Open Frank-qlu opened 4 years ago
已解决
请问训练自己数据集,检测效果怎么样啊?
请问训练自己数据集,检测效果怎么样啊? 正在训练
@Frank-qlu 怎么解决的 我也有同样的问题
Hi, i am also getting the same error.
IndexError: index 76 is out of bounds for axis 1 with size 76
.
I am using custom dataset with training.txt file in the following manner
./complete/imgs/CAR00718.jpg0.851124,0.291667,0.196629,0.125000,15
be sure that " 0<=xmax <= width and 0<=ymax<=height "
已解决
大佬可以讲述一下怎么回事吗?
已解决
您好 请问您是怎么解决这个问题的?
您好,问一下您怎么解决的
您好,问一下您怎么解决的
确实是因为数据集的label问题,你生成annotation文件的时候注意检查label的正确性就可以。
更换数据集后,.names换成一类,训练时候dataset.py 244行报错,请问什么原因,怎么解决? Instructions for updating: Use standard file APIs to check for files with this prefix. 0%| | 0/17 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 184, in
if name == 'main': YoloTrain().train()
File "train.py", line 144, in train
for train_data in pbar:
File "F:\Lee\tensorflow_for_YOLOv3\venv\lib\site-packages\tqdm\std.py", line 1081, in iter
for obj in iterable:
File "F:\Lee\tensorflow-yolov3-master\core\dataset.py", line 82, in next
label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = self.preprocess_true_boxes(bboxes)
File "F:\Lee\tensorflow-yolov3-master\core\dataset.py", line 244, in preprocess_true_boxes
label[best_detect][yind, xind, best_anchor, :] = 0
IndexError: index 52 is out of bounds for axis 1 with size 52
0%| | 0/17 [00:00<?, ?it/s]