I am using the following:
JN 2GB
Jetpack 4.4.1
DS 5.0.1
TRT 7.1.3
CUDA 10.2
I am having the following problem while building the engine:
Creating Pipeline
Creating Source
Creating Video Converter
Creating EGLSink
Playing cam /dev/video0
Adding elements to Pipeline
Linking elements in the Pipeline
Starting pipeline
Using winsys: x11
0:00:00.745268239 25976 0x38826ea0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 3]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1715> [UID = 3]: Trying to create engine from model files
Input filename: /opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-usbcam/pipeline/face/secondary/facenet_onnx.onnx
ONNX IR version: 0.0.4
Opset version: 9
Producer name: tf2onnx
Producer version: 1.8.4
Domain:
Model version: 0
Doc string:
INFO: [TRT]: Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
INFO: [TRT]: Detected 1 inputs and 1 output network tensors.
ERROR: Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-usbcam/pipeline/face/secondary/facenet_onnx.onnx_b1_gpu0_fp16.engine opened error
0:02:34.042452317 25976 0x38826ea0 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger: NvDsInferContext[UID 3]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1743> [UID = 3]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-usbcam/pipeline/face/secondary/facenet_onnx.onnx_b1_gpu0_fp16.engine
INFO: [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1:0 3x160x160
1 OUTPUT kFLOAT Bottleneck_BatchNorm/batchnorm/add_1:0 128
0:02:34.365384514 25976 0x38826ea0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 3]: Load new model:dstest1_sgie_identification.txt sucessfully
0:02:34.390015368 25976 0x38826ea0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1715> [UID = 1]: Trying to create engine from model files
ERROR: [TRT]: conv1/convolution: image size is smaller than filter size
ERROR: [TRT]: conv1/convolution: image size is smaller than filter size
ERROR: [TRT]: conv1/convolution: image size is smaller than filter size
ERROR: [TRT]: UffParser: Parser error: conv1/BiasAdd: The input to the Scale Layer is required to have a minimum of 3 dimensions.
parseModel: Failed to parse UFF model
ERROR: failed to build network since parsing model errors.
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
0:02:35.229036900 25976 0x38826ea0 ERROR nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1735> [UID = 1]: build engine file failed
I don’t know why there’s an error building the engine. Can someone help on this issue please?