def tf2_estimator():
from zoo.orca.learn.tf2.estimator import Estimator
# import ray
init_orca_context(cluster_mode="local", cores=4, memory="3g")
print("running tf2 estimator")
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=1000)
# print(train_data)
word_index = imdb.get_word_index()
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2 # unknown
word_index["<UNUSED>"] = 3
train_data = keras.preprocessing.sequence.pad_sequences(train_data, value=word_index["<PAD>"], padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data, value=word_index["<PAD>"], padding='post',
maxlen=256)
model = keras.Sequential()
model.add(keras.layers.Embedding(1000, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['acc'])
x_val = train_data[:1000]
partial_x_train = train_data[1000:]
y_val = train_labels[:1000]
partial_y_train = train_labels[1000:]
train_dataset = tf.data.Dataset.from_tensor_slices((partial_x_train, partial_y_train))
validation_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
est = Estimator.from_keras(model_creator=model)
est.fit(data=train_dataset, batch_size=512, epochs=100, validation_data=validation_dataset)
results = est.evaluate(validation_dataset)
print(results)
est.save('work/saved_model')
est.get_train_summary(tag='Loss')
est.get_validation_summary(tag='Top1Accuracy')
stop_orca_context()
def build_word_index(self):
"""
build word index for pad, start and other symbols
:return:
"""
word_index = imdb.get_word_index()
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index['<PAD>'] = 0
word_index['<START>'] = 1
word_index['<UNK>'] = 2
word_index['<UNUSED>'] = 3
self.word_index = word_index
def preprocess_data(self, data_dir):
print('IMDB_Task preprocess_data')
vocab_size = self.configs['vocab_size']
sentence_size = self.configs['max_time']
# we assign the first indices in the vocabulary \
# to special tokens that we use
# for padding, as start token, and for indicating unknown words
pad_id = 0
start_id = 1
oov_id = 2
index_offset = 2
print("Loading data...")
(x_train_variable, y_train), \
(x_test_variable, y_test) = imdb.load_data(
num_words=vocab_size,
start_char=start_id,
oov_char=oov_id,
index_from=index_offset)
print(len(y_train), "train sequences")
print(len(y_test), "test sequences")
print("Pad sequences (samples x time)")
x_train = sequence.pad_sequences(x_train_variable,
maxlen=sentence_size,
truncating='post',
padding='post',
value=pad_id)
x_test = sequence.pad_sequences(x_test_variable,
maxlen=sentence_size,
truncating='post',
padding='post',
value=pad_id)
print("x_train shape:", x_train.shape)
print("x_test shape:", x_test.shape)
x_len_train = np.array([min(len(x), sentence_size) \
for x in x_train_variable])
x_len_test = np.array([min(len(x), sentence_size) \
for x in x_test_variable])
word_index = imdb.get_word_index()
#pdb.set_trace()
return PreProcessedData(x_train=x_train,
y_train=y_train,
x_len_train=x_len_train,
x_test=x_test,
y_test=y_test,
x_len_test=x_len_test,
vocab_size=vocab_size,
word_index = word_index)
def convert2Text(self, pad_id, oov_id, start_id, index_offset):
'''
Description: covert index to text
Usage:
'''
word_index = imdb.get_word_index()
word_inverted_index = {
v + index_offset: k
for k, v in word_index.items()
}
# The first indexes in the map are reserved to represent things other than tokens
word_inverted_index[pad_id] = '<PAD>'
word_inverted_index[start_id] = '<START>'
word_inverted_index[oov_id] = '<OOV>'
for i in range(0, 10):
print(i, word_inverted_index[i])
def index_to_text(indexes):
return ' '.join([word_inverted_index[i] for i in indexes])
print(index_to_text(self.x_train_variable[0]))
truncating='post',
padding='post',
value=pad_id)
print("x_train shape:", x_train.shape)
print("x_test shape:", x_test.shape)
x_len_train = np.array([min(len(x), sentence_size) for x in x_train_variable])
x_len_test = np.array([min(len(x), sentence_size) for x in x_test_variable])
def parser(x, length, y):
features = {"x": x, "len": length}
return features, y
word_index = imdb.get_word_index()
word_inverted_index = {v + index_offset: k for k, v in word_index.items()}
# The first indexes in the map are reserved to represent things other than tokens
word_inverted_index[pad_id] = '<PAD>'
word_inverted_index[start_id] = '<START>'
word_inverted_index[oov_id] = '<OOV>'
for i in range(0, 10):
print(i, word_inverted_index[i])
def index_to_text(indexes):
return ' '.join([word_inverted_index[i] for i in indexes])
print(len(y_train), "train sequences")
