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)