chl916185

def forward(self, input, input_masking): """ input : B,T input_masking : B,T output : B,T,D B,1,D """ hidden = self.init_hidden(input) 这个地方每次读入新的数据都被初始化为0有问题吧,应该写到 __init__函数中吧 @pengshuang

ssd yolo

1

Can deployments use the yolo SSD faster- RCNN model ? @termie @sleepsonthefloor @Djelibeybi @vishvananda @tjfontaine

车牌数据集

1

您好，能提供下数据集吗，我对您的项目很感兴趣。

@szad670401 请问下怎么用ｇａｎ网络生成车牌呢，您用的是什么模型呢

cmake error!

1

cmake .. -DCMAKE_BUILD_TYPE=Release -DPYTHON_LIBRARY=$CONDAENV/lib/libpython3.10.so -DPYTHON_INCLUDE_DIR=$CONDAENV/include/python3.10 -DBOOST_INCLUDE_DIR=$CONDAENV/include -DEIGEN3_INCLUDE_DIR=$CONDAENV/include/eigen3 -DGMP_INCLUDE_DIR=$CONDAENV/include -DGMP_LIBRARY_RELEASE=$CONDAENV/lib/libgmp.so -DMPFR_INCLUDE_DIR=$CONDAENV/include -DMPFR_LIBRARIES=$CONDAENV/lib/libmpfr.so -DGMPXX_INCLUDE_DIR=$CONDAENV/include -DGMPXX_LIBRARIES=$CONDAENV/lib/libgmpxx.so -DCGAL_DIR=$CONDAENV/lib/cmake/CGAL -DOpenCV_DIR=$CONDAENV/lib/cmake/opencv4 -- Found Boost: /root/miniconda3/envs/roofline/lib/cmake/Boost-1.84.0/BoostConfig.cmake (found suitable version "1.84.0", minimum required is "1.65.0") found components: filesystem...

loss = -inf ,train cfair10 64*64*3

2

(200, 'step') tensor(-0., device='cuda:0') tensor(-inf., device='cuda:0') (400, 'step') tensor(-0., device='cuda:0') tensor(-inf., device='cuda:0') (600, 'step') tensor(-0., device='cuda:0') tensor(-inf., device='cuda:0') 64 epoch finished ----------------------------------------------------------------- (200, 'step') tensor(-0., device='cuda:0') tensor(-inf., device='cuda:0') (400, 'step')...

为啥不支持cuda11.0啊

1

我的显卡是rtx3090，只能使用cuda11.0以上的显卡，看您代码是在10.2上才可以运行啊，要修改哪里可以用cuda11.0啊

When is the code open source?

2

When is the code open source? @chenzhaiyu