.images, mnist.test.labels)
model = dc.models.TensorGraph(model_dir='mnist')
# Images in MNIST are 28x28, flattened 784
# None means that the input can be of any dimension - we can use it as variable batch size
feature = layers.Feature(shape=(None, 784))
# 0..9 digits
label = layers.Label(shape=(None, 10))
# Reshape flattened layer to matrix to use it with convolution
make_image = layers.Reshape(shape=(None, 28, 28), in_layers=feature)
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)
if f.endswith('.TIF'):
files.append(os.path.join(image_dir, f))
labels.append(int(re.findall('_C(.*?)_', f)[0]))
loader = dc.data.ImageLoader()
dataset = loader.featurize(files, np.array(labels))
splitter = dc.splits.RandomSplitter()
train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(dataset, seed=123)
# Create the model.
learning_rate = dc.models.tensorgraph.optimizers.ExponentialDecay(0.001, 0.9, 250)
model = dc.models.TensorGraph(learning_rate=learning_rate, model_dir='models/model')
features = layers.Feature(shape=(None, 520, 696))
labels = layers.Label(shape=(None,))
prev_layer = features
for num_outputs in [16, 32, 64, 128, 256]:
prev_layer = layers.Conv2D(num_outputs, kernel_size=5, stride=2, in_layers=prev_layer)
output = layers.Dense(1, in_layers=layers.Flatten(prev_layer))
model.add_output(output)
loss = layers.ReduceSum(layers.L2Loss(in_layers=(output, labels)))
model.set_loss(loss)
if not os.path.exists('./models'):
os.mkdir('models')
if not os.path.exists('./models/model'):
os.mkdir('models/model')
if not RETRAIN:
model.restore()
# Train it and evaluate performance on the test set.
if RETRAIN:
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)
