To narrow down if it is an issue in tao-converter or deepstream, please try to run experiment as I mentioned in Custom TAO unet model classifying only two classes on Deepstream! - #10 by Morganh .Thanks.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| TAO unet input and output tensor shapes and order | 3 | 870 | May 10, 2022 | |
| Always same output vlaues | 10 | 2460 | October 12, 2021 | |
| Custom TAO unet model classifying only two classes on Deepstream! | 34 | 1968 | May 12, 2022 | |
| vgg16 layer visualization | 4 | 915 | October 12, 2021 | |
| Inference of model using tensorflow/onnxruntime and TensorRT gives different result | 20 | 2664 | October 18, 2021 | |
| Get wrong result when I using tensorRT to do inference, am I wrong to use ? | 18 | 3132 | October 18, 2021 | |
| Use TensorRT without any optimization | 12 | 1455 | October 12, 2021 | |
| TensorRT 5 Input Tensor Format NCHW / NHWC | 6 | 5233 | October 24, 2019 | |
| Does TensorRT 3.0 C++ API only works for NCHW? | 5 | 1584 | October 18, 2021 | |
| Incorrect Results during Inference using Tensorrt3.0 C++ uff parser | 48 | 6977 | June 4, 2018 |