Not able to deploy int8 engine file

When attempting to deploy the resnet18_detector.trt.int8 model using DetectNet_v2 on an EC2 instance with thw following command:

!sed -i “s|/workspace/tao-experiments/data/training|/workspace/tao-experiments/data/training/image_2|g”

!tao deploy detectnet_v2 gen_trt_engine
-m $USER_EXPERIMENT_DIR/experiment_dir_final/resnet18_detector.onnx
–data_type int8
–batches 10
–batch_size 4
–max_batch_size 64
–engine_file $USER_EXPERIMENT_DIR/experiment_dir_final/resnet18_detector.trt.int8
–cal_cache_file $USER_EXPERIMENT_DIR/experiment_dir_final/calibration.bin
-e $SPECS_DIR/detectnet_v2_retrain_resnet18_kitti.txt
–results_dir $USER_EXPERIMENT_DIR/experiment_dir_final

!sed -i “s|/workspace/tao-experiments/data/training/image_2|/workspace/tao-experiments/data/training|g” $LOCAL_SPECS_DIR/detectnet_v2_retrain_resnet18_kitti.txt

I encountered the following issue:
ouput_log.txt (1.2 MB)

Please try to set lower max_batch_size. For example, --max_batch_size 4.
I am afraid the error is due to out-of-memory.

After changing the max_batch size I got the same error.
output_log.txt (1.5 MB)

The error as Error while converting .etlt model to .trt model - #9 by Morganh.
Please try to generate tensorrt engine against the unpruned onnx file.

I don’t have an unpruned onnx file. The unpruded weights output is in hdf5.

You can export the unpruned hdf5 file to onnx file as well.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.