Skip to content

Commit

Permalink
🔥 🔥 🔥
Browse files Browse the repository at this point in the history
  • Loading branch information
@pjreddie
pjreddie authored Apr 7, 2017
1 parent 179ed8e commit e15189d
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion Makefile
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ ARCH= -gencode arch=compute_20,code=[sm_20,sm_21] \
-gencode arch=compute_52,code=[sm_52,compute_52]

# This is what I use, uncomment if you know your arch and want to specify
ARCH= -gencode arch=compute_52,code=compute_52
# ARCH= -gencode arch=compute_52,code=compute_52

VPATH=./src/
EXEC=darknet
Expand Down

3 comments on commit e15189d

@TaihuLight
Copy link

@TaihuLight TaihuLight commented on e15189d Apr 9, 2017 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I read the commit about binary weights and input binarization as follow, how I coding for binary weights and input binarization as decribed in the paper XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks ECCV2016 ? Because I want to speedup YOLO-V2 by this way.
08c7cf9
23955b9
2f62fe3

allenai/XNOR-Net#21

@abagshaw
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is probably related to my question: https://groups.google.com/forum/#!topic/darknet/b-14hO_1Tf4

@TaihuLight
Copy link

@TaihuLight TaihuLight commented on e15189d Apr 10, 2017 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is only a online demo, could not find any code! I hope to accelerate YOLO V2 by modifying the codes according to the paper and some old codes in the darknet repository discribed in above three links.

allenai/XNOR-Net#21

Please sign in to comment.