You may refer to DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums, the item 2. [DS5.0GA_Jetson_GPU_Plugin] Dump the Inference Input can dump the input data of tensorRT for you to compare.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Issues running custom model in deepstream | 1 | 575 | February 17, 2021 | |
| 0x55a9170640 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]:log(): UffParser: Could not read buffer. | 15 | 4122 | June 8, 2021 | |
| Custom detection ONNX model gives wrong outputs using nvinfer with DeepStream 5.1 | 16 | 3205 | September 27, 2021 | |
| Using custom model in deepstream | 39 | 1107 | September 10, 2024 | |
| ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::parseBoundingBox() | 4 | 4859 | December 16, 2021 | |
| yolo custom model file and error from primary-nvinference-engine | 14 | 3183 | December 3, 2019 | |
| Custom Model applied on Deepstream | 2 | 587 | December 30, 2022 | |
| Parsing custom tensorflow model | 30 | 1264 | September 4, 2023 | |
| NvDsInferLayerInfo not giving expected no. of outputs | 59 | 2862 | July 31, 2020 | |
| Converting Custom RetinaNet model to TensorRT in DeepStream | 28 | 758 | January 21, 2025 |