将TensorFlow张量转换为Numpy数组

我正在尝试在TensorFlow 2.3.0中编写自定义损失函数.要计算损失，我需要将y_pred参数转换为numpy数组.但是，即使似乎有TensorFlow函数也无法将其从<class 'tensorflow.python.framework.ops.Tensor'>转换为numpy数组.

I am trying to write a custom loss function in TensorFlow 2.3.0. To calculate the loss, I need the y_pred parameter to be converted to a numpy array. However, I can't find a way to convert it from <class 'tensorflow.python.framework.ops.Tensor'> to numpy array, even though there seem to TensorFlow functions to do so.

def custom_loss(y_true, y_pred):
    print(type(y_pred))
    npa = y_pred.make_ndarray()
    ...
    

if __name__ == '__main__':
    ...
    model.compile(loss=custom_loss, optimizer="adam")
    model.fit(x=train_data, y=train_data, epochs=10)

给出错误消息:AttributeError: 'Tensor' object has no attribute 'make_ndarray 在打印y_pred参数的类型后:<class 'tensorflow.python.framework.ops.Tensor'>

gives the error message: AttributeError: 'Tensor' object has no attribute 'make_ndarray after printing the type of the y_pred parameter: <class 'tensorflow.python.framework.ops.Tensor'>

寻找解决方案时，我发现这似乎是一个普遍的问题，并且有一些建议，但到目前为止它们对我没有用:

Looking for a solution I found this seems to be a common issue and there a couple of suggestions, but they did not work for me so far:

1. " ...因此只需在Tensor对象上调用.numpy().":如何转换张量到TensorFlow中的一个numpy数组中?

1. " ... so just call .numpy() on the Tensor object.": How can I convert a tensor into a numpy array in TensorFlow?

所以我尝试了:

def custom_loss(y_true, y_pred):
    npa = y_pred.numpy()
    ...

给我AttributeError: 'Tensor' object has no attribute 'numpy'

2. 使用tensorflow.Tensor.eval()将张量转换为数组":

2. "Use tensorflow.Tensor.eval() to convert a tensor to an array": How to convert a TensorFlow tensor to a NumPy array in Python

所以我尝试了:

def custom_loss(y_true, y_pred):
    npa = y_pred.eval(session=tf.compat.v1.Session())
    ...

为我提供了我见过的最长的错误消息之一，其核心是:

giving me one of the longest trace of error messages I ever have seen with the core being:

InvalidArgumentError: 2 root error(s) found.
      (0) Invalid argument: You must feed a value for placeholder tensor 'functional_1/conv2d_2/BiasAdd/ReadVariableOp/resource' with dtype resource
         [[node functional_1/conv2d_2/BiasAdd/ReadVariableOp/resource (defined at main.py:303) ]]
         [[functional_1/cropping2d/strided_slice/_1]]
      (1) Invalid argument: You must feed a value for placeholder tensor 'functional_1/conv2d_2/BiasAdd/ReadVariableOp/resource' with dtype resource
         [[node functional_1/conv2d_2/BiasAdd/ReadVariableOp/resource (defined at main.py:303) ]]

还必须从版本1.x调用TensorFlow兼容性函数感觉不太适应未来，因此无论如何我都不太喜欢这种方法.

also having to call TensorFlow Compatibility Functions from Version 1.x does not feel very future-proof, so I do not like this approach too much anyhow.

3.看着TensorFlow文档，似乎只有我需要等待的功能: tf.make_ndarray 从张量创建一个numpy ndarray.

3. Looking at the TensorFlow Docs there seemed to be the function I needed just waiting: tf.make_ndarray Create a numpy ndarray from a tensor.

所以我尝试了:

def custom_loss(y_true, y_pred):
    npa = tf.make_ndarray(y_pred)
    ...

给我AttributeError: 'Tensor' object has no attribute 'tensor_shape'

查看TF文档中的示例，他们在proto_tensor上使用了此示例，因此我尝试先转换为proto:

Looking at the example in the TF documentation they use this on a proto_tensor, so I tried converting to a proto first:

def custom_loss(y_true, y_pred):
    proto_tensor = tf.make_tensor_proto(y_pred)
    npa = tf.make_ndarray(proto_tensor)
    ...

，但tf.make_tensor_proto(y_pred)已经引发错误:TypeError: Expected any non-tensor type, got a tensor instead.

也尝试首先创建一个常数张量会产生相同的错误:

Also trying to make a const tensor first gives the same error:

def custom_loss(y_true, y_pred):
    a = tf.constant(y_pred)
    proto_tensor = tf.make_tensor_proto(a)
    npa = tf.make_ndarray(proto_tensor)
    ...

关于此的更多文章，但似乎它们都回到了这三个基本概念上.期待您的建议！

There are many more posts around this but it seems they are all coming back to these three basic ideas. Looking forward to your suggestions!