def main():
params1 = {'m' : 1000,
'n_a' : 32,
'n_s' : 64,
'Tx' : 30, # Max length of input
'Ty' : 10 # o/p length "YYYY-MM-DD"
}
dataset, human_vocab, machine_vocab, inv_machine_vocab = nmt.load_dataset(params1['m'])
X, Y, Xoh, Yoh = nmt.preprocess_data(dataset, human_vocab, machine_vocab, params1['Tx'], params1['Ty'])
params2 = {'machine_vocab_size' : len(machine_vocab),
'human_vocab_size' : len(human_vocab)}
params = {**params1, **params2}
hparams = {'lr' : 0.005,
'beta_1' : 0.9,
'beta_2' : 0.999,
'decay' : 0.01}
vocab = {'human_vocab' : human_vocab,
'machine_vocab' : machine_vocab,
'inv_machine_vocab' : inv_machine_vocab}
# Defined shared layers as global variables
global repeator, concatenator, densor1, densor2, activator, dotor, encoder
encoder = Bidirectional(LSTM(params['n_a'], return_sequences=True))
repeator = RepeatVector(params['Tx'])
concatenator = Concatenate(axis=-1)
densor1 = Dense(10, activation = "tanh")
densor2 = Dense(1, activation = "relu")
activator = Activation(nmt.softmax, name='attention_weights') # We are using a custom softmax(axis = 1) loaded from nmt_utils
dotor = Dot(axes = 1)
model, _ = myModel(Xoh, Yoh, **params, **hparams)
model.load_weights('models/coursera_model.h5')
return model, params, vocab
parser = argparse.ArgumentParser(
description='Either train or evaluate attn model for normalizing dates.')
parser.add_argument('-m',
'--mode',
type=str,
required=True,
choices=['train', 'eval'],
help="pick mode; either train or eval")
args = parser.parse_args()
# We'll train the model on a dataset of 10000 human readable dates
# and their equivalent, standardized, machine readable dates.
nb_samples = 10000
dataset, human_vocab, machine_vocab, inv_machine_vocab = load_dataset(
nb_samples)
print('Human vocab', human_vocab)
print('Machine vocab', machine_vocab)
print('Inverse machine vocab', inv_machine_vocab)
X, Y = zip(*dataset)
X, Y, _, _ = preprocess_data(dataset, human_vocab, machine_vocab,
seq_len_human, seq_len_machine)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
encoder_rnn = EncoderRNN(EMBEDDING_DIM_PRE_ATTN, HIDDEN_DIM_PRE_ATTN_LSTM,
len(human_vocab)).to(device)
attn_decoder_rnn = AttnDecoderRNN(HIDDEN_DIM_POST_ATTN_LSTM,
len(machine_vocab)).to(device)
def main():
m = 10000
dataset, human_vocab, machine_vocab, inv_machine_vocab = load_dataset(m)
Tx = 30
Ty = 10
X, Y, Xoh, Yoh = preprocess_data(dataset, human_vocab, machine_vocab, Tx,
Ty)
if DO_TEST: test(human_vocab, X, Y, Xoh, Yoh, dataset)
# Defined shared layers as global variables
repeator = RepeatVector(Tx)
concatenator = Concatenate(axis=-1)
densor = Dense(1, activation="relu")
activator = Activation(
softmax, name='attention_weights'
) # We are using a custom softmax(axis = 1) loaded in this notebook
dotor = Dot(axes=1)
def my_one_step_attention(
a, s_prev
): # this way we fix layers without recreating them, and can pass the fct as arg
return one_step_attention(a, s_prev, repeator, concatenator, densor,
dotor, activator)
n_a = 64
n_s = 128
post_activation_LSTM_cell = LSTM(n_s, return_state=True)
output_layer = Dense(len(machine_vocab), activation=softmax)
model = create_model(Tx, Ty, n_a, n_s, len(human_vocab),
my_one_step_attention, post_activation_LSTM_cell,
output_layer)
model.summary()
### START CODE HERE ### (≈2 lines)
opt = Adam(lr=0.005, beta_1=0.9, beta_2=0.999, decay=0.01)
model.compile(optimizer=opt,
loss="categorical_crossentropy",
metrics=["accuracy"])
### END CODE HERE ###
s0 = np.zeros((m, n_s))
c0 = np.zeros((m, n_s))
outputs = list(Yoh.swapaxes(0, 1))
#model.fit([Xoh, s0, c0], outputs, epochs=1, batch_size=100)
model.fit([Xoh, s0, c0], outputs, epochs=25, batch_size=256)
EXAMPLES = [
'3 May 1979', '5 April 09', '21th of August 2016', 'Tue 10 Jul 2007',
'Saturday May 9 2018', 'March 3 2001', 'March 3rd 2001',
'1 March 2001', '5 March 09', '5 April 09', '05 April 2009'
]
for example in EXAMPLES:
