I have used tao-convertor to generate model engine file from Yolov4-tlt

i am using the below command


./tao-converter -k nvidia_tlt -p Input,1x3x384x1248,8x3x384x1248,16x3x384x1248 -d 3,384,1248 -o BatchedNMS -e  trt.engine -m 1 -t fp16 -i nchw  /home/ubuntu/PoC/model/VehicleModel/yolov4_resnet18_epoch_050.etlt

im getting the below error

[ERROR] UffParser: Unsupported number of graph 0
[ERROR] Failed to parse the model, please check the encoding key to make sure it's correct
[ERROR] Network must have at least one output
[ERROR] Network validation failed.
[ERROR] Unable to create engine
Segmentation fault (core dumped)

Is this yolov4_resnet18_epoch_050.etlt trained by yourself? Is the key correct ?

my colleague had trained it . we usually use default key nvidia_tlt , i think the KEY is correct

Could you please compare the another forum topic created by you?

You can run it successfully.

that was different etlt model , will cross check and get back to you

i was able to fix it .etlt File name issue was wrong

1 Like