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

2020-10-20 Thread Yao Wang via Apache TVM Discuss
Yes weight layout transformation should be optimized by constant folding. --- [Visit Topic](https://discuss.tvm.apache.org/t/how-dose-tvm-elimitate-calls-of-conv-weights-layout-transform/8208/5) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from

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

2020-10-19 Thread Yao Wang via Apache TVM Discuss
If original model layout is NCHW and you convert to NHWC in TVM, at least two layout transformation are required: one at the beginning and one at the end. --- [Visit Topic](https://discuss.tvm.apache.org/t/how-dose-tvm-elimitate-calls-of-conv-weights-layout-transform/8208/3) to respond.