curvelanes的训练预测为0

[FriendChi]

使用python scripts/convert_curvelanes.py出现了下面的警告
Ultra-Fast-Lane-Detection-v2/scripts/convert_curvelanes.py:31: RankWarning: Polyfit may be poorly conditioned
curve1 = np.polyfit(line_y[:2], line_x[:2], deg = 1)
Ultra-Fast-Lane-Detection-v2/scripts/convert_curvelanes.py:71: RankWarning: Polyfit may be poorly conditioned
curve = np.polyfit(arr[1::2], arr[::2], min(len(arr[::2]) - 1, 3))
我先没有管这个警告后面正常训练，结果

40005.7s	229	width_lane: 5
40005.7s	230	iou_threshold: 0.5
40005.7s	231	im_width: 224
40005.7s	232	im_height: 224
40005.7s	233	x_factor: 0.0875
40005.7s	234	y_factor: 0.155556
40005.7s	235	-----------------------------------
40005.7s	236	Evaluating the results...
40009.2s	237	tp: 0 fp: 90428 fn: 0
40009.2s	238	no ground truth positive
40009.2s	239	finished process file
40009.2s	240	precision: 0
40009.2s	241	recall: -1
40009.2s	242	Fmeasure: 0
40009.2s	243	----------------------------------
40009.2s	244	res_curve 0.0
40009.2s	245	nearly no results!
40009.2s	246	0