-
CUDNN_HALF = 1 detection on version [fb1ee79](https://github.com/AlexeyAB/darknet/commit/fb1ee79576f83d505211267252e070c3cb0f431e)
![image](https://user-images.githubusercontent.com/29922029/49805308…
-
Hi, I find the results between CPU version and GPU version are different in your latest version . The results are better in CPU version . The cfg file and weights are yolov3-spp.cfg and yolov3-spp.wei…
-
Hi,
When I trained yolov3 with yolov3-spp.cfg, it shows "Layer before convolutional layer must output image.: No error", could you tell me how to fix this error?
Thank you!
![default](https://…
-
Hello!Thanks for your work.Could you please tell me the way to calculate the mAP of darknet-yolov3?
-
After experimenting with the Yolov3 network for one week, I found several issues with multi GPU training. The trained network with a single GPU had way better detection results than the network traine…
-
我想請問下,你之前非實時那個用的是tensorflow,這個可以實時的版本用的是pytorch,能夠把pytorch這個版本的模型轉換成tensorflow的嗎?效果一樣的嗎?剛接觸深度學習,虛心請教
謝謝
-
Hi once again me,
I am currently training a yolov3 (not spp , with 608x608 , 12 anchors and focal_loss =1, classes = 3) for
40 000 iterations.
The avg loss is currently about 0.55
The loss…