Andreas Marxer

I do have the same issue. Did you find a solution yet?

Uninstall tensorflow and install tensorflow-gpu does maybe help?

I'm also interested in training with negative samples. I'm working on a 1 class bounding box detection and wanted to improve training performance with negative, but kind of similar examples....

+1

I also have the same problem. Trained about 8 hours on a cluster. Something doesn't work properly I guess.. I attached the log file, does someone have an idea? [log.txt](https://github.com/AlexeyAB/darknet/files/3721617/log.txt)

Thanks, man for the fast reply @AlexeyAB! 1. Unfortunately, I get the following error when setting GPU=1 and CUDNN=1 when compiling.:  (Previously I loaded the following modules specified in...

1. When doing `cmake . ` I get an Configuration incomplete, errors occured! output in the terminal. The following log files are: [CMakeError.log](https://github.com/AlexeyAB/darknet/files/3721693/CMakeError.log) [CMakeOutput.log](https://github.com/AlexeyAB/darknet/files/3721694/CMakeOutput.log) The terminal output further says that...

Actually, what's the difference between `cmake . && make` and only `make`? I found out that the error also exists when I go back to the original Makefile with GPU=0...

In the meantime I got further experienting with different versions. Actually I'm using **CUDA 9.0.176, openCV 3.4.3, cudnn 7.0 and cmake 3.14.4**. The `cmake .` works without problems with this...

Actually I'm using CMake 3.14.4. Okay, thanks for the hint to not build in-tree. I deleted the Microsoft Windows stuff in the build (darknet/build) folder and tried to build there...