environment version:
ubuntu 18.04 aarch64
jetpack jetson-nano-jp451-sd-card-image
jetbot v0.4.3
tensorflow 2.4.0+nv21.3
tensorrt 7.1.3.0
torch 1.6.0
torchvision 0.7.0a0+78ed10c
setuptools 49.6.0
model version:
ssd_mobilenet_v2_coco.engine v0.4 (latest)
command:
from jetbot import ObjectDetector
from jetbot import Camera
model = ObjectDetector(‘ssd_mobilenet_v2_coco.engine’)
camera = Camera.instance(width=300, height=300)
detections = model.value(camera.value)
print(detections)
error information:
[TensorRT] ERROR: coreReadArchive.cpp (38) - Serialization Error in verifyHeader: 0 (Version tag does not match)
[TensorRT] ERROR: INVALID_STATE: std::exception
[TensorRT] ERROR: INVALID_CONFIG: Deserialize the cuda engine failed.
Traceback (most recent call last):
File “object_follow.py”, line 4, in
model = ObjectDetector(‘ssd_mobilenet_v2_coco.engine’)
File “/usr/local/lib/python3.6/dist-packages/jetbot-0.4.3-py3.6.egg/jetbot/object_detection.py”, line 29, in init
output_names=[TRT_OUTPUT_NAME, TRT_OUTPUT_NAME + ‘_1’])
File “/usr/local/lib/python3.6/dist-packages/jetbot-0.4.3-py3.6.egg/jetbot/tensorrt_model.py”, line 59, in init
self.context = self.engine.create_execution_context()
AttributeError: ‘NoneType’ object has no attribute ‘create_execution_context’