[Apache TVM Discuss] [Questions] AutoTVM vs AutoScheduler tuning metrics

I have same questions. Also I'm confused about the log format generated by AutoSchedule, it's total different with AutoTVM --- [Visit Topic](https://discuss.tvm.apache.org/t/autotvm-vs-autoscheduler-tuning-metrics/10300/2) to respond. You are receiving this because you enabled mailing li

[Apache TVM Discuss] [Questions] How dose TVM elimitate calls of conv weights layout_transform?

Thanks for the reply Kevin! Those two layout trans make sense, but for filter parameters, they're loaded from .pth with OIHW by default(relay/frontend/pytorch.py) and I set desired_layout for HWIO. Will these filter parameters be transformed in advanced or by a cuda kernel in each inference?

[Apache TVM Discuss] [Questions] How dose TVM elimitate calls of conv weights layout_transform?

After reading these two links: [https://discuss.tvm.apache.org/t/layout-conversion-pass/4009/15](https://tvm.apache.org/docs/dev/convert_layout.html) [https://tvm.apache.org/docs/dev/convert_layout.html](https://tvm.apache.org/docs/dev/convert_layout.html) I'm still confused that

[Apache TVM Discuss] [Questions] How dose TVM elimitate calls of conv weights layout_transform?

Hi everyone! I modified this sample(https://tvm.apache.org/docs/tutorials/frontend/from_pytorch.html) to add desired_layout NHWC to the network saved from pytorch(which uses NCHW): ```python desired_layouts = {'qnn.conv2d': ['NHWC', 'HWIO'], 'nn.conv2d': ['NHWC', 'HWIO