Pre-trained Mask-RCNN model has no weights

[ianormy]

My understanding of a pre-trained model is that it will not only contain the structure but also the weights. However, the Mask-RCNN pre-trained model you provide does not contain any weights:

import onnx
from onnx import numpy_helper

model = onnx.load('MaskRCNN-10.onnx')
init = model.graph.initializer
print("There are {} weights in the model.".format(len(init)))