aidevmin

@ggjy Thanks a lot for your work. I have read your paper. As my understanding, GT-mask is generated from ground-truth boxes and neck features? Is that right? Could you talk...

About top-K highest quality score?

3

Thank you for your amazing paper. I have read your paper. You said that PGD keep top-K regions with highest quality score. As my understanding, for each ground-truth box, we...

PGD for coupled head?

2

Did you try any experiments of PGD with coupled head? In this case we don't seperated classification and regression head. I want to apply your method to my model with...

[BUG] Error when installing

1

Here is my error message ``` myenv) root@ubuntu:/my_tmp/cmake-3.25.3-linux-aarch64/protobuf/build_source# pip3 install onnxsim Collecting onnxsim Using cached onnxsim-0.4.13.tar.gz (18.1 MB) Preparing metadata (setup.py) ... done Collecting onnx Using cached onnx-1.14.0.tar.gz (11.3 MB)...

How to run the the program main.cc in the person detection project?

1

I could run test for the project in my PC https://github.com/tensorflow/tflite-micro/tree/main/tensorflow/lite/micro/examples/person_detection but I do not see any guide to run the main program main.cc via make file in the PC....

QAT with multiple GPUs?

1

I tried to do QAT with multiple GPUs with `torch.nn.DataParallel`, but I got an error ``` Traceback (most recent call last): File "scripts/qat.py", line 347, in args.eval_origin, args.eval_ptq File "scripts/qat.py",...

Training with multiple GPUs is not faster than 1 GPU???

2

I follow the guide to train my dataset with multiple GPUs, I saw speed of 2 cases is same. I use the same config ``` batch=64 subdivisions=32 # 16 OOM...

What is difference between yolov4.weights and yolov4_conv_137.weights?

2

What is difference between yolov4.weights and yolov4_conv_137.weights? And I want to fine tuning YOLOv4 model on my dataset with `no_classes=4`, so which way should I use? Anh I will use...

Thank you for your repo. I converted YOLOv7 .pt to ONNX with dynamic batch size. I want to convert this ONNX to engine INT8 with dynamic batch size. It seems...

**System information** - TensorFlow version (you are using): - Are you willing to contribute it (Yes/No): **Motivation** What is the use case and how does it broadly benefits users? Prioritization...