ssd.pytorch line 83, in __call__\n label_idx = self.class_to

line 83, in call\n label_idx = self.class_to_ind[name]\nKeyError:

Open sxyxf66 opened this issue 5 years ago • 11 comments

May 08 '19 08:05 sxyxf66

when i use my dataset, i have the problem KeyError: 'Traceback (most recent call last):\n File "C:\Program Files\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 138, in _worker_loop\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "C:\Program Files\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 138, in \n samples = collate_fn([dataset[i] for i in batch_indices])\n File "F:\pychqarmtestdemo\ssd.pytorch-master\data\voc0712.py", line 126, in getitem\n im, gt, h, w = self.pull_item(index)\n File "F:\pychqarmtestdemo\ssd.pytorch-master\data\voc0712.py", line 141, in pull_item\n target = self.target_transform(target, width, height)\n File "F:\pychqarmtestdemo\ssd.pytorch-master\data\voc0712.py", line 83, in call\n label_idx = self.class_to_ind[name]\nKeyError: 'feng'\n

feng is the lable name

May 08 '19 08:05 sxyxf66

you can use VOC_CLASSES = [( 'feng')] instead

May 13 '19 12:05 LeiGan0215

I have the same question,do you solve it? and how?

Oct 24 '19 13:10 liujiale1234

您可以改用VOC_CLASSES = [（ 'feng'）] it doesnt work

Oct 24 '19 13:10 liujiale1234

您可以改用VOC_CLASSES = [（ 'feng'）] it doesnt work

您好！我遇到了同样的问题，您解决了吗？可以探讨一下！

Feb 07 '20 00:02 zeroorhero

没有()发自我的华为手机-------- 原始邮件 --------发件人： zeroorhero [email protected]日期： 2020年2月7日周五早上8:49收件人： "amdegroot/ssd.pytorch" [email protected]抄送： sxyxf66 [email protected], Author [email protected]主题： Re: [amdegroot/ssd.pytorch] line 83, in call\n label_idx = self.class_to_ind[name]\nKeyError: (#343)

您可以改用VOC_CLASSES = [（

'feng'）]

it doesnt work

您好！我遇到了同样的问题，您解决了吗？可以探讨一下！

—You are receiving this because you authored the thread.Reply to this email directly, view it on GitHub, or unsubscribe.

Feb 10 '20 02:02 sxyxf66

没有()发自我的华为手机-------- 原始邮件 --------发件人： zeroorhero [email protected]日期： 2020年2月7日周五早上8:49收件人： "amdegroot/ssd.pytorch" [email protected]抄送： sxyxf66 [email protected], Author [email protected]主题： Re: [amdegroot/ssd.pytorch] line 83, in call\n label_idx = self.class_to_ind[name]\nKeyError: (#343) 您可以改用VOC_CLASSES = [（ 'feng'）] it doesnt work 您好！我遇到了同样的问题，您解决了吗？可以探讨一下！ —You are receiving this because you authored the thread.Reply to this email directly, view it on GitHub, or unsubscribe.

作者您好，遇到了一样的问题，请问你们解决了吗之前