Hi,
I am a beginer for tvm. I compile the model for vgg19 and visualize it by netron.  <br> *The original model is just conv->relu->pooling->...* <br> I know tvm do some operator fusions. But I don't know why the optimized model has p0, p1, ... nodes and they do not contain any input data. Does anyone know why we have these nodes? Thanks! --- [Visit Topic](https://discuss.tvm.ai/t/a-problem-for-the-optimized-model/6878/1) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/1aa91cd5cbdbf3c56ff2cfb71f9321af8e82bf8e43bdd301616155ea204eb1bd).