def get_processed_data(): x_train = np.random.rand(20, 28, 28, 3) y_train = np.random.rand(20, 3) x_test = np.random.rand(10, 28, 28, 3) y_test = np.random.rand(10, 3) data_transformer = DataTransformer(x_train) train_data = data_transformer.transform_train(x_train, y_train) test_data = data_transformer.transform_train(x_test, y_test) return train_data, test_data
def get_classification_data_loaders(): x_train = np.random.rand(200, 28, 28, 3) y_train = np.random.rand(200, 3) x_test = np.random.rand(190, 28, 28, 3) y_test = np.random.rand(190, 3) data_transformer = DataTransformer(x_train, augment=True) train_data = data_transformer.transform_train(x_train, y_train) test_data = data_transformer.transform_test(x_test, y_test) return train_data, test_data
def get_classification_dataloaders(): x_train = np.random.rand(200, 28, 28, 3) y_train = np.random.rand(200, 3) x_test = np.random.rand(190, 28, 28, 3) y_test = np.random.rand(190, 3) data_transformer = DataTransformer(x_train, augment=True) train_data = data_transformer.transform_train(x_train, y_train) test_data = data_transformer.transform_test(x_test, y_test) return train_data, test_data
class ImageSupervised(Supervised): """The image classifier class. It is used for image classification. It searches convolutional neural network architectures for the best configuration for the dataset. Attributes: path: A path to the directory to save the classifier. y_encoder: An instance of OneHotEncoder for `y_train` (array of categorical labels). verbose: A boolean value indicating the verbosity mode. searcher: An instance of BayesianSearcher. It searches different neural architecture to find the best model. searcher_args: A dictionary containing the parameters for the searcher's __init__ function. augment: A boolean value indicating whether the data needs augmentation. """ def __init__(self, verbose=False, path=None, resume=False, searcher_args=None, augment=None): """Initialize the instance. The classifier will be loaded from the files in 'path' if parameter 'resume' is True. Otherwise it would create a new one. Args: verbose: A boolean of whether the search process will be printed to stdout. path: A string. The path to a directory, where the intermediate results are saved. resume: A boolean. If True, the classifier will continue to previous work saved in path. Otherwise, the classifier will start a new search. augment: A boolean value indicating whether the data needs augmentation. """ super().__init__(verbose) if searcher_args is None: searcher_args = {} if path is None: path = temp_folder_generator() if augment is None: augment = Constant.DATA_AUGMENTATION if has_file(os.path.join(path, 'classifier')) and resume: classifier = pickle_from_file(os.path.join(path, 'classifier')) self.__dict__ = classifier.__dict__ self.path = path else: self.y_encoder = None self.data_transformer = None self.verbose = verbose self.searcher = False self.path = path self.searcher_args = searcher_args self.augment = augment ensure_dir(path) @property @abstractmethod def metric(self): pass @property @abstractmethod def loss(self): pass def fit(self, x_train=None, y_train=None, time_limit=None): """Find the best neural architecture and train it. Based on the given dataset, the function will find the best neural architecture for it. The dataset is in numpy.ndarray format. So they training data should be passed through `x_train`, `y_train`. Args: x_train: A numpy.ndarray instance containing the training data. y_train: A numpy.ndarray instance containing the label of the training data. time_limit: The time limit for the search in seconds. """ if y_train is None: y_train = [] if x_train is None: x_train = [] x_train = np.array(x_train) y_train = np.array(y_train).flatten() _validate(x_train, y_train) y_train = self.transform_y(y_train) # Transform x_train if self.data_transformer is None: self.data_transformer = DataTransformer(x_train, augment=self.augment) # Create the searcher and save on disk if not self.searcher: input_shape = x_train.shape[1:] self.searcher_args['n_output_node'] = self.get_n_output_node() self.searcher_args['input_shape'] = input_shape