Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) AMD 5950X, Ubuntu 20.04, (2) RTX 3080 TIs
• DeepStream Version FROM nvcr.io/nvidia/deepstream:6.2-devel
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
Question:
sample app runs correctly with default config, (gpu-id=0)
I want to run it on my 2nd gpu (gpu-id=1)
I changed:
config_infer.txt
gpu-id=1
model-engine-file=/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b4_gpu1_int8.engine
config_preprocess_sgie.txt
gpu-id=1
config_preprocess.txt
gpu-id=1
check my revised configs:
$ grep gpu GPU1.txt
config_GPU1_infer.txt:gpu-id=1
config_GPU1_infer.txt:model-engine-file=/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b4_gpu1_int8.engine
config_GPU1_preprocess.txt: # gpu-id to be used
config_GPU1_preprocess.txt:gpu-id=1
config_GPU1_preprocess_sgie.txt: # gpu-id to be used
config_GPU1_preprocess_sgie.txt:gpu-id=1
I ran it with my revised GPU1 configs:
./deepstream-preprocess-test config_GPU1_preprocess.txt config_GPU1_infer.txt file:///opt/nvidia/deepstream/deepstream-6.2/samples/streams/sample_1080p_h264.mp4 file:///opt/nvidia/deepstream/deepstream-6.2/samples/streams/sample_1080p_h264.mp4
It appears to have built the engine on GPU1
What did I miss? I see surface-gpu-id=0 - where is that config?
Now playing: file:///opt/nvidia/deepstream/deepstream-6.2/samples/streams/sample_1080p_h264.mp4, file:///opt/nvidia/deepstream/deepstream-6.2/samples/streams/sample_1080p_h264.mp4,
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING
in CUDA C++ Programming Guide
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING
in CUDA C++ Programming Guide
0:00:01.632878842 338 0x55d0c7c04cc0 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b4_gpu1_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:01.695119400 338 0x55d0c7c04cc0 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b4_gpu1_int8.engine
0:00:01.706640706 338 0x55d0c7c04cc0 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:/project/deepstream/nvidia/ds62_apps/sample_apps/deepstream-preprocess-test/config_GPU1_infer.txt sucessfully
Decodebin child added: source
Decodebin child added: decodebin0
Decodebin child added: source
Decodebin child added: decodebin1
Running…
Decodebin child added: qtdemux0
Decodebin child added: qtdemux1
Decodebin child added: multiqueue0
Decodebin child added: multiqueue1
Decodebin child added: h264parse1
Decodebin child added: h264parse0
Decodebin child added: capsfilter0
Decodebin child added: capsfilter1
WARNING from element uri-decode-bin: No decoder available for type ‘audio/mpeg, mpegversion=(int)4, framed=(boolean)true, stream-format=(string)raw, level=(string)2, base-profile=(string)lc, profile=(string)lc, codec_data=(buffer)119056e500, rate=(int)48000, channels=(int)2’.
Warning: No decoder available for type ‘audio/mpeg, mpegversion=(int)4, framed=(boolean)true, stream-format=(string)raw, level=(string)2, base-profile=(string)lc, profile=(string)lc, codec_data=(buffer)119056e500, rate=(int)48000, channels=(int)2’.
WARNING from element uri-decode-bin: No decoder available for type ‘audio/mpeg, mpegversion=(int)4, framed=(boolean)true, stream-format=(string)raw, level=(string)2, base-profile=(string)lc, profile=(string)lc, codec_data=(buffer)119056e500, rate=(int)48000, channels=(int)2’.
Warning: No decoder available for type ‘audio/mpeg, mpegversion=(int)4, framed=(boolean)true, stream-format=(string)raw, level=(string)2, base-profile=(string)lc, profile=(string)lc, codec_data=(buffer)119056e500, rate=(int)48000, channels=(int)2’.
Decodebin child added: nvv4l2decoder0
Decodebin child added: nvv4l2decoder1
In cb_newpad
In cb_newpad
ERROR from element preprocess-plugin: Memory Compatibility Error:Input surface gpu-id doesnt match with configured gpu-id for element, please allocate input using unified memory, or use same gpu-ids OR, if same gpu-ids are used ensure appropriate Cuda memories are used
Error details: gstnvdspreprocess.cpp(1386): gst_nvdspreprocess_on_frame (): /GstPipeline:preprocess-test-pipeline/GstNvDsPreProcess:preprocess-plugin:
surface-gpu-id=0,preprocess-plugin-gpu-id=1
Returned, stopping playback
Deleting pipeline