Calling isShapeTensor before the entire network is constructed may result in an inaccurate result

[ahsanmalik1010]

Getting this error on running the ./CarSmartCam after building the project

&&&& RUNNING TrafficSignClassifier # Creating a new engine file at: models/traffic_sign/traffic_sign_classification_resnet18_64.engine [04/10/2021-20:57:16] [W] [TRT] Calling isShapeTensor before the entire network is constructed may result in an inaccurate result. Killed

[vietanhdev]

Hi,

You may want to check if your Jetson Nano is 4GB-RAM version. Otherwise, you may not have enough RAM to convert models to TensorRT engines

I recommend using my converted models on the SD card image.

[electron64]

I have the same issue, using the SD card image and last code.

[openbsod]

Same here with that issue, code updated and successfully builded, models was copied from SD card image.