YunYang1994 / tensorflow-yolov3

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"
https://yunyang1994.gitee.io/2018/12/28/YOLOv3-算法的一点理解/
MIT License
3.63k stars 1.36k forks source link

运行train.py,训练自己数据集,出现问题 #467

Open wy-use opened 4 years ago

wy-use commented 4 years ago

想问下 在运行 train.py 的时候 出现这样的问题 是什么原因呢? 54:21.558613: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 train loss: 53.78: 100%|████████████████████| 7889/7889 [07:29<00:00, 17.56it/s] Traceback (most recent call last): File "train.py", line 184, in if name == 'main': YoloTrain().train() File "train.py", line 161, in train for test_data in self.testset: File "/home/administrator/m1/yolo/人脸数据集/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 "/home/administrator/m1/yolo/人脸数据集/tensorflow-yolov3-master/core/dataset.py", line 244, in preprocess_true_boxes label[best_detect][yind, xind, best_anchor, :] = 0 IndexError: index 41 is out of bounds for axis 1 with size 40

请各位大佬指导一下

fxcdl commented 4 years ago

请问你解决了吗 我也遇到了这个问题

jinyixin621 commented 4 years ago

要用0作为第一个类别的class

CNUyue commented 4 years ago

你好,我也遇到了相同的问题,您解决了吗@wy-use

tuzhirun commented 4 years ago

你好,你的数据集是怎么配置的?他给的训练自己的步骤不太明白,谢谢了

nanshenwei commented 4 years ago

加一个backgroup到class.names作为第0个class