Cannot convert a symbolic Tensor to a numpy array

使用TF进行计算，出现：

Traceback (most recent call last):
  File "infer.py", line 14, in <module>
    logits = classifier.get_output_for(image, None)
  File "/opt/stylegan2/dnnlib/tflib/network.py", line 219, in get_output_for
    expr = tf.zeros([tf.shape(valid_inputs[0])[0]] + shape[1:], name=name)
  File "/opt/AN/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line 2338, in zeros
    output = _constant_if_small(zero, shape, dtype, name)
  File "/opt/AN/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line 2295, in _constant_if_small
    if np.prod(shape) < 1000:
  File "<__array_function__ internals>", line 6, in prod
  File "/opt/AN/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 3031, in prod
    keepdims=keepdims, initial=initial, where=where)
  File "/opt/AN/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 87, in _wrapreduction
    return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
  File "/opt/AN/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 736, in __array__
    " array.".format(self.name))
NotImplementedError: Cannot convert a symbolic Tensor (celebahq-classifier-20-goatee_1/strided_slice:0) to a numpy array.

解决方式，降低版本numpy版本

pip install numpy==1.19.5