Crazod
Crazod
您好,我测试了下benchmark的程序,在不同的手机平台上,包括高通8Gen1的芯片,Vulkan上我无法得到像xiaomi 6 那么快的速度,请问是我测试的哪里有问题么 # 平台(如果交叉编译请再附上交叉编译目标平台): # Platform(Include target platform as well if cross-compiling): Android RedmiK50G 电竞版 芯片平台高通: 8gen1 # Github版本: # Github Version: 2.0.0 4679f848c45510531976ebdf32c42b1c27b92960 直接下载ZIP包请提供下载日期以及压缩包注释里的git版本(可通过``7z l zip包路径``命令并在输出信息中搜索``Comment`` 获得,形如``Comment =...
Hey , it is a really helpful job for me. I have find some bugs It seems that your python is different with mine. In inference.py when i use function...
Hi I use this code in inference.py to detect human estimation ``` from inference import Inference a = Inference() a.webcamSingle() ``` but it seems that there are no results. I...
Hi please let me praise what an amazing work! I have used your algorithm. But i found a little bit when i used.   My second image is same...
hi,请问作者 在论文里你用到了KL去学习Teacher的输出。 Equation (4)  在你的代码里 ` loss = torch.sum(-softmax_pred_T * logsoftmax(preds_S.view(-1, W * H) / self.tau)) * ( self.tau**2) ` 你使用的这个公式去计算KD loss。 但是标准的KL Loss应该是这样 ` kl_loss = torch.sum(softmax_pred_T...