Have been trying end-to-end training and deployment of model using TLT and deepstream, but now I feel stuck. Looking for some help. Thanks.
Have tried testing end-to-end training and deployment, but unable to get proper boundary boxes around objects.
- Training: nvcr.io/nvidia/tlt-streamanalytics : v1.0_py2
- Deployment: nvcr.io/nvidia/deepstream : 4.0.1-19.09-devel
- Followed the example provided by TLT container at /workspace/examples/detectnet_v2, without any changes to script (attaching notebook pdf)
- Used 8 GPUs for training, using the script embedded in example for multi-gpu training.
- Detection results were good and objects were being bounded properly by box (attaching results).
- Following files were generated successfully "calibration.bin", "calibration.tensor", "resnet18_detector.etlt", "resnet18_detector.trt". (Attaching etlt model for reference).
- These files were exported to deepstream, to be used with slight modification of example found at "/root/deepstream_sdk_v4.0.1_x86_64/sources/apps/sample_apps/deepstream-test1". (The modifications can be found at https://gist.github.com/AlexTech009/2b22805e6cfbb7ecf0c86ca004fcc6b3).
- The sample video at "/root/deepstream_sdk_v4.0.1_x86_64/samples/streams/sample_720p.h264" was used for inference testing.
- Since no modifications were made to training script and nor much to deepstream, we were expecting it to detect cars and pedestrians(person) which shows up in video, however it makes erroneous bounding boxes, if any.
- In INT8 mode, with network-mode=1, no bounding boxes appears.
- In FP32 mode, with network-mode=0, boxes appears but at erroneous places. (Attaching results)