-
Hi,
I wonder if alpha and delta are layer based (as clained in Trained Ternary Quantization paper) or filter based (like XNOR-Net). I assumed they are filter based because your paper mention n as …
-
I am trying to train BIT1-XNOR tiny-yolov2 with input size 224x224. Here is my .cfg file.
[tiny-yolo-obj_xnor_new-224x224.zip](https://github.com/AlexeyAB/yolo2_light/files/2579921/tiny-yolo-obj_x…
-
Hi @AlexeyAB,
I am training and using a XNORNet version of cifar. However, when I went through the code I saw that it does not get accelerated for the "classifier" option. Darknet only uses xnor ac…
-
I am trying to train yolov3-tiny_xnor and getting the following output while testing on 2000 epochs.
```
layer filters size input output
0 conv 16 3 x …
-
Hi Guys,
I don't understand how do you train your binary weights, if you use sign function, the gradient is broken at the sign function. And I didn't get how do you handle this (in XNor-Net paper,…
-
I was wondering whether there is XNOR for ResNet. Or can you give some hints about how to implement it?
-
Hello.
I am using model **cifar-10** for training custom dataset.
**My data:**
```
{
train :
{
data : FloatTensor - size: 3000x3x96x96
labels : FloatTensor - size: 3000
…
-
这是在torch1.4之后的新要求，改变了torch.autograd.Function的调用方法，需要使用.apply来调用。
解决方法，在XNOR-Net-PyTorch-master\MNIST\models下的LeNet_5.py第53行改为 x = BinActive.apply(x)即可正常运行
change LeNet_5.py line53 to 'x = BinActiv…
-
Hi. Thank you for your uploading. I have downloaded NIN cifar10 pretrained model and load it. Then, I run the inference evaluation. At this time. the accuracy is just only 59.36%. In this evaluation, …
-
error: ValueError: ('Input has undefined rank:', TensorShape(None))