caffe-windows
caffe-windows copied to clipboard
Configure Caffe in one hour for Windows users.
我想在windows下跑Faster RCNN,使用C++调用,使用了py-faster-rcnn的版本,其中的rpn是使用python layer实现的。当我运行的时候,就有以下错误: TypeError: No to_python (by-value) converter found for C++ type: class caffe::LayerParameter 我注意到您提供的caffe版本中有proposal layer,我看了一下源码跟rpn的源码很像,所以我直接在网络文件中将rpn替换成这个proposal layer,但是系统就直接死机了。 我在ubuntu下跑这个C++调用faster-rcnn的程序是没有任何错误的,请问有什么解决办法吗? 谢谢!
Anyone tried to training with AdaDelta solver? 1, my log is printing "...sgd_solver.cpp:106] Iteration 2900" Why not adadelta_solver.cpp? this is normal? 2. as i know, learning rate changes automatically, but...
内存溢出
各位,在卷积中添加group参数后(比如resnext网络),训练过程中内存无法释放,有人遇到类似问题吗?
In caffe.proto, there are parameters of ImageDataLayer like face_transform, min_random_scale etc. defined but unimplemented. I have checked codes in ImageDataLayer and could not found where they were used. 1.Have you...
你好,我按照步骤部署caffe,并运行mtcnn进行人脸检测,运行cpu版本没有问题,但是gpu版本没有体现出应有的速度。请问一下CascadeCNN程序有没有需要修改哪些地方?
Hi, I'm using this caffe version on windows10, but I get one error on 4 groups GTX1080TI, which is "Check failed: error == cudaSuccess (6 vs. 0) the launch timed...
Hello.. I am building Caffe on Windows 8. When the build finished caffe -help works but the Libraries folder doesn't exist in build folder which doesn't allow me to interface...
I tested your model which added in extra memorydatalayer and your bounding box regression layer. It seems that it takes longer time to perform the whole forward pass and outputs...
你好,请问你找到从MS-Celeb-1M数据集中剔除LFW的方法了吗?
I installed caffe-windows in Ubuntu 16.04. And it was ok when running "make all" but crashed when running "make pycaffe" as follow:  Does this version caffe support python...