print(len(y_test), "test sequences")
print("Pad sequences (samples x time)")
x_train = sequence.pad_sequences(x_train_variable,
maxlen=sentence_size,
padding='post',
value=0)
x_test = sequence.pad_sequences(x_test_variable,
maxlen=sentence_size,
padding='post',
value=0)
print("x_train shape:", x_train.shape)
print("x_test shape:", x_test.shape)
word_index = imdb.get_word_index(os.path.join(project_path, 'data/imdb_word_index.json'))
word_inverted_index = {v: k for k, v in word_index.items()}
# The first indexes in the map are reserved to represet things other than tokens
index_offset = 3
word_inverted_index[-1 - index_offset] = '_' # Padding at the end
word_inverted_index[ 1 - index_offset] = '>' # Start of the sentence
word_inverted_index[ 2 - index_offset] = '?' # OOV
word_inverted_index[ 3 - index_offset] = '' # Un-used
x_len_train = np.array([min(len(x), sentence_size) for x in x_train_variable])
x_len_test = np.array([min(len(x), sentence_size) for x in x_test_variable])
embedding_matrix = load_glove_embeddings('data/glove.6B.50d.txt', word_index, vocab_size, embedding_size)
def tf_estimator():
from zoo.orca.learn.tf.estimator import Estimator
init_orca_context(cluster_mode="local", cores=4, memory="3g")
os.environ["HDF5_USE_FILE_LOCKING"] = 'FALSE'
print("running tf estimator")
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=1000)
# print(train_data)
word_index = imdb.get_word_index()
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2 # unknown
word_index["<UNUSED>"] = 3
train_data = keras.preprocessing.sequence.pad_sequences(train_data, value=word_index["<PAD>"], padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data, value=word_index["<PAD>"], padding='post',
maxlen=256)
model = keras.Sequential()
model.add(keras.layers.Embedding(1000, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['acc'])
x_val = train_data[:1000]
partial_x_train = train_data[1000:]
y_val = train_labels[:1000]
partial_y_train = train_labels[1000:]
train_dataset = tf.data.Dataset.from_tensor_slices((partial_x_train, partial_y_train))
validation_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
est = Estimator.from_keras(keras_model=model)
est.set_constant_gradient_clipping(0.1, 0.2)
est.fit(data=train_dataset, batch_size=512, epochs=5, validation_data=validation_dataset)
results = est.evaluate(validation_dataset)
print(results)
est.clear_gradient_clipping()
est.set_l2_norm_gradient_clipping(0.1)
est.fit(data=train_dataset, batch_size=512, epochs=5, validation_data=validation_dataset)
results = est.evaluate(validation_dataset)
print(results)
est.save('work/saved_model')
print("save API finished")
# est.save_tf_checkpoint('work/checkpoint')
# est.load_tf_checkpoint('work/checkpoint')
print("checkpoint save and load API finished")
est.save_keras_model('work/keras_model')
est.save_keras_weights('work/keras_weights')
print("keras model and weights save API finished")
# est.load_keras_model('work/keras_model')
# est.load_keras_weights('work')
print("keras model and weights load API finished")
est.get_train_summary(tag='Loss')
est.get_validation_summary(tag='Top1Accuracy')
# Estimator.load(est, model_path='work/') # Has not been implemented
# resutls = est.predict(validation_dataset)
# print(results)
stop_orca_context()
# Trainings und Testdaten werden über Keras geladen
# Alternativ können Sie direkt die Datei als Pikle Datei herunterladen
(x_train, y_train), (x_test,
y_test) = imdb.load_data(path="imdb.npz",
num_words=VOCABULARY_SIZE,
skip_top=0,
maxlen=None,
seed=113,
start_char=START_CHAR,
oov_char=2,
index_from=INDEX_FROM)
# Die Datei wird imdb_word_index.json heruntergeladen
word_to_id = imdb.get_word_index(path="./imdb_word_index.json")
# Hier werden die korrekten Indizes mit dem passenden Wort gespeichert, da es eine Index-Verschiebung von +3 gibt (siehe Erklärung in
# https://keras.io/datasets/#imdb-movie-reviews-sentiment-classification)
# Aus: https://stackoverflow.com/questions/42821330/restore-original-text-from-keras-s-imdb-dataset
word_to_id = {k: (v + INDEX_FROM) for k, v in word_to_id.items()}
word_to_id["<PAD>"] = 0
word_to_id["<START>"] = START_CHAR # 1
word_to_id["<UNK>"] = 2
id_to_word = {value: key for key, value in word_to_id.items()}
# Zeigt den Inhalt einer Rezension (bestimmt durch REVIEW_INDEX)
REVIEW_INDEX = 2
print(x_train[REVIEW_INDEX])
print("---- Rezensionstext --------- ")
print(' '.join(id_to_word[id] for id in x_train[REVIEW_INDEX]))
