adizhol

Hi, I apologize if this is a basic question - why are the weights calculated as in https://github.com/muskie82/simple_dvo/blob/ff1e04cc660f95d0c890990178b1162667f5ed8e/src/image_alignment.cpp#L279 ? From the DVO paper it should be log(p(r))/r where p is...

identifier "angleaxis_to_rotmatrix_gpu" is undefined

2

error building depthtoflow_cuda.cu(282): error: identifier "angleaxis_to_rotmatrix_gpu" is undefined detected during: instantiation of "void DepthToFlowOp_GPU::Compute(tensorflow::OpKernelContext *) [with T=double]"

How to render SDF?

1

Hi, There's a header definition for render() in the CudaRayCastSDF.h but no implementation. Have you had a chance perhaps to implement it? Thank you!

In https://github.com/FangGet/BundleFusion_Ubuntu_Pangolin/blob/0c470d91b2773daad2f7b7adc5819144e1779041/src/BundleFusion.cpp#L322 you basically call g_marchingCubesHashSDF->extractIsoSurfaceGPUNoChrunk every two frames, instead of every frame. I tried to change line 322 to "if (true)" and run every frame, but then Pangloin is...

pickle support

4

Please add pickle support. Now there's an error: ``` pickle.dump( File "stringsource", line 2, in pykdtree.kdtree.KDTree.__reduce_cython__ TypeError: no default __reduce__ due to non-trivial __cinit__ ```

DICOM conformance statement

1

Hello, Does pynetdicom has a DICOM conformance statement? Which transfer syntax does it support? Thanks

Getting black output images

1

Hi, When I try to optimize d_latent as in the code, I start from a nice image but it transforms into a completely black image. Adding an L2 loss between...

Mounting network storage in docker causes error

4

OS: Ububtu 16.04 wandb version 0.12.1 I try to start wandb local server with: `docker run --rm -d -v /home/MYUSERNAME/net_mount/wandb/:/vol -p 8080:8080 --name wandb-local wandb/local ` The container starts and...

Hi, Has anyone tried to do a reverse backprop using a target image, to find the best style vector and/or closest GAN image? I can't seem to make it work....

Hi, When I load weights_SSD300.hdf5 I get the following error: > Layer 27 (named "conv4_3_norm") expects 0 weight(s), but the saved weights have 1 element(s). Am I missing something?