ArmNN only supports SSDMobileNet via the TFLite parser, not the TFParser. However, the SSDMobileNet mAP accuracy score is very low on ArmNN, compared to running the same model in native Python TensorFlowLite, which scores an expected value. There are two open issues on Arm's GitHub repo for ArmNN addressing this issue:
ArmNN only supports SSDMobileNet via the TFLite parser, not the TFParser. However, the SSDMobileNet mAP accuracy score is very low on ArmNN, compared to running the same model in native Python TensorFlowLite, which scores an expected value. There are two open issues on Arm's GitHub repo for ArmNN addressing this issue:
MLMark is awaiting resolution on these issues to update the target in a V1.0.x release.