def _get_keras_model(self) -> models.Model:
I = layers.Input(shape=(KerasCNNModel.MAX_SEQUENCE_LENGTH, 300),
dtype='float32',
name='comment_text')
# Convolutional Layers
X = I
for filter_size in self.hparams().filter_sizes:
X = layers.Conv1D(self.hparams().num_filters,
filter_size,
activation='relu',
padding='same')(X)
X = layers.GlobalAveragePooling1D()(X)
# Dense
for num_units in self.hparams().dense_units:
X = layers.Dense(num_units, activation='relu')(X)
X = layers.Dropout(self.hparams().dropout_rate)(X)
# Outputs
outputs = []
for label in self._labels:
outputs.append(
layers.Dense(1, activation='sigmoid', name=label)(X))
model = models.Model(inputs=I, outputs=outputs)
model.compile(
optimizer=optimizers.Adam(lr=self.hparams().learning_rate),
loss='binary_crossentropy',
metrics=['binary_accuracy', super().roc_auc])
tf.logging.info(model.summary())
return model
def __init__(self, channel, reduction=16):
super().__init__()
self.fc = Sequential()
self.fc.add(layers.GlobalAveragePooling1D())
self.fc.add(layers.Dense(channel // reduction, activation='relu'))
self.fc.add(layers.Dense(channel))
self.fc.add(layers.Activation('sigmoid'))
def _model_fn(self, features, labels, mode, params, config):
embedding = tf.Variable(tf.truncated_normal(
[256, params.embedding_size]),
name='char_embedding')
texts = features[base_model.TEXT_FEATURE_KEY]
batch_size = tf.shape(texts)[0]
byte_ids = tf.reshape(
tf.cast(
tf.decode_raw(
tf.sparse_tensor_to_dense(tf.string_split(texts, ''),
default_value='\0'), tf.uint8),
tf.int32), [batch_size, -1])
padded_ids = tf.slice(
tf.concat([
byte_ids,
tf.zeros([batch_size, params.string_len], tf.int32)
],
axis=1), [0, 0], [batch_size, params.string_len])
inputs = tf.nn.embedding_lookup(params=embedding, ids=padded_ids)
# Conv
X = inputs
for filter_size in params.filter_sizes:
X = layers.Conv1D(params.num_filters,
filter_size,
activation='relu',
padding='same')(X)
if params.pooling_type == 'average':
X = layers.GlobalAveragePooling1D()(X)
elif params.pooling_type == 'max':
X = layers.GlobalMaxPooling1D()(X)
else:
raise ValueError('Unrecognized pooling type parameter')
# FC
logits = X
for num_units in params.dense_units:
logits = tf.layers.dense(inputs=logits,
units=num_units,
activation=tf.nn.relu)
logits = tf.layers.dropout(logits, rate=params.dropout_rate)
logits = tf.layers.dense(inputs=logits,
units=len(self._target_labels),
activation=None)
output_heads = [
tf.contrib.estimator.binary_classification_head(name=name)
for name in self._target_labels
]
multihead = tf.contrib.estimator.multi_head(output_heads)
optimizer = tf.train.AdamOptimizer(learning_rate=params.learning_rate)
return multihead.create_estimator_spec(features=features,
labels=labels,
mode=mode,
logits=logits,
optimizer=optimizer)
def __init__(self):
super(Model, self).__init__()
self.main = tf.keras.Sequential([
layers.Embedding(vocab_size, embedding_dim, input_length=maxlen),
layers.GlobalAveragePooling1D(),
layers.Dense(16, activation=tf.nn.relu),
layers.Dense(1, activation=tf.nn.sigmoid)
])
def __init__(self, vocab_size, embedding_size, max_sentence_len):
self.vocab_size = vocab_size
self.embedding_size = embedding_size
# create model
self.model = models.Sequential()
self.model.add(
layers.Embedding(vocab_size, embedding_size, max_sentence_len))
self.model.add(layers.GlobalAveragePooling1D())
