在VOC数据集上训练遇见报错

[FelixCaae]

raise self.exc_type(msg)

ValueError: Caught ValueError in DataLoader worker process 7.
Original Traceback (most recent call last):
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 207, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/home/yww/MobileNetV3-SSD/vision/datasets/voc_dataset.py", line 65, in getitem
image, boxes, labels = self.transform(image, boxes, labels)
File "/home/yww/MobileNetV3-SSD/vision/ssd/data_preprocessing.py", line 34, in call
return self.augment(img, boxes, labels)
File "/home/yww/MobileNetV3-SSD/vision/transforms/transforms.py", line 55, in call
img, boxes, labels = t(img, boxes, labels)
File "/home/yww/MobileNetV3-SSD/vision/transforms/transforms.py", line 278, in call
if overlap.min() < min_iou and max_iou < overlap.max():
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/numpy/core/_methods.py", line 29, in _amin
return umr_minimum(a, axis, None, out, keepdims)
ValueError: zero-size array to reduction operation minimum which has no identity

怀疑是数据集的处理过程中出现0-size 的batch

[weidongmei123]

请问这部分您已经复现了吗？我也想用voc数据集训练，可是不知道怎么改配置代码

[shaoshengsong]

请问这部分您已经复现了吗？我也想用voc数据集训练，可是不知道怎么改配置代码

这里有个现成的使用VOC的,https://github.com/shaoshengsong/MobileNetV3-SSD-Compact-Version

[weidongmei123]

非常感谢作者！我看到您新发的代码啦，请问这个代码也是ubuntu系统的吗？或者说windows系统上可以兼容吗？您前面那个代码我这边运行报错EOFError：Ran out of input 和在您的GitHub上提问的人遇到的报错一样，请问这种报错原因是什么呢？ 发自我的iPhone

…

------------------ 原始邮件 ------------------ 发件人: shaoshengsong <notifications@github.com&gt; 发送时间: 2020年4月22日 11:12 收件人: shaoshengsong/MobileNetV3-SSD <MobileNetV3-SSD@noreply.github.com&gt; 抄送: weidongmei123 <303462500@qq.com&gt;, Comment <comment@noreply.github.com&gt; 主题: 回复：[shaoshengsong/MobileNetV3-SSD] 在VOC数据集上训练遇见报错 (#19) 请问这部分您已经复现了吗？我也想用voc数据集训练，可是不知道怎么改配置代码 这里有个现成的使用VOC的,https://github.com/shaoshengsong/MobileNetV3-SSD-Compact-Version — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[shaoshengsong]

MobileNetV3-SSD-Compact-Version/create_data_lists.py ，打开 ，换成您自己的数据集路径

[shaoshengsong]

Ubuntu18.04测过，windows没测

[tianyuluan]

raise self.exc_type(msg)

ValueError: Caught ValueError in DataLoader worker process 7.
Original Traceback (most recent call last):
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 207, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/home/yww/MobileNetV3-SSD/vision/datasets/voc_dataset.py", line 65, in getitem
image, boxes, labels = self.transform(image, boxes, labels)
File "/home/yww/MobileNetV3-SSD/vision/ssd/data_preprocessing.py", line 34, in call
return self.augment(img, boxes, labels)
File "/home/yww/MobileNetV3-SSD/vision/transforms/transforms.py", line 55, in call
img, boxes, labels = t(img, boxes, labels)
File "/home/yww/MobileNetV3-SSD/vision/transforms/transforms.py", line 278, in call
if overlap.min() < min_iou and max_iou < overlap.max():
File "/home/yww/anaconda3/envs/pytorch1.3/lib/python3.6/site-packages/numpy/core/_methods.py", line 29, in _amin
return umr_minimum(a, axis, None, out, keepdims)
ValueError: zero-size array to reduction operation minimum which has no identity

怀疑是数据集的处理过程中出现0-size 的batch

我也遇到了同样的问题，请问您解决了吗