Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) : NVIDIA-A10
DeepStream Version : nvcr.io/nvidia/deepstream:6.3-samples
NVIDIA GPU Driver Version (valid for GPU only) : Driver Version: 535.183.01 CUDA Version: 12.2
I was trying to use the Action Recognition Model (resnet18_3d_rgb_hmdb5_32.onnx) and it was running perfectly but accuracy was not good so i thought i can try the resnet18_3d_of_hmdb5_32_a100.onnx as mentioned on NVIDIA that a100 accuracy is greater but below error is coming…
root@19499bc379e5:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-3d-action-recognition# ./deepstream-3d-act
ion-recognition -c deepstream_action_recognition_config.txt
num-sources = 1
Now playing: file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_run.mov,
0:00:00.230368626 11434 0x557ccda3f360 WARN nvinfer gstnvinfer.cpp:887:gst_nvinfer_start:<primary-nvinference-engine> warning: NvInfer output-tensor-meta is enabled but init_params auto increase memory (auto-inc-mem) is disabled. The bufferpool will not be automatically resized.
0:00:00.230842421 11434 0x557ccda3f360 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: onnx2trt_utils.cpp:377: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
WARNING: [TRT]: TensorRT encountered issues when converting weights between types and that could affect accuracy.
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 21 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 20 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
0:00:49.774054445 11434 0x557ccda3f360 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2034> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.3/sources/apps/sample_apps/deepstream-3d-action-recognition/resnet18_3d_of_hmdb5_32_a100.onnx_b4_gpu0_fp16.engine successfully
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 2
0 INPUT kFLOAT input_of 2x32x224x224 min: 1x2x32x224x224 opt: 4x2x32x224x224 Max: 4x2x32x224x224
1 OUTPUT kFLOAT fc_pred 5 min: 0 opt: 0 Max: 0
0:00:49.897270091 11434 0x557ccda3f360 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:config_infer_primary_3d_action.txt sucessfully
sequence_image_process.cpp:494, [INFO: CUSTOM_LIB] 3D custom sequence network info(NCSHW), [N: 4, C: 3, S: 32, H: 224, W:224]
sequence_image_process.cpp:522, [INFO: CUSTOM_LIB] Sequence preprocess buffer manager initialized with stride: 1, subsample: 0
sequence_image_process.cpp:526, [INFO: CUSTOM_LIB] SequenceImagePreprocess initialized successfully
Using user provided processing height = 224 and processing width = 224
Decodebin child added: source
Decodebin child added: decodebin0
Running...
WARNING from element primary-nvinference-engine: NvInfer output-tensor-meta is enabled but init_params auto increase memory (auto-inc-mem) is disabled. The bufferpool will not be automatically resized.
Warning: NvInfer output-tensor-meta is enabled but init_params auto increase memory (auto-inc-mem) is disabled. The bufferpool will not be automatically resized.
Decodebin child added: qtdemux0
Decodebin child added: multiqueue0
Decodebin child added: h264parse0
Decodebin child added: capsfilter0
Decodebin child added: faad0
Decodebin child added: nvv4l2decoder0
In cb_newpad
In cb_newpad
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
FPS(cur/avg): 37.90 (37.90)
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
FPS(cur/avg): 33.33 (33.33)
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
0:00:51.785222252 11434 0x557cccf9be40 WARN nvinfer gstnvinfer.cpp:1993:gst_nvinfer_process_tensor_input:<primary-nvinference-engine> warning: nvinfer could not find input layer with name = input_rgb
WARNING from element primary-nvinference-engine: nvinfer could not find input layer with name = input_rgb
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
Warning: nvinfer could not find input layer with name = input_rgb
0:00:51.818503698 11434 0x557cccf9be40 WARN nvinfer gstnvinfer.cpp:1993:gst_nvinfer_process_tensor_input:<primary-nvinference-engine> warning: nvinfer could not find input layer with name = input_rgb
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
WARNING from element primary-nvinference-engine: nvinfer could not find input layer with name = input_rgb
Warning: nvinfer could not find input layer with name = input_rgb
0:00:51.851893233 11434 0x557cccf9be40 WARN nvinfer gstnvinfer.cpp:1993:gst_nvinfer_process_tensor_input:<primary-nvinference-engine> warning: nvinfer could not find input layer with name = input_rgb
WARNING from element primary-nvinference-engine: nvinfer could not find input layer with name = input_rgb
ROI: [left: 0.000000, top: 0.000000, width: 1280.000000, height: 720.000000]
Warning: nvinfer could not find input layer with name = input_rgb
can anyone help me in this …