self.searcher_args['path'] = self.path self.searcher_args['metric'] = self.metric self.searcher_args['loss'] = self.loss self.searcher_args['verbose'] = self.verbose searcher = Searcher(**self.searcher_args) self.save_searcher(searcher) self.searcher = True # Divide training data into training and testing data. x_train, x_test, y_train, y_test = train_test_split( x_train, y_train, test_size=min(Constant.VALIDATION_SET_SIZE, int(len(y_train) * 0.2)), random_state=42) # Wrap the data into DataLoaders train_data = self.data_transformer.transform_train(x_train, y_train) test_data = self.data_transformer.transform_test(x_test, y_test) # Save the classifier pickle.dump(self, open(os.path.join(self.path, 'classifier'), 'wb')) pickle_to_file(self, os.path.join(self.path, 'classifier')) if time_limit is None: time_limit = 24 * 60 * 60 start_time = time.time() time_remain = time_limit try: while time_remain > 0: run_searcher_once(train_data, test_data, self.path, int(time_remain)) if len(self.load_searcher().history) >= Constant.MAX_MODEL_NUM: break time_elapsed = time.time() - start_time time_remain = time_limit - time_elapsed # if no search executed during the time_limit, then raise an error if time_remain <= 0: raise TimeoutError except TimeoutError: if len(self.load_searcher().history) == 0: raise TimeoutError( "Search Time too short. No model was found during the search time." ) elif self.verbose: print('Time is out.') @abstractmethod def get_n_output_node(self): pass def transform_y(self, y_train): return y_train def predict(self, x_test): """Return predict results for the testing data. Args: x_test: An instance of numpy.ndarray containing the testing data. Returns: A numpy.ndarray containing the results. """ if Constant.LIMIT_MEMORY: pass test_loader = self.data_transformer.transform_test(x_test) model = self.load_searcher().load_best_model().produce_model() model.eval() outputs = [] with torch.no_grad(): for index, inputs in enumerate(test_loader): outputs.append(model(inputs).numpy()) output = reduce(lambda x, y: np.concatenate((x, y)), outputs) return self.inverse_transform_y(output) def inverse_transform_y(self, output): return output def evaluate(self, x_test, y_test): """Return the accuracy score between predict value and `y_test`.""" y_predict = self.predict(x_test) return accuracy_score(y_test, y_predict) def save_searcher(self, searcher): pickle.dump(searcher, open(os.path.join(self.path, 'searcher'), 'wb')) def load_searcher(self): return pickle_from_file(os.path.join(self.path, 'searcher')) def final_fit(self, x_train, y_train, x_test, y_test, trainer_args=None, retrain=False): """Final training after found the best architecture. Args: x_train: A numpy.ndarray of training data. y_train: A numpy.ndarray of training targets. x_test: A numpy.ndarray of testing data. y_test: A numpy.ndarray of testing targets. trainer_args: A dictionary containing the parameters of the ModelTrainer constructor. retrain: A boolean of whether reinitialize the weights of the model. """ if trainer_args is None: trainer_args = {'max_no_improvement_num': 30} y_train = self.transform_y(y_train) y_test = self.transform_y(y_test) train_data = self.data_transformer.transform_train(x_train, y_train) test_data = self.data_transformer.transform_test(x_test, y_test) searcher = self.load_searcher() graph = searcher.load_best_model() if retrain: graph.weighted = False _, _1, graph = train((graph, train_data, test_data, trainer_args, None, self.metric, self.loss, self.verbose)) def get_best_model_id(self): """ Return an integer indicating the id of the best model.""" return self.load_searcher().get_best_model_id() def export_keras_model(self, model_file_name): """ Exports the best Keras model to the given filename. """ self.load_searcher().load_best_model().produce_keras_model().save( model_file_name) def export_autokeras_model(self, model_file_name): """ Creates and Exports the AutoKeras model to the given filename. """ portable_model = PortableImageSupervised(graph=self.load_searcher().load_best_model(), \ y_encoder=self.y_encoder, data_transformer=self.data_transformer) pickle_to_file(portable_model, model_file_name)
