There is no torch.nonzero in my torch model, but a nonzero error is reported when I convert the model to a TensorRT engine. Which torch operations may cause nonzero problems, or how can I find out which operators contain nonzero operations?
There is no torch.nonzero in my torch model, but a nonzero error is reported when I convert the model to a TensorRT engine. Which torch operations may cause nonzero problems, or how can I find out which operators contain nonzero operations?