Please provide the following information when requesting support.
• Hardware (T4/V100/Xavier/Nano/etc) : ** x86_64 GPU machine**
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) : ** detectnet_v2
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here) : i can able to run container
• Training spec file(If have, please share here): attached log
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
Hi,
I’m trying to do dataset conversion in tao toolkit. log shows tfrecord generation was successful. But i couldn’t see generated tfrecord files in given result path.
dataset used: PASCAL VOC 2012 dataset → converted to KITTI format → dataset_convert_config file
data_convert_config_spec.txt (409 Bytes)
command: tao detectnet_v2 dataset_convert -v -d /home/soundarrajan/detectnet_v2/config/data_convert_config_spec.txt -o /home/soundarrajan/detectnet_v2/result --log_file /home/soundarrajan/detectnet_v2/result/dataset_convert_log.txt
Output:
dataset_convert_log.txt (4.3 KB)
.tao_mount.json file used:
.tao_mounts.json (491 Bytes)
Actually the command was executed successfully as you can see the attached logs. But i couldn’t able to find the converted .tfrecord file in given output folder -o home/soundarrajan/detectnet_v2/result
In which path the converted .tfrecord will be saved to?
Kindly refer the config file and .tao_mounts.json file i attached, is anything missing in config and help to fix it.