量化模型的时候出现TypeError

[Francis235]

量化模型的时候出现如下错误： Exception has occurred: RuntimeError Op Execution Error: ConstantOfShape_87(Type: ConstantOfShape, Num of Input: 1, Num of Output: 1) File "/root/workspace/ppq/ppq/executor/torch.py", line 536, in __forward outputs = operation_forward_func(operation, inputs, self._executing_context) File "/root/workspace/ppq/ppq/executor/op/torch/default.py", line 1295, in ConstantOfShape_forward output = torch.Tensor().new_full( TypeError: new_full(): argument 'size' must be tuple of ints, but found element of type float at pos 1 输入的onnx模型是可以正常推理无错误的，在使用ppq的quantize_onnx_model api做模型的量化时，会有上述错误报出。有人遇到过类似的情况吗？