def train():
# load training dataset (6K)
filename = 'Flickr_8k.trainImages.txt'
train = util.load_ids(filename)
print('Dataset: %d' % len(train))
train_captions = util.load_clean_captions('descriptions.txt', train)
print('Captions: train number=%d' % len(train_captions))
# photo features
train_features = util.load_photo_features('features.pkl', train)
print('Photos: train=%d' % len(train_features))
# prepare tokenizer
tokenizer = load(open('tokenizer.pkl', 'rb'))
vocab_size = len(tokenizer.word_index) + 1
print('Vocabulary Size: %d' % vocab_size)
# determine the maximum sequence length
max_len = util.get_max_length(train_captions)
print('Description Length: %d' % max_len)
# define the model
model = caption_model(vocab_size, max_len)
# train the model, run epochs manually and save after each epoch
epochs = 20
steps = len(train_captions)
for i in range(epochs):
# create the data generator
generator = data_generator(train_captions, train_features, tokenizer, max_len)
# fit for one epoch
model.fit_generator(generator, epochs=1, steps_per_epoch=steps, verbose=1)
# save model
model.save('model_' + str(i) + '.h5')
def train():
# load training dataset (6K)
filename = 'Flickr_8k.trainImages.txt'
train = util.load_ids(filename)
print('Dataset: %d' % len(train))
train_captions = util.load_clean_captions('descriptions.txt', train)
print('Captions: train number=%d' % len(train_captions))
# photo features
train_features = util.load_photo_features('features.pkl', train)
print('Photos: train=%d' % len(train_features))
# prepare tokenizer
tokenizer = load(open('tokenizer.pkl', 'rb'))
vocab_size = len(tokenizer.word_index) + 1
print('Vocabulary Size: %d' % vocab_size)
# determine the maximum sequence length
max_len = util.get_max_length(train_captions)
print('Description Length: %d' % max_len)
# define the model
model = caption_model(vocab_size, max_len)
# train the model, run epochs manually and save after each epoch
epochs = 5
steps = len(train_captions)
for i in range(epochs):
# create the data generator
generator = data_generator(train_captions, train_features, tokenizer,
max_len)
# fit for one epoch
# generator just return two dimenstion data, the first means X, which has two data
# first is the featur of the pic, second is the surfix words; second means Y, the
# word of predict for Next.
# At first I don't kown why generator will return three value(feature, surfix, the next word)
# but the model just has two input, later I got first tow means X and will go into the model,
# the third is means Y, the reponse variance.
# Don't need fear the generator will be executed forever, for the super-parameter epoches & steps_per_epoch
# has limited the time of invoking generator, which is epochs * steps_per_epoch
# Generator, is magical!
model.fit_generator(generator,
epochs=1,
steps_per_epoch=steps,
verbose=1)
# save model
model.save('model' + os.sep + 'model_my' + str(i) + '.h5')
def prepare_data(pronunciations, letter_ids):
logging.info('preparing the data...')
max_length = util.get_max_length(pronunciations)
X = np.zeros((len(pronunciations), max_length, len(letter_ids)),
dtype=bool)
y = np.zeros(len(pronunciations), dtype=int)
for n, word in enumerate(pronunciations):
for i, letter in enumerate(word):
letter_id = letter_ids[letter]
X[n, i, letter_id] = True
y[n] = len(pronunciations[word])
return X, y
def __init__(self, model: Model, pronunciations, letter_ids):
self.model = model
self.pronunciations = pronunciations
self.letter_ids = letter_ids
max_len = util.get_max_length(pronunciations.values())
self.max_len = max_len
# 'startseq Two women laying on grass with a dog . endseq',
# 'startseq Two women on a grassy hill lit by the sun ; one looks at a dachshund , the other looks to the side . endseq']
# photo features
feature_path = r"E:/AI资源计算机视觉/JM07 - TXXY - CV2期/02.资料/homework-master-7fc833414b95225130c323c278230bc388af5c6b/homework1/features.pkl"
train_features = util.load_photo_features(feature_path, train)
# print('Photos: train=%d' % len(train_features))
# print(len(train_features["3585117340_73e96b6173"][0])) # 4096
# prepare tokenizer
tokenizer = load(open('tokenizer.pkl', 'rb'))
vocab_size = len(tokenizer.word_index) + 1 # 词汇表大小
print('Vocabulary Size: %d' % vocab_size) # 7378
# determine the maximum sequence length
max_len = util.get_max_length(train_captions)
print('Description Length: %d' % max_len) # 40
# define the model
model = caption_model(vocab_size, max_len)
print(model)
# train the model, run epochs manually and save after each epoch
epochs = 20
steps = len(train_captions) # 6000
for i in range(epochs):
# create the data generator
generator = data_generator(train_captions, train_features, tokenizer,
max_len)
# print(generator)
# fit for one epoch
model.fit_generator(generator,
# ---------- Data Load ----------
x_paths = {}
t_paths = {}
dataset = {}
loader = {}
for type_ in types:
print('Loading %s dataset ... ' % (type_), end='')
x_paths[type_] = glob(join(data_dir, 'x_' + type_, '*.bin'))
t_paths[type_] = glob(join(data_dir, 't_' + type_, '*.bin'))
x_dim = config.get_feature_config().get_linguistic_dim(type_)
t_dim = config.get_feature_config().get_parm_dim(type_)
max_len = get_max_length(x_paths[type_], x_dim)
pad_value = config.get_feature_config().pad_value
dataset[type_] = SpeechDataset(x_paths[type_],
t_paths[type_],
x_dim=x_dim,
t_dim=t_dim,
max_len=max_len,
pad_value=pad_value)
batch_size = config.get_train_config().batch_size
loader[type_] = DataLoader(dataset[type_],
batch_size=batch_size,
shuffle=True)
print('done!')
print('\tDataset Size\t%d' % (len(x_paths[type_])))
print('\tInput Dim\t%d' % (x_dim))