nmxnql

I think the coordinate loss is computed by error

2

In yolo_net.py line 278-281 ,the coordinate is wrong . The yolo paper says that "Each bounding box consists of 5 predictions: x, y, w, h, and confidence. The (x,y) coordinates...

when i train my own style transform network,it occures the follwing error: Number of ways to split should evenly divide the split dimension, but got split_dim 2 (size = 4)...

intersect_min = np.minimum(box_min, anchors_min) intersect_max = np.maximum(box_max, anchors_max) 这两句中的取极值写反了吧