Closed daquexian closed 6 years ago
Please try these steps changes:
cd third-party/NNPACK && git pull origin master
, cd third-party/cpuinfo && git pull origin master
).--caffe2_profile_nnpack true
and post the results of the convolution.protoc --decode caffe2.NetDef /path/to/caffe2/proto/caffe2.proto -I /path/to/caffe2/proto < predict_net.pb > predict_net.pbtxt
@Maratyszcza Updating NNPACK and cpuinfo to latest solves this problem, Thanks!
Thanks, this is helpful. I'll update the submodules in pytorch/pytorch repo to make sure this problem doesn't reoccur.
The model is a faster-rcnn-MobileNetV2-FPN model which contains many depthwise convolutions, what's more I modify the convolution in "detection head" of faster-rcnn to depthwise convolution. I'm using caffe2 with detectron ops so that I can run FPN models on Android. :)
Without NNPACK:
With NNPACK:
The result without NNPACK is right, for it is the same with that producing by GPU.
I didn't modify the code when switching between NNPACK and non-NNPACK, and the faster-rcnn-ResNet-50-FPN model works correctly with NNPACK.
My phone is Google Pixel (arm64-v8a) with Android 8.1. I can provide a minimal project and my model if you need.
BTW, I don't know how to use NNPACK with Caffe2 on PC. So I haven't tested it on PC :)