FPN_Faster_RCNN
FPN_Faster_RCNN copied to clipboard
a tensorflow implementation for FPN
作者您好,这个参数是数据集的图片数量吗?
在Faster RCNN中训练的时候将RPN和Fast-RCNN交叉进行他网络微调,但是我看代码中是直接将两者loss相加求梯度并反向传播?请问是这样的吗?
Do you have any demo files?
when I try run python train.py , it get an error :failed call to cuInit: CUDA_ERROR_NO_DEVICE
i changed BASE_ANCHOR_SIZE_LIST and ANCHOR_RATIOS base on my own dataset in config.py, should i also change RPN_BBOX_STD_DEV and BBOX_STD_DEV? And how to calculate the two parameters? Thanks.