当试图为多个特征输入(即特性a)和一个标签h创建OrderedDict时,我有以下代码和问题。
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()])它显示了在执行input_spec=preprocessed_sample_dataset.element_spec时出现这样一个错误
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))]).我读过这个替代的solution,但是在我的例子中还不清楚如何实现它。因此,如何正确地为TFF中的多个特性分配有序的dict?
当前的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element_spec作为后一种使用batch_format_fn?
发布于 2020-07-16 04:50:16
batch_format_fn当前返回张量类型的结构;tf.data.Dataset.map期望接收作为函数返回值的张量结构。
我们应该更新batch_format_fn以重新格式化它的element参数并返回它。让我们试一试如下:
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'])让其他一切保持不变。
https://stackoverflow.com/questions/62893523
复制相似问题