-
After serious perf improvements by NVIDIA's CUDNN R4 across board, I suppose Nervana weren't too happy to be left behind.
They've just released (as part of Neon) their Winograd-based kernels which ha…
-
Hello,
I am using CMake as my build system for RTL simulations.
Very often I have a scenario where I have a custom command that would generate Verilog files.
I am using custom_commands rather tha…
-
I've done a experimental tool to convert bison grammars to a kind of EBNF understood by https://www.bottlecaps.de/rr/ui to generate railroad diagrams see bellow the converted `verilog/parser/verilog.y…
-
Currently we have some bitwise operators for the `Vector` type. It would be useful for some scenarios (especially cryptography, where xoring two long buffers is common) to extend these bitwise operato…
-
Hi AlexeyAB,
Thanks for you repo. I managed to run the yolo3-voc but since the darknet is quite large so I am trying to replace it by ResNet50.
My question is how should I write the route layers…
-
I've tested this yolov3 implementation in pytorch [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3). I used the same dataset and same yolov3-spp.cfg file (same of everythi…
-
I am sorry that I have to open this but both in the opencl github branch and the google forums dont have any kind (updated) step by step installation instructions for installing Caffe Opencl on Intel …
-
I saw gplhegde fork of darknet which enables to easily truncate weights to 16 or 8 bits. My question is if one can run it on the original darknet without upscaling it to float before? I would like to …
-
Hi Everyone,
I have been training different YOLO networks for my custom dataset following the repository from @AlexeyAB and i am quite puzzled about the performance obtained for each network.
I a…
-
Hi all,
The reason I've been slow on convnet-benchmarks these days is because i've been working on the side on DeepMark.
I initially wrote _convnet-benchmarks_ to increase competition among framewor…