Results 215 comments of Manu Mathew

"Objects as Points (CenterNet)" is a popular, high accuracy Object Detector. "Objects as Points" Xingyi Zhou, Dequan Wang, Philipp Krähenbühl https://arxiv.org/abs/1904.07850 Source code: https://github.com/xingyizhou/CenterNet (This detector is referred to as...

Can you please pull the repository once again and try. For running the benchmarks, you can use run_benchmarks_ps.sh To compile your own models, you can use run_custom_pc.sh

>>>When training done with fp32, I convert the .pt model to .onnx, and I respectively use them to predict one pic, and the results are very close QAT onnx model...

That is the expectation, getting exact accuracy involves a lot of aspects including using the correct confidence threshold, top-k boxes, input pre-processing etc. So, do don't think it will be...

Yes - you can see details here: https://github.com/TexasInstruments/edgeai-torchvision/blob/master/docs/pixel2pixel/Quantization.md#how-to-use--quanttrainmodule

Accuracy benchmark is provided via: https://github.com/TexasInstruments/edgeai-benchmark See the instructions to compile custom models: https://github.com/TexasInstruments/edgeai-benchmark/blob/master/docs/custom_models.md

Are you asking about adding this postprocessing for depth estimation in [edgeai-gst-apps](https://github.com/TexasInstruments/edgeai-gst-apps) in the sdk? What is the exact postprocessing needed? You can modify the python postprocessing code to add...

You can get the link by browsing in this repository: https://github.com/TexasInstruments/edgeai-modelzoo If you open a .link file, you will get the correct link. For example, please see if the edgeai-yolox...

Copying the previous conversation from issue #386 ----------------------------------------------------- mathmanu commented 23 hours ago @drnikolaev I have an interesting observation. If I add a few Crop layers to the mobilenet model,...

There is a range estimation function which is done after every frame of inference. The quantization is not only dependent on the current input - it also depends on the...