TypeError: Expected tensorflow.python.framework.tensor_spec.TensorSpec, found numpy.ndarray

Question

当我想从 TFF 0.12.0 迁移到 TFF 0.18.0 时出现以下错误，知道我有一个图像数据集，这是我的 sample_batch

images, labels = next(img_gen.flow_from_directory(path0,target_size=(224, 224), batch_size=2))
sample_batch = (images,labels)
...

def model_fn():

  keras_model = create_keras_model()
  return tff.learning.from_keras_model(
      keras_model,
      input_spec=sample_batch,
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])

那么我该如何修改我的 sample_batch 以使其与这个版本相符呢？请帮忙！！谢谢

Answer 1

版本 0.13.0 the sample_batch parameter was deprecated. The input_spec parameter must be a tff.Type or tf.TensorSpec as per the documentation。

从 numpy.ndarray 构建 tf.TensorSpec 的结构：

def tensor_spec_from_ndarray(a):
  return tf.TensorSpec(dtype=tf.dtypes.as_dtype(a.dtype),
                       shape=a.shape)

sample_batch = (images,labels)  # assumes images and labels are np.ndarray
input_spec = tf.nest.map_structure(
  tensor_spec_from_ndarray, sample_batch)

TypeError: Expected tensorflow.python.framework.tensor_spec.TensorSpec, found numpy.ndarray

TypeError: Expected tensorflow.python.framework.tensor_spec.TensorSpec, found numpy.ndarray

tensorflow-federated