cfzd / Ultra-Fast-Lane-Detection

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

test.py 运行报错:Format of lanes error

hwang12345 opened this issue · comments

使用1080p图像数据集训练模型,训练完成后使用test.py进行测试,运行报错:
merge test_model config
merge test_work_dir config
start testing...
use_aux:false
init cls
initialize_weights
100%|███████████████████████████████████████████| 49/49 [00:06<00:00, 7.69it/s]
Traceback (most recent call last):
File "/home/hw/project/LaneDetection/ultra-fast-lane-detection/evaluation/tusimple/lane.py", line 79, in bench_one_submit
a, p, n = LaneEval.bench(pred_lanes, gt_lanes, y_samples, run_time)
File "/home/hw/project/LaneDetection/ultra-fast-lane-detection/evaluation/tusimple/lane.py", line 31, in bench
raise Exception('Format of lanes error.')
Exception: Format of lanes error.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "test.py", line 48, in
eval_lane(net, cfg.dataset, cfg.data_root, cfg.test_work_dir, cfg.griding_num, False, distributed)
File "/home/hw/project/LaneDetection/ultra-fast-lane-detection/evaluation/eval_wrapper.py", line 164, in eval_lane
res = LaneEval.bench_one_submit(os.path.join(work_dir,exp_name + '.txt'),os.path.join(data_root,'test_label.json'))
File "/home/hw/project/LaneDetection/ultra-fast-lane-detection/evaluation/tusimple/lane.py", line 81, in bench_one_submit
raise Exception('Format of lanes error.')
Exception: Format of lanes error.
这个问题应该如何解决?