class ImageSupervised(Supervised): """The image classifier class. It is used for image classification. It searches convolutional neural network architectures for the best configuration for the dataset. Attributes: path: A path to the directory to save the classifier. y_encoder: An instance of OneHotEncoder for `y_train` (array of categorical labels). verbose: A boolean value indicating the verbosity mode. searcher: An instance of BayesianSearcher. It searches different neural architecture to find the best model. searcher_args: A dictionary containing the parameters for the searcher's __init__ function. augment: A boolean value indicating whether the data needs augmentation. If not define, then it will use the value of Constant.DATA_AUGMENTATION which is True by default. """ def __init__(self, verbose=False, path=None, resume=False, searcher_args=None, augment=None): """Initialize the instance. The classifier will be loaded from the files in 'path' if parameter 'resume' is True. Otherwise it would create a new one. Args: verbose: A boolean of whether the search process will be printed to stdout. path: A string. The path to a directory, where the intermediate results are saved. resume: A boolean. If True, the classifier will continue to previous work saved in path. Otherwise, the classifier will start a new search. augment: A boolean value indicating whether the data needs augmentation. If not define, then it will use the value of Constant.DATA_AUGMENTATION which is True by default. """ super().__init__(verbose) if searcher_args is None: searcher_args = {} if path is None: path = temp_folder_generator() if augment is None: augment = Constant.DATA_AUGMENTATION if has_file(os.path.join(path, 'classifier')) and resume: classifier = pickle_from_file(os.path.join(path, 'classifier')) self.__dict__ = classifier.__dict__ self.path = path else: self.y_encoder = None self.data_transformer = None self.verbose = verbose self.searcher = False self.path = path self.searcher_args = searcher_args self.augment = augment ensure_dir(path) @property @abstractmethod def metric(self): pass @property @abstractmethod def loss(self): pass def fit(self, x_train=None, y_train=None, time_limit=None): """Find the best neural architecture and train it. Based on the given dataset, the function will find the best neural architecture for it. The dataset is in numpy.ndarray format. So they training data should be passed through `x_train`, `y_train`. Args: x_train: A numpy.ndarray instance containing the training data. y_train: A numpy.ndarray instance containing the label of the training data. time_limit: The time limit for the search in seconds. """ if y_train is None: y_train = [] if x_train is None: x_train = [] x_train = np.array(x_train) y_train = np.array(y_train).flatten() _validate(x_train, y_train) y_train = self.transform_y(y_train) # Transform x_train if self.data_transformer is None: self.data_transformer = DataTransformer(x_train, augment=self.augment) # Create the searcher and save on disk if not self.searcher: input_shape = x_train.shape[1:] self.searcher_args['n_output_node'] = self.get_n_output_node() self.searcher_args['input_shape'] = input_shape self.searcher_args['path'] = self.path self.searcher_args['metric'] = self.metric self.searcher_args['loss'] = self.loss self.searcher_args['verbose'] = self.verbose searcher = Searcher(**self.searcher_args) self.save_searcher(searcher) self.searcher = True # Divide training data into training and testing data. x_train, x_test, y_train, y_test = train_test_split(x_train, y_train, test_size=min(Constant.VALIDATION_SET_SIZE, int(len(y_train) * 0.2)), random_state=42) # Wrap the data into DataLoaders train_data = self.data_transformer.transform_train(x_train, y_train) test_data = self.data_transformer.transform_test(x_test, y_test) # Save the classifier pickle.dump(self, open(os.path.join(self.path, 'classifier'), 'wb')) pickle_to_file(self, os.path.join(self.path, 'classifier')) if time_limit is None: time_limit = 24 * 60 * 60 start_time = time.time() time_remain = time_limit