SageMaker Neo Compilation - Unable to Neo Compile for FP16 and INT8 precision

0

I'm trying to Neo compile a Pytorch YoloV5 Large model for edge deployment on an Nvidia Jetson Xavier NX device. I'm able to do it using the default settings for FP32 precision but I'm unable to do it for FP16 or INT8 precision. I have tried passing it in "CompilerOptions" in the OutputConfig but the output of Neo compilation is still FP32.

How can I get a Neo compiled model for for FP16 and INT8 precision? Does Neo support these precision modes or not?

質問済み 2年前240ビュー
1回答
0

Unfortunately Neo doesn't support quantization for Jetson Devices. It means you can only compile FP32 models and they will be FP32 after compilation.

I know this is not what you're looking for, but FYI, Neo supports int8 model optimization only for TFLite and targeting CPU not GPU. Check here some supported models: https://docs.amazonaws.cn/en_us/sagemaker/latest/dg/neo-supported-edge-tested-models.html

AWS
回答済み 2年前

ログインしていません。 ログイン 回答を投稿する。

優れた回答とは、質問に明確に答え、建設的なフィードバックを提供し、質問者の専門分野におけるスキルの向上を促すものです。

質問に答えるためのガイドライン

関連するコンテンツ