import argparse import numpy as np import tensorflow as tf import tqdm from data_providers import QuickDrawImageDataProvider from network_builder import ClassifierNetworkGraph from utils.parser_utils import ParserClass from utils.storage import build_experiment_folder, save_statistics tf.reset_default_graph() # resets any previous graphs to clear memory parser = argparse.ArgumentParser( description='Welcome to CNN experiments script' ) # generates an argument parser parser_extractor = ParserClass( parser=parser) # creates a parser class to process the parsed input batch_size, seed, epochs, logs_path, continue_from_epoch, tensorboard_enable, batch_norm, \ strided_dim_reduction, experiment_prefix, dropout_rate_value, rnn_dropout_rate_value, layer_stage_sizes, \ rnn_cell_type, bidirectional, rnn_stage_sizes, conv_rnn_sizes, num_classes_use, inner_layer_depth, \ filter_size, num_dense_layers, num_dense_units, network_name, rotate = parser_extractor.get_argument_variables() # returns a list of objects that contain our parsed input convnet_desc = "" if batch_norm: convnet_desc = convnet_desc + "BN" for ls in layer_stage_sizes: convnet_desc = "{}_{}".format(convnet_desc, ls) if network_name == 'fcn': experiment_name = "exp{}_{}_{}_layers".format(experiment_prefix,
import argparse import numpy as np import tensorflow as tf import tqdm from data_providers import CIFAR10DataProvider from network_builder import ClassifierNetworkGraph from utils.parser_utils import ParserClass from utils.storage import build_experiment_folder, save_statistics tf.reset_default_graph() # resets any previous graphs to clear memory parser = argparse.ArgumentParser( description='Welcome to CNN experiments script' ) # generates an argument parser parser_extractor = ParserClass( parser=parser) # creates a parser class to process the parsed input batch_size, seed, epochs, logs_path, continue_from_epoch, tensorboard_enable, batch_norm, \ strided_dim_reduction, experiment_prefix, dropout_rate_value = parser_extractor.get_argument_variables() # returns a list of objects that contain # our parsed input experiment_name = "experiment_{}_batch_size_{}_bn_{}_mp_{}".format( experiment_prefix, batch_size, batch_norm, strided_dim_reduction) # generate experiment name rng = np.random.RandomState(seed=seed) # set seed train_data = CIFAR10DataProvider(which_set="train", batch_size=batch_size, rng=rng) val_data = CIFAR10DataProvider(which_set="valid",
vocab = {} words = [] PADWORD = 'PADDING' vocab[PADWORD] = 0 words.append(PADWORD) for word, index in vocab_processor.vocabulary_._mapping.items(): vocab[word] = index + 1 words.append(word) return vocab, words tf.reset_default_graph() # resets any previous graphs to clear memory parser = argparse.ArgumentParser( description='Welcome to CNN experiments script' ) # generates an argument parser parser_extractor = ParserClass( parser=parser) # creates a parser class to process the parsed input batch_size, seed, epochs, logs_path, continue_from_epoch, tensorboard_enable, embedding_dim, \ filter_sizes, num_filters, experiment_prefix, dropout_rate_value, pt_embeddings, static_embeddings, \ l2_norm, activation, typec, cell, hidden_unit, num_units = parser_extractor.get_argument_variables() # returns a list of objects that contain # our parsed input experiment_name = "experiment_{}_batch_size_{}_ptembed_{}".format( experiment_prefix, batch_size, pt_embeddings) # generate experiment name rng = np.random.RandomState(seed=seed) # set seed train_data = TwitterDataProvider(which_set="train",