try: while time_remain > 0: run_searcher_once(train_data, test_data, self.path, int(time_remain)) if len(self.load_searcher().history) >= Constant.MAX_MODEL_NUM: break time_elapsed = time.time() - start_time time_remain = time_limit - time_elapsed # if no search executed during the time_limit, then raise an error if time_remain <= 0: raise TimeoutError except TimeoutError: if len(self.load_searcher().history) == 0: raise TimeoutError("Search Time too short. No model was found during the search time.") elif self.verbose: print('Time is out.') @abstractmethod def get_n_output_node(self): pass def transform_y(self, y_train): return y_train def predict(self, x_test): """Return predict results for the testing data. Args: x_test: An instance of numpy.ndarray containing the testing data. Returns: A numpy.ndarray containing the results. """ if Constant.LIMIT_MEMORY: pass test_loader = self.data_transformer.transform_test(x_test) model = self.load_searcher().load_best_model().produce_model() model.eval() outputs = [] with torch.no_grad(): for index, inputs in enumerate(test_loader): outputs.append(model(inputs).numpy()) output = reduce(lambda x, y: np.concatenate((x, y)), outputs) return self.inverse_transform_y(output) def inverse_transform_y(self, output): return output def evaluate(self, x_test, y_test): """Return the accuracy score between predict value and `y_test`.""" y_predict = self.predict(x_test) return self.metric().compute(y_test, y_predict) def save_searcher(self, searcher): pickle.dump(searcher, open(os.path.join(self.path, 'searcher'), 'wb')) def load_searcher(self): return pickle_from_file(os.path.join(self.path, 'searcher')) def final_fit(self, x_train, y_train, x_test, y_test, trainer_args=None, retrain=False): """Final training after found the best architecture. Args: x_train: A numpy.ndarray of training data. y_train: A numpy.ndarray of training targets. x_test: A numpy.ndarray of testing data. y_test: A numpy.ndarray of testing targets. trainer_args: A dictionary containing the parameters of the ModelTrainer constructor. retrain: A boolean of whether reinitialize the weights of the model. """ if trainer_args is None: trainer_args = {'max_no_improvement_num': 30} y_train = self.transform_y(y_train) y_test = self.transform_y(y_test) train_data = self.data_transformer.transform_train(x_train, y_train) test_data = self.data_transformer.transform_test(x_test, y_test) searcher = self.load_searcher() graph = searcher.load_best_model() if retrain: graph.weighted = False _, _1, graph = train((graph, train_data, test_data, trainer_args, None, self.metric, self.loss, self.verbose)) def get_best_model_id(self): """ Return an integer indicating the id of the best model.""" return self.load_searcher().get_best_model_id() def export_keras_model(self, model_file_name): """ Exports the best Keras model to the given filename. """ self.load_searcher().load_best_model().produce_keras_model().save(model_file_name) def export_autokeras_model(self, model_file_name): """ Creates and Exports the AutoKeras model to the given filename. """ portable_model = PortableImageSupervised(graph=self.load_searcher().load_best_model(), y_encoder=self.y_encoder, data_transformer=self.data_transformer, metric=self.metric, inverse_transform_y_method=self.inverse_transform_y) pickle_to_file(portable_model, model_file_name)
class ImageClassifier: """The image classifier class. It is used for image classification. It searches convolutional neural network architectures for the best configuration for the dataset. Attributes: path: A path to the directory to save the classifier. y_encoder: An instance of OneHotEncoder for y_train (array of categorical labels). verbose: A boolean value indicating the verbosity mode. searcher: An instance of BayesianSearcher. It search different neural architecture to find the best model. searcher_args: A dictionary containing the parameters for the searcher's __init__ function. augment: A boolean value indicating whether the data needs augmentation. """ def __init__(self, verbose=False, path=Constant.DEFAULT_SAVE_PATH, resume=False, searcher_args=None, augment=None): """Initialize