[Apache TVM Discuss] [Development] [VTA] Bringing depthwise convolution support

[Mengbo Z via Apache TVM Discuss <no...@discuss.tvm.ai>]

@liangfu @suvadeep 
I was recently trying to deploy the network on an FPGA using VTA, but I ran into this problem when deploying mobilenetV2. When executing nn.conv2d, I set groups to the following format:
```
groups = int(in_planes/16)
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, groups=groups ,stride=stride ,padding=1, bias=False)
```
Although such setting can be achieved, the final result is inconsistent with the result obtained by software training. I don't know why such a result occurs. Have you tried to implement Mobilenet and verified the correctness of the result?





---
[Visit Topic](https://discuss.tvm.apache.org/t/vta-bringing-depthwise-convolution-support/5742/4) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/fe776f5b085e363fb7c52c1a2dfefb9f083bdc0331ef98722e97bc1430c3c205).