Hello, has your problem been solved? When I use vta, I will report an error in
graph_pack. How did you solve it? Looking forward to your reply
---
[Visit
Topic](https://discuss.tvm.apache.org/t/mobilenetv2-is-implemented-on-vta-and-nn-conv2d-group-problem/11761/2)
to respond.
You are rec
Hello, have you implemented the deployment of mobilenetv2 on FPGA?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/some-questions-about-mobilenet-and-dcgan-implemented-on-vta/2842/8)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these em
without explicitly setting the threadpool, multiple backend runtime instance
control flow will share a same threadpool and execute the operator sequential,
you can reference this example
https://discuss.tvm.apache.org/t/cpu-affinity-setting-of-pipeline-process-when-using-config-threadpool/121
Hi @SYangDong
Could you provide some code on how you modified the buffers offset?
Thanks!
---
[Visit
Topic](https://discuss.tvm.apache.org/t/double-buffer-schedule-conflict-with-tenorize/1641/10)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe
Can someone tell me different:
1. graph, lib, params = relay.build(xxx)
1. mod = relay.build(xxx)
Three outputs and one output . What's the difference between them, and where do
they apply？Thanks
---
[Visit
Topic](https://discuss.tvm.apache.org/t/question-about-relay-build/12930/1) to
I dropped a `print` statement into the [default AVX x86 conv2d
schedule](https://github.com/apache/tvm/blob/70884e957aa5c8de9c02c25a14d30563d7300cb9/python/tvm/topi/x86/conv2d_avx_common.py#L87),
so I know that this is the schedule that is being run.
To check if there is an int16 fallback, I
