Most of the YOLO series algorithms adopt a unified algorithm building structure, typically as Darknet + PAFPN. In order to let users quickly understand the YOLO series algorithm architecture, we deliberately designed the `BaseBackbone` + `BaseYOLONeck` structure as shown in the above graph.
We can see in the above graph，as for P5，`BaseBackbone` include 1 stem layer and 4 stage layers which are similar to the basic structural of ResNet. Different backbone network algorithms inheritance the `BaseBackbone`, users can achieve construction of every layer of the network by using self-custom basic module through `build_xx` method.
We reproduce the YOLO series Neck component by the similar method of the BaseBackbone, we can mainly divide them into Reduce layer, UpSample layer, TopDown layer, DownSample layer, BottomUP layer and output convolution layer, every layer can self-custom its inside construction by inheritance and rewrite `build_xx` method.
The YOLO series uses the BaseDenseHead designed in MMDetection as the base class of the Head structure. Take YOLOv5 as an example, [HeadModule](https://github.com/open-mmlab/mmyolo/blob/main/mmyolo/models/dense_heads/yolov5_head.py#L2) class's forward function replace original forward method.
Methods implementation in the [MMDetection](https://github.com/open-mmlab/mmdetection) is shown in the above graph. The solid line is the implementation in [MMYOLO](https://github.com/open-mmlab/mmyolo/blob/main/mmyolo/models/dense_heads/yolov5_head.py), which has the following advantages over the original implementation:
1. MMDetection in the `bbox_head` split into `assigner` + `box coder` + `sampler` three large components, but for the generality of passing through the 3 components , the model need to encapsulate additional objects to handle, and after the unification, the user needn't separate them. The benefits of not deliberately forcing the division of the three components are: no longer need to data encapsulation of internal data, simplifying the code logic, reducing the difficulty of use and the difficulty of algorithm implementation.
2. MMYOLO is Faster, the user can customize the implementation of the algorithm when the original framework does not depend on the deep optimization of part of the code.
In general, in the MMYOLO, they only need to implement the decouple of the model + `loss_by_feat` parts, and users can achieve any model with any `loss_by_feat` calculation process through modify the configuration. For example, applying the YOLOX `loss_by_feat` to the YOLOv5 model, etc.
