You can set “network-type=100”, 100 is for customized models.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| [deepstream_pose_estimation] Why is the network-type set to 100 in the config? | 2 | 553 | October 12, 2021 | |
| How to get `nvinfer` raw tensor output of a custom model? | 2 | 105 | November 9, 2024 | |
| Parsing custom network output | 5 | 839 | September 4, 2021 | |
| Set network-type=100 in Deepstream, how to get data from nvinfer? | 6 | 981 | August 2, 2022 | |
| Does nvinfer work with custom neural Network? | 10 | 1324 | October 12, 2021 | |
| Enable both tensor meta and classifier_meta_list | 3 | 395 | June 25, 2023 | |
| Parsing custom tensorflow model | 31 | 647 | September 4, 2023 | |
| Wrong / Missing output from Gst-nvinfer plugin | 9 | 81 | April 1, 2025 | |
| Regarding the understanding of networks supported by nvinfer, which kind is right? | 8 | 422 | December 19, 2022 | |
| [python] Extract raw `output_tensor_meta` from nvinferserver[triton] in numpy | 2 | 538 | June 30, 2022 |