explicit batch is required when using the dynamic shapes for inference

Tianxiaomo / pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Apache License 2.0

4.47k stars 1.49k forks source link

explicit batch is required when using the dynamic shapes for inference #431

Open Ongoza opened 3 years ago

Ongoza commented 3 years ago

explicit batch is required when using the dynamic shapes for inference In 5.1 Convert from ONNX of static Batch size command has to be: trtexec --onnx= --saveEngine= --workspace= --fp16