Keras 自定义层 - NotImplementedError：无法将符号张量转换为 numpy 数组

Question

我在 keras 中创建了一个自定义层，它获取 (N, 3) 个顶点张量作为输入。因为我的层应该学习这些顶点的嵌入，所以我想用顶点的随机投影来初始化权重。我试图这样做：

class CustomLayer(Layer):
    def __init__(self, feat_dims,  **kwargs):
        super(CustomLayer, self).__init__(**kwargs)
        self.feat_dims = feat_dims
        self.embeddings = None
        self.first = True

    def build(self, input_shape):
        _, nvertex, k = input_shape

    def call(self, inputs, **kwargs):
        vertices = inputs
        _, nvertex, k = inputs.shape
        if self.first:
            q = tf.random.normal((k, self.feat_dims), dtype=tf.dtypes.float32)
            q = tf.transpose(tf.linalg.pinv(q))
            scale = tf.math.sqrt(tf.cast(k, tf.dtypes.float32))
            projection_m = scale * q
            projected_verts = tf.tensordot(vertices, projection_m, axes=1)
            initializer = lambda x, dtype=np.float: tf.constant(projected_verts, dtype=dtype)
            self.embeddings = self.add_weight(name="vertex_embedding", shape=(nvertex, self.feat_dims),
                                              initializer=initializer, trainable=True)
            self.first = False

    def get_config(self):
        config = {'feat_dims': self.feat_dims}

        base_config = super(CustomLayer, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

但 Keras 声明 NotImplementedError: Cannot convert a symbolic Tensor (custom_layer/strided_slice:0) to a numpy array.。这是由projected_verts 引起的，具体取决于输入（符号张量）。 （我使用 call 方法，因为我无法访问 build() 中的顶点）

有什么办法可以规避这个问题吗？我需要维护顶点之间的关系以便更好地初始化。

编辑，堆栈跟踪中的相关部分：

NotImplementedError: in user code:

/home/.../layers.py:5744 call  *
    initializer = lambda x, dtype=np.float: tf.constant(projected_verts, dtype=dtype)
/home/.../python3.8/site-packages/tensorflow/python/framework/constant_op.py:264 constant  **
    return _constant_impl(value, dtype, shape, name, verify_shape=False,
/home/.../python3.8/site-packages/tensorflow/python/framework/constant_op.py:276 _constant_impl
    return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
/home/.../python3.8/site-packages/tensorflow/python/framework/constant_op.py:301 _constant_eager_impl
    t = convert_to_eager_tensor(value, ctx, dtype)
/home/.../python3.8/site-packages/tensorflow/python/framework/constant_op.py:98 convert_to_eager_tensor
    return ops.EagerTensor(value, ctx.device_name, dtype)
/home/.../python3.8/site-packages/tensorflow/python/framework/ops.py:867 __array__
    raise NotImplementedError(

NotImplementedError: Cannot convert a symbolic Tensor (custom_layer/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported

Answer 1

尝试将projected_verts 显式转换为张量

initializer = lambda x, dtype=tf.dtypes.float32 : tf.convert_to_tensor(projected_verts)

而不是使用tf.constant。请注意，我还将np.float 替换为tf.dtypes.float32。