foxkw
foxkw
例如旋转，裁剪之类的攻击，即使裁剪的非常小，只要还原回去了就能提取水印，但例如裁剪还原填补的是白色像素，像素值已经与原图不同了，请问为何这时候也能提取出水印呀
label pictures in CULane are black. How to get the label picture like that？the lane line pixels are colored 
when I remove '-s' in labelGen.sh, it's ok . but when I add '-s', it is wrong . could please tell me why ? `OpenCV Error: Assertion failed (ssize.width >...
from g2o import AngleAxis ImportError: cannot import name 'AngleAxis' from 'g2o' (unknown location) How should I solved it ?
could you provide this datasets link ? thank you
您好，我有2个问题想请教。 1）请问为何在val模式下， Loss的值没有求平均呢，即：最后在tensorboard上显示的loss值。 ` val_loss += loss.item() val_loss_seg += loss_seg.item() val_loss_exist += loss_exist.item() progressbar.set_description("batch loss: {:.3f}".format(loss.item())) progressbar.update(1) progressbar.close() iter_idx = (epoch + 1) * len(train_loader) # keep align with training...
您好，有一处问题想请教一下 ` lstm, _ = self.convlstm(data) test = lstm[0][-1,:,:,:,:] ` 第一行是定义了2层的lstm，一层用于提取特征，一层用于集成。 第二行的test =test = lstm[0][-1,:,:,:,:] 。 不知道是什么意思， 希望能解答一下， 谢谢
Hi, thanks for your great job. I want to train magicpoint on kitti , so is it needed to use magicpoint_kitti_train.yaml ? I noticed there is a path of labels....
Thanks for ur diles. if I just want to predict on tusimple dataset .I don’t want to use ros, Is there a corresponding file?
Hi, thanks for your great job. I want to train magicpoint on kitti , so is it needed to use magic_point_coco_train.yaml ? I noticed there is a path of labels....