rnn_model_training.py File Reference

Namespaces
namespace	rnn_model_training

Variables
	rnn_model_training.parser = argparse.ArgumentParser()
	rnn_model_training.help
	rnn_model_training.type
	rnn_model_training.required
	rnn_model_training.default
	rnn_model_training.args = parser.parse_args()
x	rnn_model_training.f = lambda x[: args.max_letters]
	rnn_model_training.df
	rnn_model_training.axis
	rnn_model_training.how
	rnn_model_training.inplace
	rnn_model_training.columns
	rnn_model_training.indexNames = df[df['state'].str.len() < args.min_letters].index
	rnn_model_training.vocabulary = list('abcdefghiABCDEFGHIrstuvwxyzRSTUVWXYZ1234567890,.+*')
dict	rnn_model_training.int_of_letters = {}
	rnn_model_training.vocabulary_size = len(int_of_letters)
int	rnn_model_training.features_per_sample = 1
	rnn_model_training.x_data = df['state'].to_numpy()
	rnn_model_training.y_data = df['label'].to_numpy()
	rnn_model_training.max_length_of_outtupple = max([len(sublist) for sublist in df.state.to_list()])
	rnn_model_training.padded_x_data
	rnn_model_training.train_x_data = padded_x_data
	rnn_model_training.train_y_data = y_data
	rnn_model_training.num_outtuples = train_x_data.shape[0]
	rnn_model_training.timesteps = max_length_of_outtupple
tuple	rnn_model_training.input_shape = (timesteps, features_per_sample)
	rnn_model_training.model = tf.keras.models.Sequential()
	rnn_model_training.loss = history.history['loss']
	rnn_model_training.optimizer
	rnn_model_training.metrics
	rnn_model_training.history
	rnn_model_training.model_file
	rnn_model_training.overwrite
	rnn_model_training.acc = history.history['accuracy']
	rnn_model_training.val_acc = history.history['val_accuracy']
	rnn_model_training.val_loss = history.history['val_loss']
	rnn_model_training.epochs = range(1, len(acc) + 1)
	rnn_model_training.label