Model inference on Image File run into Numpy Error

[theclassroam]

I ran the following script and encounter a Numpy error:

from doctr.io import DocumentFile
from doctr.models import ocr_predictor

model = ocr_predictor(pretrained=True)
doc = DocumentFile.from_images("test.png")
result = model(doc)

Got this error:

    906 if isinstance(tensor, ops.EagerTensor):
    907   return tensor_shape.TensorShape(
--> 908       [dim if dim != -1 else None for dim in tensor.numpy()])
    910 if tensor.get_shape().ndims == 0:
    911   value = constant_value(tensor)
`ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()`