def test_reduce_mean(self): """Test invoking ReduceMean in eager mode.""" with context.eager_mode(): input = np.random.rand(5, 10).astype(np.float32) result = layers.ReduceMean(axis=1)(input) assert result.shape == (5, ) assert np.allclose(result, np.mean(input, axis=1))
def _create_loss(self): """Create the loss function.""" prob = layers.ReduceSum(self.output * self._labels, axis=2) mask = layers.ReduceSum(self._labels, axis=2) log_prob = layers.Log(prob + 1e-20) * mask loss = -layers.ReduceMean( layers.ReduceSum(log_prob, axis=1), name='cross_entropy_loss') if self._variational: mean_sq = self._embedding_mean * self._embedding_mean stddev_sq = self._embedding_stddev * self._embedding_stddev kl = mean_sq + stddev_sq - layers.Log(stddev_sq + 1e-20) - 1 anneal_steps = self._annealing_final_step - self._annealing_start_step if anneal_steps > 0: current_step = tf.to_float( self.get_global_step()) - self._annealing_start_step anneal_frac = tf.maximum(0.0, current_step) / anneal_steps kl_scale = layers.TensorWrapper( tf.minimum(1.0, anneal_frac * anneal_frac), name='kl_scale') else: kl_scale = 1.0 loss += 0.5 * kl_scale * layers.ReduceMean(kl) return loss
def create_generator_loss(self, discrim_output): """Create the loss function for the generator. The default implementation is appropriate for most cases. Subclasses can override this if the need to customize it. Parameters ---------- discrim_output: Layer the output from the discriminator on a batch of generated data. This is its estimate of the probability that each sample is training data. Returns ------- A Layer object that outputs the loss function to use for optimizing the generator. """ return -layers.ReduceMean(layers.Log(discrim_output + 1e-10))
def test_tensorboard(self): """Test creating an Estimator from a TensorGraph that logs information to TensorBoard.""" n_samples = 10 n_features = 3 n_tasks = 2 # Create a dataset and an input function for processing it. np.random.seed(123) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y) def input_fn(epochs): x, y, weights = dataset.make_iterator(batch_size=n_samples, epochs=epochs).get_next() return {'x': x, 'weights': weights}, y # Create a TensorGraph model. model = dc.models.TensorGraph() features = layers.Feature(shape=(None, n_features)) dense = layers.Dense(out_channels=n_tasks, in_layers=features) dense.set_summary('histogram') model.add_output(dense) labels = layers.Label(shape=(None, n_tasks)) loss = layers.ReduceMean(layers.L2Loss(in_layers=[labels, dense])) model.set_loss(loss) # Create an estimator from it. x_col = tf.feature_column.numeric_column('x', shape=(n_features, )) estimator = model.make_estimator(feature_columns=[x_col]) # Train the model. estimator.train(input_fn=lambda: input_fn(100))
model = dc.models.TensorGraph(model_dir='rnai') features = layers.Feature(shape=(None, 21, 4)) labels = layers.Label(shape=(None, 1)) prev = features for i in range(2): prev = layers.Conv1D(filters=10, kernel_size=10, activation=tf.nn.relu, padding='same', in_layers=prev) prev = layers.Dropout(dropout_prob=0.3, in_layers=prev) output = layers.Dense(out_channels=1, activation_fn=tf.sigmoid, in_layers=layers.Flatten(prev)) model.add_output(output) loss = layers.ReduceMean(layers.L2Loss(in_layers=[labels, output])) model.set_loss(loss) # Load the data. train = dc.data.DiskDataset('train_siRNA') valid = dc.data.DiskDataset('valid_siRNA') # Train the model, tracking its performance on the training and validation datasets. metric = dc.metrics.Metric(dc.metrics.pearsonr, mode='regression') for i in range(20): model.fit(train, nb_epoch=10) print(model.evaluate(train, [metric])['pearsonr'][0]) print(model.evaluate(valid, [metric])['pearsonr'][0])
def create_discriminator_loss(self, discrim_output_train, discrim_output_gen): gradient_penalty = GradientPenaltyLayer(discrim_output_train, self) return gradient_penalty + layers.ReduceMean(discrim_output_train - discrim_output_gen)
def create_generator_loss(self, discrim_output): return layers.ReduceMean(discrim_output)
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 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)