the instance. The classifier will be loaded from the files in 'path' if parameter 'resume' is True. Otherwise it would create a new one. Args: verbose: An boolean of whether the search process will be printed to stdout. path: A string. The path to a directory, where the intermediate results are saved. resume: An boolean. If True, the classifier will continue to previous work saved in path. Otherwise, the classifier will start a new search. augment: A boolean value indicating whether the data needs augmentation. """ if searcher_args is None: searcher_args = {} if augment is None: augment = Constant.DATA_AUGMENTATION if has_file(os.path.join(path, 'classifier')) and resume: classifier = pickle_from_file(os.path.join(path, 'classifier')) self.__dict__ = classifier.__dict__ self.path = path else: self.y_encoder = None self.data_transformer = None self.verbose = verbose self.searcher = False self.path = path self.searcher_args = searcher_args self.augment = augment ensure_dir(path) def fit(self, x_train=None, y_train=None, time_limit=None): """Find the best neural architecture and train it. Based on the given dataset, the function will find the best neural architecture for it. The dataset is in numpy.ndarray format. So they training data should be passed through x_train, y_train. Args: x_train: An numpy.ndarray instance contains the training data. y_train: An numpy.ndarray instance contains the label of the training data. time_limit: The time limit for the search in seconds. """ if y_train is None: y_train = [] if x_train is None: x_train = [] x_train = np.array(x_train) y_train = np.array(y_train).flatten() _validate(x_train, y_train) # Transform y_train. if self.y_encoder is None: self.y_encoder = OneHotEncoder() self.y_encoder.fit(y_train) y_train = self.y_encoder.transform(y_train) # Transform x_train if self.data_transformer is None: self.data_transformer = DataTransformer(x_train, augment=self.augment) # Create the searcher and save on disk if not self.searcher: input_shape = x_train.shape[1:] n_classes = self.y_encoder.n_classes self.searcher_args['n_classes'] = n_classes self.searcher_args['input_shape'] = input_shape self.searcher_args['path'] = self.path self.searcher_args['verbose'] = self.verbose searcher = BayesianSearcher(**self.searcher_args) self.save_searcher(searcher) self.searcher = True # Divide training data into training and testing data. x_train, x_test, y_train, y_test = train_test_split( x_train, y_train, test_size=min(Constant.VALIDATION_SET_SIZE, int(len(y_train) * 0.2)), random_state=42) train_data = self.data_transformer.transform_train(x_train, y_train) test_data = self.data_transformer.transform_test(x_test, y_test) pickle.dump(self, open(os.path.join(self.path, 'classifier'), 'wb')) pickle_to_file(self, os.path.join(self.path, 'classifier')) if time_limit is None: time_limit = 24 * 60 * 60 start_time = time.time() while time.time() - start_time <= time_limit: run_searcher_once(train_data, test_data, self.path) if len(self.load_searcher().history) >= Constant.MAX_MODEL_NUM: break def predict(self, x_test): """Return predict result for the testing data. Args: x_test: An instance of numpy.ndarray contains the testing data. Returns: An numpy.ndarray containing the results. """ if Constant.LIMIT_MEMORY: pass test_data = self.data_transformer.transform_test(x_test) test_loader = DataLoader(test_data, batch_size=Constant.MAX_BATCH_SIZE, shuffle=False) model = self.load_searcher().load_best_model().produce_model() model.eval() outputs = [] with torch.no_grad(): for index, inputs in enumerate(test_loader): outputs.append(model(inputs).numpy()) output = reduce(lambda x, y: np.concatenate((x, y)), outputs) return self.y_encoder.inverse_transform(output) def evaluate(self, x_test, y_test): """Return the accuracy score between predict value and test_y.""" y_predict = self.predict(x_test) return accuracy_score(y_test, y_predict) def save_searcher(self, searcher): pickle.dump(searcher, open(os.path.join(self.path, 'searcher'), 'wb')) def load_searcher(self): return pickle_from_file(os.path.join(self.path, 