Training with greyscale images

[SnowNation101]

您好，因为我目前只有检测灰度图的需求，训练时所用数据集也全是灰度图，使用yolov7-tiny版本。请问有什么办法可以针对这种情况减少通道数，使得减少模型的参数量以达到提高训练和推理速度效果呢？如果有的话，可以讲解一下具体如何修改代码或配置文件吗？感谢！ Hello, because I only need to detect grayscale images at present, the datasets used in training are all grayscale images, using the yolov7-tiny version. Is there any way to reduce the number of channels for this situation, so that the number of parameters of the model can be reduced to achieve the effect of improving the speed of training and inference? If so, can you explain how to modify the code or configuration file? grateful! (translated by Google Translate)