wolfworld6

when i run the script feat_extract.py,i got this error,why? fast_input shape: (1, 3, 18, 224, 224) slow_input shape: (1, 3, 0, 224, 224) Fast x shape: (1, 8, 18, 112,...

If possible, could you please send the ultra-high precision model to [email protected] ? Thank you！

i install on windows,as follows: os:windows10 cuda:10.0 pytorch:1.7.0 vs:2017 i got this error when i run "python setup.py build develop", could you tell me how i solve this error?thx! building...

How do I get the result of Figure 1 in the paper？

hi,i got this error, "cudnn_conv_layer.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory" ，so confused ，how much memory required for the model？(test on gtx1050,4G),

from mask_net import MASK_CLASSIFY

7

hello，thx for your code，but i wanna know where is the mask_net？ besides，i use onnx versio is 1.8.0，the Opset version 13，why i got this error？ TypeError: ONNX node of type Shape...

the performace

1

hello，thx for your code，i have test the yolov5s，but the res is not well，could you help me confirm if there is any loss between onnx-caffe？thx again！

hello，i wanna to know your lfw.py and lfw_test_pairs.txt are right? i got this error, ValueError: invalid literal for int() with base 10: 'Akhmed_Zakayev/Akhmed_Zakayev_0003.jpg' the lfw_test_pairs.txt 

please help!

7

when i run this code,i got this error: Check failed: bottom[0]->count() == bottom[1]->count() (20 vs. 10) SIGMOID_CROSS_ENTROPY_LOSS layer inputs must have the same count. how do i solve it?

please， I got this error“error LNK2001: 无法解析的外部符号 "protected: virtual void __cdecl caffe::FocalLossLayer::Forward_gpu(class std::vector const &,class std::vector const &)" (?Forward_gpu@?$FocalLossLayer@N@caffe@@MEAAXAEBV?$vector@PEAV?$Blob@N@caffe@@V?$allocator@PEAV?$Blob@N@caffe@@@std@@@std@@0@Z) E:\DXD\caffefl\caffe\windows\caffe\focal_loss_layer.obj caffe