'searcher')) def final_fit(self, x_train, y_train, x_test, y_test, trainer_args=None, retrain=False): """Final training after found the best architecture. Args: x_train: An numpy.ndarray of training data. y_train: An numpy.ndarray of training targets. x_test: An numpy.ndarray of testing data. y_test: An numpy.ndarray of testing targets. trainer_args: A dictionary containing the parameters of the ModelTrainer constructure. retrain: A boolean of whether reinitialize the weights of the model. """ if trainer_args is None: trainer_args = {} y_train = self.y_encoder.transform(y_train) y_test = self.y_encoder.transform(y_test) train_data = self.data_transformer.transform_train(x_train, y_train) test_data = self.data_transformer.transform_test(x_test, y_test) searcher = self.load_searcher() graph = searcher.load_best_model() if retrain: graph.weighted = False _, _1, graph = train( (graph, train_data, test_data, trainer_args, None, self.verbose)) def get_best_model_id(self): """ Returns: An integer. The best model id. """ return self.load_searcher().get_best_model_id()
class DCGAN(Unsupervised): """ Deep Convolution Generative Adversary Network """ def __init__(self, nz=100, ngf=32, ndf=32, nc=3, verbose=False, gen_training_result=None, augment=Constant.DATA_AUGMENTATION): """ Args: nz: size of the latent z vector ngf: of gen filters in first conv layer ndf: of discrim filters in first conv layer nc: number of input chanel verbose: A boolean of whether the search process will be printed to stdout. gen_training_result: A tuple of (path, size) to denote where to output the intermediate result with size augment: A boolean value indicating whether the data needs augmentation. """ super().__init__(verbose) self.nz = nz self.ngf = ngf self.ndf = ndf self.nc = nc self.verbose = verbose self.gen_training_result = gen_training_result self.augment = augment self.data_transformer = None self.net_d = Discriminator(self.nc, self.ndf) self.net_g = Generator(self.nc, self.nz, self.ngf) def fit(self, x_train): """ Train only Args: x_train: ndarray contained the training data Returns: """ # input size stay the same, enable cudnn optimization cudnn.benchmark = True self.data_transformer = DataTransformer(x_train, augment=self.augment) train_dataloader = self.data_transformer.transform_train(x_train) GANModelTrainer(self.net_g, self.net_d, train_dataloader, binary_classification_loss, self.verbose, self.gen_training_result).train_model() def generate(self, input_sample=None): if input_sample is None: input_sample = torch.randn(self.gen_training_result[1], self.nz, 1, 1, device=get_device()) if not isinstance(input_sample, torch.Tensor) and \ isinstance(input_sample, np.ndarray): input_sample = torch.from_numpy(input_sample) if not isinstance(input_sample, torch.Tensor) and \ not isinstance(input_sample, np.ndarray): raise TypeError( "Input should be a torch.tensor or a numpy.ndarray") self.net_g.eval() with torch.no_grad(): generated_fake = self.net_g(input_sample) vutils.save_image(generated_fake.detach(), '%s/evaluation.png' % self.gen_training_result[0], normalize=True)
from autokeras.preprocessor import OneHotEncoder, DataTransformer from autokeras.utils import ModelTrainer if __name__ == '__main__': (x_train, y_train), (x_test, y_test) = cifar10.load_data() print('Start Encoding') encoder = OneHotEncoder() encoder.fit(y_train) y_train = encoder.transform(y_train) y_test = encoder.transform(y_test) data_transformer = DataTransformer(x_train, augment=True) train_data = data_transformer.transform_train(x_train, y_train) test_data = data_transformer.transform_test(x_test, y_test) print('Start Generating') graphs = [DefaultClassifierGenerator(10, x_train.shape[1:]).generate()] keras_model = graphs[0].produce_model() print('Start Training') loss, acc = ModelTrainer(keras_model, train_data, test_data, True).train_model(max_no_improvement_num=100, batch_size=128) print(loss, acc)
def get_classification_train_data_loaders(): x_train = np.random.rand(200, 32, 32, 3) data_transformer = DataTransformer(x_train, augment=True) train_data = data_transformer.transform_train(x_train) return train_data