Validaiton| TypeError: 'DataContainer' object is not subscriptable

[chrissyguo]

Encounter this error when procssessing validation

[ ] 0/4952, elapsed: 0s, ETA:Traceback (most recent call last):
File "./tools/train.py", line 267, in
main()
File "./tools/train.py", line 242, in main
distributed=distributed, validate=args.no_validate, timestamp=timestamp, meta=meta)
File "/home/bdggj/MI-AOD/mmdet/apis/train.py", line 120, in train_detector
runner.run(data_loaders_L, cfg.workflow, cfg.total_epochs)
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 161, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 43, in train
self.call_hook('after_train_epoch')
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/mmcv/runner/base_runner.py", line 298, in call_hook
getattr(hook, fn_name)(self)
File "/home/bdggj/MI-AOD/mmdet/core/evaluation/eval_hooks.py", line 71, in after_train_epoch
gpu_collect=self.gpu_collect)
File "/home/bdggj/MI-AOD/mmdet/apis/test.py", line 85, in multi_gpu_test
y_head = model(return_loss=False, rescale=True, **data)
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 705, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/bdggj/MI-AOD/mmdet/core/fp16/decorators.py", line 51, in new_func
return old_func(*args, **kwargs)
File "/home/bdggj/MI-AOD/mmdet/models/detectors/base.py", line 164, in forward
return self.forward_test(x, img_metas, return_box=return_box, **kwargs)
File "/home/bdggj/MI-AOD/mmdet/models/detectors/base.py", line 144, in forward_test
return self.simple_test(imgs[0], img_metas[0], return_box=return_box, **kwargs)
File "/home/bdggj/MI-AOD/mmdet/models/detectors/single_stage.py", line 109, in simple_test
y_head_loc_cls = self.bbox_head.get_bboxes(*outs, img_metas, rescale=rescale)
File "/home/bdggj/MI-AOD/mmdet/core/fp16/decorators.py", line 131, in new_func
return old_func(*args, **kwargs)
File "/home/bdggj/MI-AOD/mmdet/models/dense_heads/MIAOD_head.py", line 641, in get_bboxes
img_shape = img_metas[img_id]['img_shape']
TypeError: 'DataContainer' object is not subscriptable
Traceback (most recent call last):
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/torch/distributed/launch.py", line 340, in
main()
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/torch/distributed/launch.py", line 326, in main
sigkill_handler(signal.SIGTERM, None) # not coming back
File "/home/bdggj/anaconda3/envs/miaod/lib/python3.7/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler
raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/bdggj/anaconda3/envs/miaod/bin/python', '-u', './tools/train.py', '--local_rank=0', 'configs/MIAOD.py', '--launcher', 'pytorch']' returned non-zero exit status 1.
Killing subprocess 30225

[yuantn]

You can debug it to see what the format of img_metas is. It may be solved by adding [0] after it, like this:
img_shape = img_metas[0][img_id]['img_shape']

[chrissyguo]

Thanks for your reply!

The format of img_metas is 'DataContainer'. FYI

ETA:DataContainer([[{'filename': '/home/bdggj/Documents/data/voc/VOCdevkit/VOC2007/JPEGImages/000001.jpg', 'ori_filename': 'JPEGImages/000001.jpg', 'ori_shape': (500, 353, 3), 'img_shape': (850, 600, 3), 'pad_shape': (864, 608, 3), 'scale_factor': array([1.6997167, 1.7 , 1.6997167, 1.7 ], dtype=float32), 'flip': False, 'flip_direction': None, 'img_norm_cfg': {'mean': array([123.675, 116.28 , 103.53 ], dtype=float32), 'std': array([58.395, 57.12 , 57.375], dtype=float32), 'to_rgb': True}}]])

I also tried img_shape = img_metas[0][img_id]['img_shape'] but does not help.

I think this is a similar problem as #https://github.com/open-mmlab/mmdetection/issues/1501

But I do run this code on a GPU environment.

I have never met this problem when I training with two-stage detectors using mmdetection.