# below: version of notebook, using Keras 2.0.7
# source = string_to_int(example, Tx, human_vocab)
# source = np.array(list(map(lambda x: to_categorical(x, num_classes=len(human_vocab)), source))).swapaxes(0, 1)
# below: locl version, using Keras 2.1.3
source = string_to_int(example, Tx, human_vocab)
source = np.array(
list(
map(lambda x: to_categorical(x, num_classes=len(human_vocab)),
source)))
# .swapaxes(0,1) remove the swap axes call
# Add an additional dimension as axes 0
source = np.expand_dims(source, axis=0)
prediction = model.predict([source, s0, c0])
prediction = np.argmax(prediction, axis=-1)
output = [inv_machine_vocab[int(i)] for i in prediction]
print("source:", example)
print("output:", ''.join(output))
def main(save=True, save_dir=os.getcwd(), load_model=None):
"""
Arguments:
save : save model after training to directory
save_dir: save trained models to this directory if not provided will save in current working directory
return: trained/ loaded model, parameters of models, vocbulary
"""
global model, params, vocab
params1 = {
'm': 1000,
'n_a': 32,
'n_s': 64,
'Tx': 30, # Max length of input
'Ty': 10 # o/p length "YYYY-MM-DD"
}
dataset, human_vocab, machine_vocab, inv_machine_vocab = nmt_utils.load_dataset(
params1['m'])
X, Y, Xoh, Yoh = nmt_utils.preprocess_data(dataset, human_vocab,
machine_vocab, params1['Tx'],
params1['Ty'])
params2 = {
'machine_vocab_size': len(machine_vocab),
'human_vocab_size': len(human_vocab)
}
params = {**params1, **params2}
hparams = {'lr': 0.005, 'beta_1': 0.9, 'beta_2': 0.999, 'decay': 0.01}
vocab = {
'human_vocab': human_vocab,
'machine_vocab': machine_vocab,
'inv_machine_vocab': inv_machine_vocab
}
# Defined shared layers as global variables
global repeator, concatenator, densor1, densor2, activator, dotor
repeator = RepeatVector(params['Tx'])
concatenator = Concatenate(axis=-1)
densor1 = Dense(10, activation="tanh")
densor2 = Dense(1, activation="relu")
activator = Activation(
nmt_utils.softmax, name='attention_weights'
) # We are using a custom softmax(axis = 1) loaded from nmt_utils_utils
dotor = Dot(axes=1)
if save:
model, _ = myModel(Xoh, Yoh, **params, **hparams)
print("Saving weights...")
model.save_weights(os.path.join(save_dir, 'date_model_epoch1.h5'))
print("Weight Saved!")
else:
if load_model == None:
raise FileNotFoundError(
'Please provide valid model path along with model name!')
else:
model = create_model(**params)
print("loading pretrained weights...")
model.load_weights('models/date_model_epoch15.h5')
print("date_model_epoch15.h5 weights loaded!!")
return model, params, vocab
from faker import Faker
import random
from tqdm import tqdm
from babel.dates import format_date
from nmt_utils import load_dataset, preprocess_data, string_to_int, to_categorical
from pyt_model import Attn
import torch.optim as optim
import torch
import torch.nn as nn
# We'll train the model on a dataset of 10000 human readable dates
# and their equivalent, standardized, machine readable dates.
m = 10000
dataset, human_vocab, machine_vocab, inv_machine_vocab = load_dataset(m)
# X: a processed version of the human readable dates in the training set,
# where each character is replaced by an index mapped to the character via human_vocab.
# Each date is further padded to $T_x$ values with a special character (< pad >). X.shape = (m, Tx)
# Y: a processed version of the machine readable dates in the training set,
# where each character is replaced by the index it is mapped to in machine_vocab.
# You should have Y.shape = (m, Ty).
# Xoh: one-hot version of X, the "1" entry's index is mapped to the character thanks
# to human_vocab. Xoh.shape = (m, Tx, len(human_vocab))
# Yoh: one-hot version of Y, the "1" entry's index is mapped to the character thanks to machine_vocab.
# Yoh.shape = (m, Tx, len(machine_vocab)).
# Here, len(machine_vocab) = 11 since there are 11 characters ('-' as well as 0-9).