lovekittynine

/bin/sh: 1: nvcc: not found I have met this problem,but i have installed cuda-toolkit9.0 and i run nvcc -V shows " Cuda compilation tools, release 9.0, V9.0.176"

thanks very much! i have changed nvcc path,and it works.But i have met another problem. 5 errors detected in the compilation of "/tmp/tmpxft_00006e0d_00000000-6_data_augmentation.cu.cpp1.ii".

detected during: instantiation of "Scalar Eigen::internal::igamma_series_impl::run(Scalar, Scalar) [with Scalar=float, mode=Eigen::internal::VALUE]" (863): here instantiation of "Scalar Eigen::internal::igamma_generic_impl::run(Scalar, Scalar) [with Scalar=float, mode=Eigen::internal::VALUE]" (2096): here instantiation of "Eigen::internal::igamma_retval::type Eigen::numext::igamma(const Scalar &, const Scalar...

ubuntu18.04 cuda9.0 tensorflow1.12

@bfan after i have got descriptors , matches, keypoints,but when i run reconstruction_pipeline.py it outputs as follow: Importing features for 0003.png Importing features for 0007.png Importing features for 0004.png Importing...

thanks for your reply!In training stage, even though i set random seed,the results are different each time!Other works,such as Hardnet,it can get same training results,when set identical random seed.

np.random.seed(0) torch.cuda.manual_seed(0) torch.backends.cudnn.deterministic=True

@ericsqxd Hi,I can not download the pretrained model! There show 403 Forbidden,how to solve it?Thanks

@ZhengMengbin hi, I have a question! How to get the synthesized video using test_sample1_fake_B_0_x.png? The number of image sequence is 99, according to the process of preprocessing.py, one generated image...

Hello, I've been researching L2-NET recently and I've encountered related problems. Did you solve the problem? Can you send me a copy of your tensorflow code? If you can, will...