You are viewing a plain text version of this content. The canonical link for it is here.

Posted to discuss-archive@tvm.apache.org by Shengxi Li via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/12 02:33:39 UTC

[Apache TVM Discuss] [Questions] Whether TVM has batch optimization


Run the gpu_imagenet_bench.py script  get the following results:
batchsize=1,  resnet-50            5.54 ms             (1.18 ms)
batchsize=2,  resnet-50            15.28 ms            (1.87 ms)
Why is batch processing set to 2 so slow?





---
[Visit Topic](https://discuss.tvm.apache.org/t/whether-tvm-has-batch-optimization/8142/1) 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/9dafe2078fb5bf60901262ea152e153eac3d4e409d09ae5e3172194adb51aebd).