self.model.add(layers.Dense(units=1, activation='sigmoid'))
# 损失和优化器选择
self.model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
self.model.summary()
def _model_fn(self, features, labels, mode, params, config):
inputs = features[base_model.TOKENS_FEATURE_KEY]
batch_size = tf.shape(inputs)[0]
# Conv
X = inputs
for filter_size in params.filter_sizes:
X = layers.Conv1D(params.num_filters,
filter_size,
activation='relu',
padding='same')(X)
if params.pooling_type == 'average':
X = layers.GlobalAveragePooling1D()(X)
elif params.pooling_type == 'max':
X = layers.GlobalMaxPooling1D()(X)
else:
raise ValueError('Unrecognized pooling type parameter')
# FC
logits = X
for num_units in params.dense_units:
logits = tf.layers.dense(inputs=logits,
units=num_units,
activation=tf.nn.relu)
logits = tf.layers.dropout(logits, rate=params.dropout_rate)
logits = tf.layers.dense(inputs=logits,
units=len(self._target_labels),
activation=None)
output_heads = [
tf.contrib.estimator.binary_classification_head(name=name)
for name in self._target_labels
]
multihead = tf.contrib.estimator.multi_head(output_heads)
optimizer = tf.train.AdamOptimizer(learning_rate=params.learning_rate)
return multihead.create_estimator_spec(features=features,
labels=labels,
mode=mode,
logits=logits,
optimizer=optimizer)
test_data, value=word_index['<PAD>'], padding='post', maxlen=maxlen)
print(train_data[0])
# 创建一个简单的模型
'''
1:第一层是嵌入层。这一层使用整数编码的词汇表，并为每个单词索引查找嵌入向量。这些向量作为模型火车来学习。这些向量向输出数组添加一个维度。得到的维度是:'(批量、顺序、嵌入)' '。
2:接下来，GlobalAveragePooling1D层通过对序列维数进行平均，为每个示例返回一个固定长度的输出向量。这允许模型以最简单的方式处理可变长度的输入。
3:这个固定长度的输出向量通过一个有16个隐藏单元的全连接(密集)层来传输。
4:最后一层与单个输出节点紧密连接。使用sigmoid激活函数，这个值是0到1之间的浮点数，表示评审结果为正的概率(或置信水平)。
'''
embedding_dim = 16
model = keras.Sequential([
layers.Embedding(vocab_size, embedding_dim, input_length=maxlen),
layers.GlobalAveragePooling1D(),
layers.Dense(16, activation='relu'),
layers.Dense(1, activation='sigmoid')
])
model.summary()
# 编译和训练模型
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
history = model.fit(train_data,
train_labels,
epochs=30,
batch_size=512,
To dive more in-depth into the differences between the Functional API and Model subclassing, you can read [What are Symbolic and Imperative APIs in TensorFlow 2.0?](https://medium.com/tensorflow/what-are-symbolic-and-imperative-apis-in-tensorflow-2-0-dfccecb01021).
## Mix-and-matching different API styles
Importantly, choosing between the Functional API or Model subclassing isn't a binary decision that restricts you to one category of models. All models in the tf.keras API can interact with each, whether they're Sequential models, Functional models, or subclassed Models/Layers written from scratch.
You can always use a Functional model or Sequential model as part of a subclassed Model/Layer:
"""
units = 32
timesteps = 10
input_dim = 5
# Define a Functional model
inputs = keras.Input((None, units))
x = layers.GlobalAveragePooling1D()(inputs)
outputs = layers.Dense(1, activation='sigmoid')(x)
model = keras.Model(inputs, outputs)
class CustomRNN(layers.Layer):
def __init__(self):
super(CustomRNN, self).__init__()
self.units = units
self.projection_1 = layers.Dense(units=units, activation='tanh')
self.projection_2 = layers.Dense(units=units, activation='tanh')
# Our previously-defined Functional model
self.classifier = model
def call(self, inputs):
outputs = []