yolov2
yolov2 copied to clipboard
YOLOv2 Implementation in TF/Keras. Allowing to experiment on different feature detectors (MobileNet, Darknet-19). Paper: https://arxiv.org/abs/1612.08242
 what is Ci?
from yolov2.zoo import yolov2_darknet19
my training datasets contains 12300*8 data ,and my calsss is 3, my learning rate is 0.0001. I train it with yolo-coco.weights as initial weights,and just after two epoch ,the val_loss...
Hi Dat, I just wonder why when create y_batch, you don't consider about prior-anchor(created by k-mean clustering) `xc, yc, w, h = bbox.to_relative_size((float(width), float(height)))` `object_mask = np.concatenate([[xc, yc, w, h],...
Hi Dat, It looks like there is a bug around the line https://github.com/dat-ai/yolov2/blob/master/models/YOLOv2.py#L346 I'm not 100% sure, but it looks like there's some value range mismatch: At first, there's ground...
Hi Dat I could not found out some points for putting a yolo config file so I guess the yolo structure would be defined in the pretrained weight. Please correct...
I tried to use this for detection. it was not accurate. why so?