DayBreak
DayBreak
你好 我提供了snet146的预训练模型，代码也重写了，你可以更新下
Hi, I send train code in imagenet on : https://github.com/ouyanghuiyu/Snet
你是改了代码吧
看readme 更新了
hi,levine! Your MAP is 0.81?That's impossible，Did you change anything？My result is only 0.62，It's still in the works！
yes！ I'm still working on the Data Augmentation
使用src/retinaface2yololandmark.py脚本将retinaface的标记文件转为yolo的格式使用, 使用src/create_train.py 创建训练样本
I see the code with fr: scalar_t roi_y = bbox_offset[0] * spatial_scale; scalar_t roi_x = bbox_offset[1] * spatial_scale; scalar_t px[5] = { roi_x, 0, 0, 0, 0 }; scalar_t py[5]...
得提供fastchat类似接口才行吧
您好，请问cv2.dct 具体是怎么操作的呀？