import openpifpaf
openpifpaf.plugin.register()
Base Networks¶
The following types of base networks have implementations and can be used with the --basenet command line argument for training. Not all base networks are well optimized and you can consult the {ref}introduction for benchmark results.
list(openpifpaf.BASE_FACTORIES.keys())
Pretrained Models¶
The current list of pretrained models is below and you can use them with the --checkpoint argument. Not all pretrained models are well optimized and you can consult the {ref}introduction for benchmark results.
[c for c, u in openpifpaf.CHECKPOINT_URLS.items() if isinstance(u, str)]
(coordinate-system)=
Coordinate System¶
When adding your own datasets or transformations, it is good to keep in mind the coordinate system that OpenPifPaf assumes. The short summary is, everything is done in such a way that annotation coordinates only need to be multiplied by the image rescaling factor without offset. Therefore, the (0, 0) feature map needs to be aligned with the (0, 0) pixel.
This also shows that training image sizes must be a multiple of the network stride plus one, i.e., in the above image, an input image size of $5\times5$ would be optimal for a feature map of size $2\times2$ because the stride is 4.