The 2x down-sampling is one of the important operations in reference models. But, a convolution or a pooling with stride=2, padding='SAME' may result in different outputs over different deep learning libraries (e.g., TensorFlow, CNTK, Theano, Caffe, Torch, ...) due to their different padding behaviors.

For example (TensorNets syntax; but can be regarded as pseudo codes for other libraries),

I see you have added gaussian_yolov3_layer and yolo detection gaussian_box.(from this paper https://arxiv.org/abs/1904.04620)

can you provide a wiki or same example prototxts to explain how to use gaussian yolo correctly

thank you very much

You may use a lot of TOC generator tools to add a table of contents into the readme because your readme is too long.

Another option is to use Sphinx to document your project.

I find your tool very useful, however when annotating objects close to image edges, it is very easy to drag the bbox outside of the image. Adding a small feature to keep the bbox within the image would be appreciated.