I have got the .so .paramers and .json,but the module which I use autotuing even slower than the module I didn’t use autotuing.Is the way I import it wrong?please help me
Did you uncomment the tune_and_evaluate function call in the tutorial?
yes，i did，and i got this output
so I think I made a mistake in import the model which used autotuing. I’m new to ai,I dont know how to import the new module
Is it available to post your script? It’s hard to locate the problem from your screenshots.
In addition, the tuning space size for your renset-18 looks weird to me. For example, Task 1 only has 400 candidates. What’s your input shapes?
Thank you for replying me. I just change some part of the tutorials’code.
The tutorial is "“Compile PyTorch Models”:https://tvm.apache.org/docs/tutorials/frontend/from_pytorch.html#sphx-glr-tutorials-frontend-from-pytorch-py
I change the part which named “Execute the portable graph on TVM” into the code I sent before.
I dont know is this code correct to import the module which has used autotuing.I use these to load
While the autotuing code I used is " Auto-tuning a convolutional network for x86 CPU".: https://tvm.apache.org/docs/tutorials/autotvm/tune_relay_x86.html#sphx-glr-tutorials-autotvm-tune-relay-x86-py And I uncomment the tune-and-evaluate，then add these code to get .json,.so and .params files.
