TLT CONVERTER
necatiCelik opened this issue · 5 comments
Hi,
I get an error while tlt_convert.
Although I changed "-p" to "-d",
"./tlt-converter -k nvidia_tlt -d image_input, 1x3x48x96,4x3x48x96,16x3x48x96 ./us_lprnet_baseline18_deployable.etlt -t fp16 -e lpr_us_onnine_b
terminate called after throwing an instance of 'std :: invalid_argument'
what (): stoi
Aborted (core dumped) "error. Can you help?
you need to remove "image_input,"
i.e. it became ./tlt-converter -k nvidia_tlt -p 1x3x48x96,4x3x48x96,16x3x48x96 ./us_lprnet_baseline18_deployable.etlt -t fp16 -e lpr_us_onnine_b
However, when I doing this I am getting another issue:
[ERROR] UffParser: Could not parse MetaGraph from /tmp/file8doOYv
[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
I am using tensorRT 7.0 and cuda10.2. What's the issue then?
you need to remove "image_input,"
i.e. it became ./tlt-converter -k nvidia_tlt -p 1x3x48x96,4x3x48x96,16x3x48x96 ./us_lprnet_baseline18_deployable.etlt -t fp16 -e lpr_us_onnine_b16.engine
it true, thanks. But when I doing it, I am getting your error:
[ERROR] UffParser: Could not parse MetaGraph from /tmp/filea498W4
[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)
i have the same problem from x86 with NVIDIA GPU
“ ./tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96 /Workspacelpr_app/models/LP/LPR/ch_lprnet_baseline18_deployable.etlt -t fp16 -e models/LP/LPR/lpr_ch_onnx_b16.engine
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] Tensor DataType is determined at build time for tensors not marked as input or output.
[WARNING] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to INT32.
[WARNING] Calling isShapeTensor before the entire network is constructed may result in an inaccurate result.
[WARNING] Calling isShapeTensor before the entire network is constructed may result in an inaccurate result.
[WARNING] Calling isShapeTensor before the entire network is constructed may result in an inaccurate result.
[WARNING] Calling isShapeTensor before the entire network is constructed may result in an inaccurate result.
[WARNING] Calling isShapeTensor before the entire network is constructed may result in an inaccurate result.
[INFO] Detected input dimensions from the model: (-1, 3, 48, 96)
[INFO] Model has dynamic shape. Setting up optimization profiles.
[INFO] Using optimization profile min shape: (1, 3, 48, 96) for input: image_input
[INFO] Using optimization profile opt shape: (4, 3, 48, 96) for input: image_input
[INFO] Using optimization profile max shape: (16, 3, 48, 96) for input: image_input
[INFO] Detected 1 inputs and 2 output network tensors.”
i implement this command and then get the following info,it seems successful but there is no .engine file generated in targeted directory. How is it happened? is there any wrong?