如何使用 Tensorflow Federated 中的多个功能构建模型?
How to build a model using multiple features in Tensorflow Federated?
我在尝试为多个特征输入(即特征 a-g)和一个标签 h 创建 OrderedDict 时遇到以下代码和问题。
def preprocess(dataset):
def batch_format_fn(element):
return collections.OrderedDict(
x=collections.OrderedDict(
a=tf.TensorSpec(shape=[None,], dtype=tf.int32),
b=tf.TensorSpec(shape=[None,], dtype=tf.int32),
c=tf.TensorSpec(shape=[None,], dtype=tf.int32),
d=tf.TensorSpec(shape=[None,], dtype=tf.int32),
e=tf.TensorSpec(shape=[None,], dtype=tf.int32),
f=tf.TensorSpec(shape=[None,], dtype=tf.int32),
g=tf.TensorSpec(shape=[None,], dtype=tf.int32)),
y=tf.TensorSpec(shape=[None,], dtype=tf.int32))
return dataset.map(batch_format_fn).prefetch(PREFETCH_BUFFER)
preprocessed_sample_dataset = preprocess(example_dataset)
def create_keras_model():
model = Sequential([
feature_layer,
Dense(64, activation='relu'),
Dense(64, activation='relu'),
Dense(3, activation='softmax') #classification 3 outputs
])
return model
def model_fn():
keras_model = create_keras_model()
return tff.learning.from_keras_model(
keras_model,
input_spec=preprocessed_sample_dataset.element_spec,
loss=losses.SparseCategoricalCrossentropy(),
metrics=[metrics.SparseCategoricalAccuracy()])
执行时出现这样的错误input_spec=preprocessed_sample_dataset.element_spec
:
TypeError: Unsupported return value from function passed to Dataset.map(): OrderedDict([('x', OrderedDict([('a', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('b', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('c', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('d', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('e', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('f', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('g', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])), ('y', TensorSpec(shape=(None,), dtype=tf.int32, name=None))]).
我已阅读此备选方案 ,但不清楚如何在我的案例中实施它。因此,如何为 TFF 中的多个特征正确分配有序字典?
当前example_dataset.element_spec如下:
OrderedDict([
('a', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('b', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('c', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('d', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('e', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('f', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('g', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('y', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])
我希望element_spec变成这样:
OrderedDict([('x', OrderedDict([
('a', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('b', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('c', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('d', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('e', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('f', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('g', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])),
('y', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])
如何使用batch_format_fn使element_spec成为后者?
batch_format_fn
当前 return 是张量 类型 的结构; tf.data.Dataset.map
期望接收一个 tensors 的结构作为函数的 return 值。
我们应该更新 batch_format_fn
以重新格式化它的 element
参数,而不是 return。让我们尝试类似的东西:
def batch_format_fn(element):
feature_dict = collections.OrderedDict(
a=element['a'],
b=element['b'],
c=element['c'],
d=element['d'],
e=element['e'],
f=element['f'],
g=element['g'],
)
return collections.OrderedDict(x=feature_dict, y=element['y'])
并保持其他一切不变。
我在尝试为多个特征输入(即特征 a-g)和一个标签 h 创建 OrderedDict 时遇到以下代码和问题。
def preprocess(dataset):
def batch_format_fn(element):
return collections.OrderedDict(
x=collections.OrderedDict(
a=tf.TensorSpec(shape=[None,], dtype=tf.int32),
b=tf.TensorSpec(shape=[None,], dtype=tf.int32),
c=tf.TensorSpec(shape=[None,], dtype=tf.int32),
d=tf.TensorSpec(shape=[None,], dtype=tf.int32),
e=tf.TensorSpec(shape=[None,], dtype=tf.int32),
f=tf.TensorSpec(shape=[None,], dtype=tf.int32),
g=tf.TensorSpec(shape=[None,], dtype=tf.int32)),
y=tf.TensorSpec(shape=[None,], dtype=tf.int32))
return dataset.map(batch_format_fn).prefetch(PREFETCH_BUFFER)
preprocessed_sample_dataset = preprocess(example_dataset)
def create_keras_model():
model = Sequential([
feature_layer,
Dense(64, activation='relu'),
Dense(64, activation='relu'),
Dense(3, activation='softmax') #classification 3 outputs
])
return model
def model_fn():
keras_model = create_keras_model()
return tff.learning.from_keras_model(
keras_model,
input_spec=preprocessed_sample_dataset.element_spec,
loss=losses.SparseCategoricalCrossentropy(),
metrics=[metrics.SparseCategoricalAccuracy()])
执行时出现这样的错误input_spec=preprocessed_sample_dataset.element_spec
:
TypeError: Unsupported return value from function passed to Dataset.map(): OrderedDict([('x', OrderedDict([('a', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('b', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('c', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('d', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('e', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('f', TensorSpec(shape=(None,), dtype=tf.int32, name=None)), ('g', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])), ('y', TensorSpec(shape=(None,), dtype=tf.int32, name=None))]).
我已阅读此备选方案
当前example_dataset.element_spec如下:
OrderedDict([
('a', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('b', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('c', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('d', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('e', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('f', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('g', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('y', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])
我希望element_spec变成这样:
OrderedDict([('x', OrderedDict([
('a', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('b', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('c', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('d', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('e', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('f', TensorSpec(shape=(None,), dtype=tf.int32, name=None)),
('g', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])),
('y', TensorSpec(shape=(None,), dtype=tf.int32, name=None))])
如何使用batch_format_fn使element_spec成为后者?
batch_format_fn
当前 return 是张量 类型 的结构; tf.data.Dataset.map
期望接收一个 tensors 的结构作为函数的 return 值。
我们应该更新 batch_format_fn
以重新格式化它的 element
参数,而不是 return。让我们尝试类似的东西:
def batch_format_fn(element):
feature_dict = collections.OrderedDict(
a=element['a'],
b=element['b'],
c=element['c'],
d=element['d'],
e=element['e'],
f=element['f'],
g=element['g'],
)
return collections.OrderedDict(x=feature_dict, y=element['y'])
并保持其他一切不变。