-
compile failed when target win32|x86 in msvc 2015.
it complains cannot find ___popcnt64
-
Dear Alexey,
Now I want to fine-tune on my little dataset,but I designed my net by myself.
So how should I get pre-trained model? Should I train my net on imagenet1k or VOC07+12 then parti…
-
感谢您开源了XNOR的pytorch代码
有一些疑问，您当时使用的是哪个pytorch版本呢
-
In you code “m:add(1/n):mul(1-1/s[2])”, why you mul (1-1/s[2]) to m ? After this, why you mul n ? I can't understand this ? @mrastegari
-
Hello,
I submitted this through the Cycling 74 support, and they asked me to also post this here.
I’m struggling to get RNBO plugins to properly compile for Unity Android. I’ve been able to comp…
-
Hey @AlexeyAB .
I am training your repo of darknet with tiny-yolov2 and full yolov2 cfg file with XNOR = 1 on COCO and Pascal VOC dataset. I have completed 10,000 iterations on both the models with …
-
https://github.com/liuzechun/Bi-Real-net/blob/0a4b802f94009b8b2419d53b0152a94feff81189/18-layer/Bi-Real-net-18-train.prototxt#L355
In your code, it seems that the downsample layer in basic block is…
-
I think there are some mistakes in bnn_layers.py (mxnet version). In BinaryActivation, the forward and backward should contain the alpha. Do you think so? When I contain the alpha, I get 94.28% testin…
-
I would like to ask you who came up with the activation function leaky tanh. I used the larq framework to experiment with binary networks and found it very effective. I have not found its author o…
-
Hi, I'm student studying NN with your great source.
Thanks for your project, we succeeded image recognition in window and linux inspite of having trouble with many dependency problems with GPU) …