Question

有没有办法在自定义Keras损失函数内重塑TF张量？我为卷积神经网络定义了这个自定义丢失函数？

def custom_loss(x, x_hat):
    """
    Custom loss function for training background extraction networks (autoencoders)
    """

    #flatten x, x_hat before computing mean, median
    shape = x_hat.get_shape().as_list()
    batch_size = shape[0]
    image_size = np.prod(shape[1:])

    x = tf.reshape(x, [batch_size, image_size])
    x_hat = tf.reshape(x_hat, [batch_size, image_size]) 

    B0 = reduce_median(tf.transpose(x_hat))
    # I divide by sigma in the next step. So I add a small float32 to F0
    # so as to prevent sigma from becoming 0 or Nan.

    F0 = tf.abs(x_hat - B0) + 1e-10

    sigma = tf.reduce_mean(tf.sqrt(F0 / 0.5), axis=0)

    background_term = tf.reduce_mean(F0 / sigma, axis=-1)

    bce = binary_crossentropy(x, x_hat)

    loss = bce + background_term 

    return loss

除了计算标准binary_crossentropy之外，还会在损失中添加额外的background_term。该术语激励网络预测图像接近批次的中位数。由于CNN的输出为2d且reduce_median对于1d阵列效果更好，因此我必须将图像重新整形为1d阵列。当我尝试训练这个网络时，我收到了错误

Traceback (most recent call last):
  File "stackoverflow.py", line 162, in <module>
    autoencoder = build_conv_autoencoder(lambda_W, input_shape, num_filters, optimizer, custom_loss)
  File "stackoverflow.py", line 136, in build_conv_autoencoder
    autoencoder.compile(optimizer, loss, metrics=[mean_squared_error])
  File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 594, in compile
    **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 667, in compile
    sample_weight, mask)
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 318, in weighted
    score_array = fn(y_true, y_pred)
  File "stackoverflow.py", line 26, in custom_loss
    x = tf.reshape(x, [batch_size, image_size])
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2448, in reshape
    name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 494, in apply_op
    raise err
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 491, in apply_op
    preferred_dtype=default_dtype)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 710, in internal_convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 176, in _constant_tensor_conversion_function
    return constant(v, dtype=dtype, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 165, in constant
    tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 441, in make_tensor_proto
    tensor_proto.string_val.extend([compat.as_bytes(x) for x in proto_values])
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 441, in <listcomp>
    tensor_proto.string_val.extend([compat.as_bytes(x) for x in proto_values])
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/compat.py", line 65, in as_bytes
    (bytes_or_text,))
TypeError: Expected binary or unicode string, got None

在TensorFlow图实例化之前，似乎Keras正在调用custom_loss。这使batch_size无，而不是实际值。有没有一种正确的方法来重塑损失函数内的张量，避免这种错误？您可以查看完整代码here。

Answer 1

是否有适当的方法来重塑张量...

如果您使用的是Keras，则应使用K.reshape(x,shape)方法，这是tf.reshape(x,shape)的包装，我们可以在docs中看到。

我还注意到你正在使用get_shape()来获得张量形状，在Keras上你可以使用K.int_shape(x)中的shape = K.int_shape(x_hat)执行此操作，如下所示：

tf.abs()

除此之外，还有其他一些操作直接调用Tensorflow导入，而不是Keras后端（如tf.reduce_mean()，tf.transpose()，TypeError等）。您应该考虑在keras后端使用其相应的包装器来使用统一的符号并保证更常规的行为。此外，通过使用Keras后端，您可以使您的程序兼容Theano和Tensorflow，因此这是您应该考虑的一大优势。

此外，在处理具有未定义维度的张量时，可能会出现一些x = tf.reshape(x, [-1, image_size])。请查看docs，了解有关重新定义尺寸未定义的张量的问题。另外，对于Keras中的等价物，请检查this question问题，在答案中我解释了如何使用带有Tensorflow的Keras作为后端来实现这一点。

...现在关于你的代码。基本上，由于您有一些未定义的维度，您可以传递值-1以使其推断形状，无论其大小如何（在第一个链接问题中进行了解释，但也可以在{{3}中看到） }）。类似的东西：

x = K.reshape(x, [-1, image_size])

或使用Keras后端：

{{1}}

重塑Keras损失函数内的TensorFlow张量？

1 个答案: