Open lewis-bo opened 1 year ago
Are you using force-implicit-batch-dim=1
in the config_infer_primary_yoloV8.txt
file?
yes,
net-scale-factor=0.0039215697906911373
model-color-format=0
network-input-order=0 onnx-file=plate.onnx model-engine-file=model_b16_dla1_int8.engine int8-calib-file=cabli.table labelfile-path=labels.txt batch-size=16
network-mode=1 num-detected-classes=1 interval=0 gie-unique-id=1
process-mode=1
network-type=0 cluster-mode=2 maintain-aspect-ratio=1 symmetric-padding=1 force-implicit-batch-dim=1 workspace-size=1000 enable-dla=1 use-dla-core=0 parse-bbox-func-name=NvDsInferParseYolo
custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so engine-create-func-name=NvDsInferYoloCudaEngineGet
I think it's not working well yet. Please comment it and try again.
I think it's not working well yet. Please comment it and try again.
It work when I change 'force-implicit-batch-dim=1' to 'force-implicit-batch-dim=0'
I think it's need to change the network shape to force the implicit batch. I will some tests soon.
I hava another question about dynamic batch。
I converted yolov5s.onnx to an int8 type engine and set the maximum batch to 16. But when I run it, whether it's with one input or multiple inputs or 1b or 16b, it's very slow. max fps < 20
To use force-implicit-batch-dim=1
you to export the model with --batch 1
(example for batch-size 1) instead the --dynamic
.
I converted yolov5s.onnx to an int8 type engine and set the maximum batch to 16. But when I run it, whether it's with one input or multiple inputs or 1b or 16b, it's very slow. max fps < 20.
The batch-size is related to the number of sources on DeepStream. How is the FPS with FP16?
sorry so late to reply, you mean use --batch when export onnx model
Only if you aren't using --dynamic
on the export command. The --batch
should be the same of the batch-size
you are using.
env: DS6.2, CUDA11.4.315
Jetpack:5.1.1
onnx: python3 export_yoloV5.py -w vehicle.pt -s 640 --simplify --dynamic
when I run "deepstream-app -c deepstream_app_config.txt" , I get this error