[yuantn]

I've met similar problem, and I think you can try these solutions, which may be useful:

1. img_shape = img_metas.data[img_id]['img_shape']

2. img_shape = img_metas['img_shape']

3. try other methods to read DataContainer, such as img_metas[0], img_metas.data, img_metas.data[0], img_metas[img_shape] and so on.

Hope these can help you. (It's a pity that I cannot debug these days.)

[chrissyguo]

Thank you so much!
img_metas.data[0] can work!

[wuliacbd]

你好，我这个之前也报这个错误，然后我也改了，为什么还是有TypeError: 'DataContainer' object is not subscriptable问题

[yuantn]

你好，请提供你的输出日志，以及对应的 img_metas 打印结果。

---

Hello, please provide your output log, and the corresponding img_metas result printed.

[wuliacbd]

我在终端输入python tools/train.py configs/MIAOD.py 运行没有问题，但是输入./script.sh 0时就有问题了

[yuantn]

我在终端输入python tools/train.py configs/MIAOD.py 运行没有问题，但是输入./script.sh 0时就有问题了

请提供你的输出日志。

---

Please provide your output log.

[wuliacbd]

[ &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;] 0/4952, elapsed: 0s, ETA:Traceback (most recent call last): &nbsp; File "./tools/train.py", line 257, in <module&gt; &nbsp; &nbsp; main() &nbsp; File "./tools/train.py", line 232, in main &nbsp; &nbsp; distributed=distributed, validate=args.no_validate, timestamp=timestamp, meta=meta) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/apis/train.py", line 120, in train_detector &nbsp; &nbsp; runner.run(data_loaders_L, cfg.workflow, cfg.total_epochs) &nbsp; File "/home/liugh/.conda/envs/miaod/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 161, in run &nbsp; &nbsp; epoch_runner(data_loaders[i], **kwargs) &nbsp; File "/home/liugh/.conda/envs/miaod/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 43, in train &nbsp; &nbsp; self.call_hook('after_train_epoch') &nbsp; File "/home/liugh/.conda/envs/miaod/lib/python3.7/site-packages/mmcv/runner/base_runner.py", line 298, in call_hook &nbsp; &nbsp; getattr(hook, fn_name)(self) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/core/evaluation/eval_hooks.py", line 71, in after_train_epoch &nbsp; &nbsp; gpu_collect=self.gpu_collect) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/apis/test.py", line 85, in multi_gpu_test &nbsp; &nbsp; y_head = model(return_loss=False, rescale=True, **data) &nbsp; File "/home/liugh/.conda/envs/miaod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl &nbsp; &nbsp; result = self.forward(*input, **kwargs) &nbsp; File "/home/liugh/.conda/envs/miaod/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 705, in forward &nbsp; &nbsp; output = self.module(*inputs[0], **kwargs[0]) &nbsp; File "/home/liugh/.conda/envs/miaod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl &nbsp; &nbsp; result = self.forward(*input, **kwargs) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/core/fp16/decorators.py", line 51, in new_func &nbsp; &nbsp; return old_func(*args, **kwargs) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/models/detectors/base.py", line 164, in forward &nbsp; &nbsp; return self.forward_test(x, img_metas, return_box=return_box, **kwargs) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/models/detectors/base.py", line 144, in forward_test &nbsp; &nbsp; return self.simple_test(imgs[0], img_metas[0], return_box=return_box, **kwargs) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/models/detectors/single_stage.py", line 109, in simple_test &nbsp; &nbsp; y_head_loc_cls = self.bbox_head.get_bboxes(*outs, img_metas, rescale=rescale) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/core/fp16/decorators.py", line 131, in new_func &nbsp; &nbsp; return old_func(*args, **kwargs) &nbsp; File "/home/liugh/MI-AOD-master/mmdet/models/dense_heads/MIAOD_head.py", line 636, in get_bboxes &nbsp; &nbsp; img_shape = img_metas[img_id]['img_shape'] TypeError: 'DataContainer' object does not support indexing 这是./script.sh 0的结果， 然后在使用python直接运行的时候已经出了1k的结果了 [&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;&gt;] 4952/4952, 74.0 task/s, elapsed: 67s, ETA:&nbsp; &nbsp; &nbsp;0s2022-04-20 15:41:02,700 - mmdet - INFO -&nbsp; +-------------+------+-------+--------+-------+ | class&nbsp; &nbsp; &nbsp; &nbsp;| gts&nbsp; | dets&nbsp; | recall | ap&nbsp; &nbsp; | +-------------+------+-------+--------+-------+ | aeroplane&nbsp; &nbsp;| 285&nbsp; | 923&nbsp; &nbsp;| 0.779&nbsp; | 0.663 | | bicycle&nbsp; &nbsp; &nbsp;| 337&nbsp; | 1090&nbsp; | 0.742&nbsp; | 0.612 | | bird&nbsp; &nbsp; &nbsp; &nbsp; | 459&nbsp; | 2388&nbsp; | 0.643&nbsp; | 0.471 | | boat&nbsp; &nbsp; &nbsp; &nbsp; | 263&nbsp; | 1780&nbsp; | 0.673&nbsp; | 0.422 | | bottle&nbsp; &nbsp; &nbsp; | 469&nbsp; | 3348&nbsp; | 0.422&nbsp; | 0.217 | | bus&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;| 213&nbsp; | 997&nbsp; &nbsp;| 0.836&nbsp; | 0.668 | | car&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;| 1201 | 4420&nbsp; | 0.839&nbsp; | 0.727 | | cat&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;| 358&nbsp; | 1036&nbsp; | 0.782&nbsp; | 0.643 | | chair&nbsp; &nbsp; &nbsp; &nbsp;| 756&nbsp; | 6845&nbsp; | 0.663&nbsp; | 0.372 | | cow&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;| 244&nbsp; | 1157&nbsp; | 0.738&nbsp; | 0.404 | | diningtable | 206&nbsp; | 1333&nbsp; | 0.772&nbsp; | 0.568 | | dog&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;| 489&nbsp; | 2055&nbsp; | 0.822&nbsp; | 0.630 | | horse&nbsp; &nbsp; &nbsp; &nbsp;| 348&nbsp; | 1900&nbsp; | 0.865&nbsp; | 0.630 | | motorbike&nbsp; &nbsp;| 325&nbsp; | 1340&nbsp; | 0.766&nbsp; | 0.626 | | person&nbsp; &nbsp; &nbsp; | 4528 | 19870 | 0.810&nbsp; | 0.640 | | pottedplant | 480&nbsp; | 2273&nbsp; | 0.442&nbsp; | 0.234 | | sheep&nbsp; &nbsp; &nbsp; &nbsp;| 242&nbsp; | 1115&nbsp; | 0.645&nbsp; | 0.444 | | sofa&nbsp; &nbsp; &nbsp; &nbsp; | 239&nbsp; | 1687&nbsp; | 0.824&nbsp; | 0.555 | | train&nbsp; &nbsp; &nbsp; &nbsp;| 282&nbsp; | 1130&nbsp; | 0.819&nbsp; | 0.711 | | tvmonitor&nbsp; &nbsp;| 308&nbsp; | 1912&nbsp; | 0.776&nbsp; | 0.593 | +-------------+------+-------+--------+-------+ | mAP&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;|&nbsp; &nbsp; &nbsp; |&nbsp; &nbsp; &nbsp; &nbsp;|&nbsp; &nbsp; &nbsp; &nbsp; | 0.542 | +-------------+------+-------+--------+-------+ 2022-04-20 15:41:02,866 - mmdet - INFO - Epoch [5][2000/2000]&nbsp; &nbsp;lr: 1.000e-04, mAP: 0.5415mAP: 0.5415

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Tianning ***@***.***&gt;; 发送时间: 2022年4月20日(星期三) 下午3:39 收件人: ***@***.***&gt;; 抄送: ***@***.***&gt;; ***@***.***&gt;; 主题: Re: [yuantn/MI-AOD] Validaiton| TypeError: &#39;DataContainer&#39; object is not subscriptable (#14) 我在终端输入python tools/train.py configs/MIAOD.py 运行没有问题，但是输入./script.sh 0时就有问题了 请提供你的输出日志。 Please provide your output log. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***&gt;

[yuantn]

请提供你对应的 img_metas 打印结果。

---

Please your corresponding img_metas printed result.