Nvinfer could not find input layer with name = input_1

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hardware Platform (Jetson / GPU) NX
• DeepStream Version 6.11
• JetPack Version (valid for Jetson only) 5.02
• TensorRT Version 8.4

I am using preprocess func to infer on my customed ROI, in the preprocess config file:
tensor-data-type=0
tensor-name=input_1

My primary gie is a trt file converted from yolov5-6.1 torch and onnx model. When running DS:
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1916): gst_nvinfer_process_tensor_input (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie
0:02:09.804809884 6965 0xaaab1b5d6800 WARN nvinfer gstnvinfer.cpp:1916:gst_nvinfer_process_tensor_input:<primary_gie> warning: nvinfer could not find input layer with name = data

WARNING from primary_gie: nvinfer could not find input layer with name = data

Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1916): gst_nvinfer_process_tensor_input (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie
0:02:09.838122361 6965 0xaaab1b5d6800 WARN nvinfer gstnvinfer.cpp:1916:gst_nvinfer_process_tensor_input:<primary_gie> warning: nvinfer could not find input layer with name = data

WARNING from primary_gie: nvinfer could not find input layer with name = data

WARNING from primary_gie: nvinfer could not find input layer with name = input_1

Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1916): gst_nvinfer_process_tensor_input (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie
0:00:06.612731621 8200 0xaaaab82e4800 WARN nvinfer gstnvinfer.cpp:1916:gst_nvinfer_process_tensor_input:<primary_gie> warning: nvinfer could not find input layer with name = input_1

WARNING from primary_gie: nvinfer could not find input layer with name = input_1

Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1916): gst_nvinfer_process_tensor_input (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie
0:00:06.645826201 8200 0xaaaab82e4800 WARN nvinfer gstnvinfer.cpp:1916:gst_nvinfer_process_tensor_input:<primary_gie> warning: nvinfer could not find input layer with name = input_1

Please info me what’s the problem. Thank you.

3

What is the input layer name? For ONNX model, please do not config “uff-input-blob-name” in the configuration file.

4

Using winsys: x11
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:03.913840057 2403647 0xaaaae4905010 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/gh_fp16.trt
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: [Implicit Engine Info]: layers num: 5
0 INPUT kFLOAT images 3x640x640
1 OUTPUT kFLOAT onnx::Sigmoid_477 3x80x80x6
2 OUTPUT kFLOAT onnx::Sigmoid_529 3x40x40x6
3 OUTPUT kFLOAT onnx::Sigmoid_581 3x20x20x6
4 OUTPUT kFLOAT output 25200x6

ERROR: [TRT]: 3: Cannot find binding of given name: conv2d_bbox
0:00:03.964227673 2403647 0xaaaae4905010 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:1876> [UID = 1]: Could not find output layer ‘conv2d_bbox’ in engine
ERROR: [TRT]: 3: Cannot find binding of given name: conv2d_cov/Sigmoid
0:00:03.964349438 2403647 0xaaaae4905010 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:1876> [UID = 1]: Could not find output layer ‘conv2d_cov/Sigmoid’ in engine
0:00:03.964392703 2403647 0xaaaae4905010 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/gh_fp16.trt
0:00:03.970790555 2403647 0xaaaae4905010 INFO

I set enable=0 in the preprocess config file, and run DS, it appears like above. There were 2 ERRORs.
Could not find output layer ‘conv2d_bbox’ in engine
ERROR: [TRT]: 3: Cannot find binding of given name: conv2d_cov/Sigmoid

5

The logs show that your model have 4 output layers. So please config “output-blob-names=onnx::Sigmoid_477;onnx::Sigmoid_529;onnx::Sigmoid_581;output” in your configuration file.

Please check your configuration file carefully, all parameters in the configuration file should adapt to your model. Gst-nvinfer — DeepStream 6.1.1 Release documentation

6

Thanks

7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.