# I have used tao-convertor to generate model engine file from Yolov4-tlt **URL:** \ **Category:** TAO Toolkit\ **Created:** [September 28, 2021, 5:39am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289 "2021-09-28T05:39:29Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [September 28, 2021, 5:39am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/1 "2021-09-28T05:39:29Z")
i am using the below command ```auto ./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 ```auto [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) ``` ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [September 28, 2021, 7:23am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/3 "2021-09-28T07:23:41Z")
Is this yolov4\_resnet18\_epoch\_050.etlt trained by yourself? Is the key correct ? ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [September 28, 2021, 7:25am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/4 "2021-09-28T07:25:01Z")
my colleague had trained it . we usually use default key nvidia\_tlt , i think the KEY is correct ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [September 28, 2021, 7:27am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/5 "2021-09-28T07:27:54Z")
Could you please compare the another forum topic created by you? > [@Input: for dimension number 2 in profile 0 does not match network definition (got min=800, opt=800, max=800), expected min=opt=max=384](https://forums.developer.nvidia.com/t/input-for-dimension-number-2-in-profile-0-does-not-match-network-definition-got-min-800-opt-800-max-800-expected-min-opt-max-384/189220): > > im trying to create engine file with the below command ./tao-converter -k nvidia\_tlt -p Input,1x3x800x1376,8x3x800x1376,16x3x800x1376 -d 3,384,384 -o BatchedNMS -e trt.engine -m 1 -t fp16 -i nchw /home/ubuntu/PoC/model/yolov4\_resnet18\_epoch\_050.etlt And i get the below error . Kindly help ./tao-converter -k nvidia\_tlt -p Input,1x3x800x1376,8x3x800x1376,16x3x800x1376 -d 3,384,384 -o BatchedNMS -e trt.engine -m 1 -t fp16 -i nchw /home/ubuntu/PoC/model/yolov4\_resnet18\_epoch\_050.etlt [WARNI… You can run it successfully. ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [September 28, 2021, 7:29am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/6 "2021-09-28T07:29:20Z")
that was different etlt model , will cross check and get back to you ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [September 28, 2021, 9:07am UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/7 "2021-09-28T09:07:29Z")
i was able to fix it .etlt File name issue was wrong ---
**Author:** ![TomNVIDIA](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/tomnvidia/32/14181_2.png) [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Post date:** [October 12, 2021, 4:23pm UTC](https://forums.developer.nvidia.com/t/i-have-used-tao-convertor-to-generate-model-engine-file-from-yolov4-tlt/190289/9 "2021-10-12T16:23:28Z")
Closed on October 12, 2021, 4:23pm UTC