Jetson Nano Jetbot ssd_mobilenet_v2_coco.engine has no attribute

Trying to execute the following utilzing the NVIDIA-AI-IOT/jetbot :

from jetbot import ObjectDetector

model = ObjectDetector(‘ssd_mobilenet_v2_coco.engine’)

here’s the error


AttributeError Traceback (most recent call last)
in
1 from jetbot import ObjectDetector
2
----> 3 model = ObjectDetector(‘ssd_mobilenet_v2_coco.engine’)

/usr/local/lib/python3.6/dist-packages/jetbot-0.3.0-py3.6.egg/jetbot/object_detection.py in init(self, engine_path, preprocess_fn)
26 load_plugins()
27 self.trt_model = TRTModel(engine_path, input_names=[TRT_INPUT_NAME],
—> 28 output_names=[TRT_OUTPUT_NAME, TRT_OUTPUT_NAME + ‘_1’])
29 self.preprocess_fn = preprocess_fn
30

/usr/local/lib/python3.6/dist-packages/jetbot-0.3.0-py3.6.egg/jetbot/tensorrt_model.py in init(self, engine_path, input_names, output_names, final_shapes)
57 with open(engine_path, ‘rb’) as f:
58 self.engine = self.runtime.deserialize_cuda_engine(f.read())
—> 59 self.context = self.engine.create_execution_context()
60
61 if input_names is None:

AttributeError: ‘NoneType’ object has no attribute ‘create_execution_context’

Dou you have solved,I have the smae problem as fllow:

[TensorRT] ERROR: Could not compute dimensions for Concatenate/concat, because the network is not valid
Traceback (most recent call last):
File “main_my.py”, line 43, in
buf = engine.serialize()
AttributeError: ‘NoneType’ object has no attribute ‘serialize’

Hi, kingyuluk

Which image do you use?
Please noticed that you will need to use this image to make jetbot model work:
https://github.com/NVIDIA-AI-IOT/jetbot/wiki/software-setup#step-1—flash-jetbot-image-onto-sd-card

The model shared in the GitHub cannot work with TensorRT 5.1 yet.

Thanks

Hi, 452302450

[TensorRT] ERROR: Could not compute dimensions for Concatenate/concat, because the network is not valid

The error indicates that there are some compatible issue on the model architecture, which is different from the kingyuluk.

We always encourage user to file a new topic for their own problem so it can be well-handled.
Could you help us doing so?

Thanks.

Hi,AastaLLL,
thanks very much,the problem has solved,and is different from the kingyuluk exactly,the reason is Compatibility issues。

I have the same AtributeError problem too. Same as the topic indicated. Is there any solution? Thx
I am using Download the expandable JetBot SD card image jetbot_image_v0p4p0.zip

I used the older Jetbot SD card image and the problem is solved.

Hi, I got exactly the same error message:

from jetbot import ObjectDetector
​
model = ObjectDetector('ssd_mobilenet_v2_coco.engine')
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-3-78c468b59bd4> in <module>
      1 from jetbot import ObjectDetector
      2 
----> 3 model = ObjectDetector('ssd_mobilenet_v2_coco.engine')

/usr/local/lib/python3.6/dist-packages/jetbot-0.3.0-py3.6.egg/jetbot/object_detection.py in __init__(self, engine_path, preprocess_fn)
     26         load_plugins()
     27         self.trt_model = TRTModel(engine_path, input_names=[TRT_INPUT_NAME],
---> 28                                   output_names=[TRT_OUTPUT_NAME, TRT_OUTPUT_NAME + '_1'])
     29         self.preprocess_fn = preprocess_fn
     30 

/usr/local/lib/python3.6/dist-packages/jetbot-0.3.0-py3.6.egg/jetbot/tensorrt_model.py in __init__(self, engine_path, input_names, output_names, final_shapes)
     57         with open(engine_path, 'rb') as f:
     58             self.engine = self.runtime.deserialize_cuda_engine(f.read())
---> 59         self.context = self.engine.create_execution_context()
     60 
     61         if input_names is None:

AttributeError: 'NoneType' object has no attribute 'create_execution_context'

I am using JetBot SD card image jetbot_image_v0p4p0.zip and ssd_mobilenet_v2_coco.engine for v0.4 downloaded from https://drive.google.com/open?id=1KjlDMRD8uhgQmQK-nC2CZGHFTbq4qQQH

Hi leon-zhang,

Please help to open a new topic for your issue. Thanks