Emanuele Plebani

Seems an `Eigen3` bug. Using the last `g2o` and `Eigen3 `code from the mirror here: https://github.com/RLovelett/eigen The error disappears and the compilation ends correctly.

A workaround is to pad the array with NaNs in the filtering axis on the right side and remove the excess elements on the left side to emulate symmetric filtering....

With `caffe-cpu` I have the same problem of 'DLL load failed', under Windows 10 and conda Python 3.7. Launching the `caffe` command from terminal, some debug DLLs are missing, e.g....

The project now runs fine, but `prettytensor` is still required because of the unused `deconv` imports. I created PR #11 to remove them.

YOLO expects inputs in the range `[0,1]` while the OpenCV `img` has range `[0, 255]`. The function `caffe.io.load_image` takes already care of that by calling `skimage.img_as_float`. You need simply to...

I have the same issue, a delay in the refresh of about 4s with 2.5k notes when e.g. changing the sort order. Using the profiler in the developer console, you...

@Limezy thanks for the terrific work on creating a full Lua solution. However, I found Albert's script structure quite long and hard to understand. I created a simplified alternative script...

The agreement is still available on the Wayback machine: https://web.archive.org/web/20171205195950/http://suncg.cs.princeton.edu/ But I doubt someone will answer the email, given that the website was taken down.

They likely refer to Adaptive Copy-Paste (ACP) and Adaptive CutMix (ACM) referred in the paper (section 3.3).

@chord, first of all thanks for debugging the YOLO model. Can you give me some information on your system, e.g.: * OS (Linux, Windows) * Python version and type (e.g....