[5] register aten ops in lite interpreter for detectron2go model (#35248)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/35248
register aten ops in lite interpreter for detectron2go models. Also set catchAllKernel for some ops since the model requires different DispatchKey.
(Note: this ignores all push blocking failures!)
Test Plan:
(whole stack)
buck build -c user.ndk_cxxflags='-g1' -c caffe2.expose_op_to_c10=1 //xplat/caffe2/fb/pytorch_predictor:maskrcnnAndroid#android-armv7
Reviewed By: iseeyuan
Differential Revision: D20528762
fbshipit-source-id: 4da4699fe547a63b0c664fe666a8a688f1ab8c6c
