def run(method, model_path): model = NeuralClassifier(input_dim=28 * 28) model.stack(Dense(128, 'relu'), Dense(128, 'relu'), Dense(10, 'linear'), Softmax()) trainer = ScipyTrainer(model, method) annealer = LearningRateAnnealer() mnist = MiniBatches(MnistDataset(), batch_size=100) trainer.run(mnist, epoch_controllers=[annealer]) model.save_params(model_path)
def run(initializer, model_path): model = NeuralClassifier(input_dim=28 * 28) for _ in range(6): model.stack(Dense(128, 'relu', init=initializer)) model.stack(Dense(10, 'linear'), Softmax()) trainer = MomentumTrainer(model) annealer = LearningRateAnnealer(trainer) mnist = MiniBatches(MnistDataset(), batch_size=20) trainer.run(mnist, controllers=[annealer]) model.save_params(model_path)
def run(method, model_path): model = NeuralClassifier(input_dim=28 * 28) model.stack(Dense(128, 'relu'), Dense(128, 'relu'), Dense(10, 'linear'), Softmax()) trainer = ScipyTrainer(model, method) annealer = LearningRateAnnealer() mnist = MiniBatches(MnistDataset(), batch_size=100) trainer.run(mnist, controllers=[annealer]) model.save_params(model_path)
expanded_train_set = [] for img, label in mnist.train_set(): expanded_train_set.append((img, label)) original_img = (img * 256).reshape((28, 28)) transformed_img = (elastic_distortion(original_img) / 256).flatten() expanded_train_set.append((transformed_img, label)) global_rand.shuffle(expanded_train_set) expanded_mnist = BasicDataset(train=expanded_train_set, valid=mnist.valid_set(), test=mnist.test_set()) logging.info("expanded training data size: %d" % len(expanded_train_set)) if __name__ == '__main__': model = NeuralClassifier(input_dim=28 * 28) model.stack(Dense(256, 'relu'), Dense(256, 'relu'), Dense(10, 'linear'), Softmax()) trainer = MomentumTrainer(model) annealer = LearningRateAnnealer() mnist = MiniBatches(expanded_mnist, batch_size=20) trainer.run(mnist, controllers=[annealer]) model.save_params(default_model)
default_model = os.path.join(os.path.dirname(__file__), "models", "deep_conv.gz") if __name__ == '__main__': model = NeuralClassifier(input_dim=28 * 28) model.stack( # Reshape to 3D tensor Reshape((-1, 28, 28)), # Add a new dimension for convolution DimShuffle((0, 'x', 1, 2)), Convolution((4, 1, 5, 5), activation="relu"), Dropout(0.15), Convolution((8, 4, 5, 5), activation="relu"), Dropout(0.1), Convolution((16, 8, 3, 3), activation="relu"), Flatten(), Dropout(0.1), # As dimension information was lost, reveal it to the pipe line RevealDimension(16), Dense(10, 'linear'), Softmax()) trainer = MomentumTrainer(model) annealer = LearningRateAnnealer() mnist = MiniBatches(MnistDataset(), batch_size=20) trainer.run(mnist, controllers=[annealer]) model.save_params(default_model)
Classify MNIST digits using a very deep think network. Plain deep networks are very hard to be trained, as shown in this case. But we should notice that if highway layers just learn to pass information forward, in other words, just be transparent layers, then they would be meaningless. """ import logging, os logging.basicConfig(level=logging.INFO) from deepy.dataset import MnistDataset, MiniBatches from deepy.networks import NeuralClassifier from deepy.layers import Dense, Softmax from deepy.trainers import MomentumTrainer, LearningRateAnnealer model_path = os.path.join(os.path.dirname(__file__), "models", "baseline1.gz") if __name__ == '__main__': model = NeuralClassifier(input_dim=28 * 28) for _ in range(20): model.stack(Dense(71, 'relu')) model.stack(Dense(10, 'linear'), Softmax()) trainer = MomentumTrainer(model) mnist = MiniBatches(MnistDataset(), batch_size=20) trainer.run(mnist, controllers=[LearningRateAnnealer()]) model.save_params(model_path)
import logging, os logging.basicConfig(level=logging.INFO) # MNIST Multi-layer model with dropout. from deepy.dataset import MnistDataset, MiniBatches from deepy.networks import NeuralClassifier from deepy.layers import Dense, Softmax, Dropout from deepy.trainers import MomentumTrainer, LearningRateAnnealer model_path = os.path.join(os.path.dirname(__file__), "models", "tutorial1.gz") if __name__ == '__main__': model = NeuralClassifier(input_dim=28 * 28) model.stack(Dense(256, 'relu'), Dropout(0.2), Dense(256, 'relu'), Dropout(0.2), Dense(10, 'linear'), Softmax()) mnist = MiniBatches(MnistDataset(), batch_size=20) trainer = MomentumTrainer(model, {"learning_rate": LearningRateAnnealer.learning_rate(0.01)}) annealer = LearningRateAnnealer(trainer) trainer.run(mnist, controllers=[annealer]) model.save_params(model_path)