Hanson
I have the same problem. Have you solved it？
> task_shared网络写得好像有些小问题，应该将peranchor_feature的定义放到第一个循环里面， 不然每一次peranchor_feature都是在上一个peranchor_feature的基础上累加。 > > def task_shared (inp, oup, stride = 1, leaky = 0, m1 = 3,anchorNum = 3) : > > ``` > allanchor_feature =nn.ModuleList() > for i...
@ZhangwenguangHikvision 其实我push上去的已经包含一套完整的训练、前向流程了，你可以自己添加你自己的数据集先训练。
Thanks for your prompt reply，this is my step: 1)git clone --recursive https://github.com/RedisAI/RedisAI; 2)bash get_deps.sh, it will download tf and torch.. 3)ALL=1 make -C opt clean build I build them in...
> class SSH(nn.Module): > > ``` > def __init__(self, in_channel, out_channel): > super(SSH, self).__init__() > assert out_channel % 4 == 0 > leaky = 0 > > if (out_channel leaky...
仔细阅读一下readme，给出的模型只是为了验证模型框架的有效性在一张图片上过拟合的结果。
等忙玩这段时间我会把整个push上去的。
> Dear Sir, > how to calculate the precision about multi-label classification? you can use roc_auc_score
> roc_auc_score is used to calculate the auc score. how about calculating the precision? You can refer to https://www.kaggle.com/c/ranzcr-clip-catheter-line-classification/overview/evaluation
> As in this code-base direct .`mnn` weight files are provided which are parsed using the custom CPP module and then infered using MNN inference engine, but one of you...