jjungm4155

안녕하세요, 강사님.저번 train_detector(model, datasets, cfg, distributed=False, validate=False)으로 일단 코드를 고쳐서 돌려보라고 주신 답변에 학습은 잘 되었습니다. 감사드립니다!이번에는 mm_mask_rcnn_train_balloon 같은 코드를 custom 데이터셋에서 클래스를 하나에서 두개로 추가하여 돌리고 있는 중입니다. <pre class="hljs"><code># epochs는 config의 runner 파라미터로 지정됨. 기본 12회 
train_detector(model, datasets, cfg, distributed=False, validate=False)</code></pre>이번에는 여기서 'NoneType' object has no attribute 'get' 오류가 떠서 해결을 못하고 있는데 혹시 도움을 주실 수 있으실까요?<img src="https://cdn.inflearn.com/public/files/posts/d0885e4d-95ac-4edb-a0a1-fce33a740a53/image.png" alt="image" title="image">

Segmentation

추가적으로 mm_mask_rcnn_train_balloon 를 구글 코랩에서 학습을 시킬 때 <img src="https://cdn.inflearn.com/public/files/posts/45152014-515b-479d-8459-a5a293643d5a/image.png" alt="image" title="image">이 부분에서 "세션이 다운되었습니다." 라는 경고창이 뜨면서 학습이 중단되어서function ClickConnect()도 콘솔창에 붙여넣어보고 코랩 pro 버전도 사보았는데 똑같은 문제가 계속 발생해서 학습이 완료되지 않습니다. 무엇이 문제인지 여쭤봐도 될까요?아래는 세션이 다운되었습니다 경고창이 뜨면서 나타난 결과창입니다..!<pre class="hljs"><code>2023-03-28 02:17:28,439 - mmdet - INFO - Automatic scaling of learning rate (LR) has been disabled.
2023-03-28 02:17:28,450 - mmdet - INFO - load checkpoint from local path: /content/mmdetection/checkpoints/mask_rcnn_r101_fpn_1x_coco_20200204-1efe0ed5.pth
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
2023-03-28 02:17:28,700 - mmdet - WARNING - The model and loaded state dict do not match exactly

size mismatch for roi_head.bbox_head.fc_cls.weight: copying a param with shape torch.Size([81, 1024]) from checkpoint, the shape in current model is torch.Size([2, 1024]).
size mismatch for roi_head.bbox_head.fc_cls.bias: copying a param with shape torch.Size([81]) from checkpoint, the shape in current model is torch.Size([2]).
size mismatch for roi_head.bbox_head.fc_reg.weight: copying a param with shape torch.Size([320, 1024]) from checkpoint, the shape in current model is torch.Size([4, 1024]).
size mismatch for roi_head.bbox_head.fc_reg.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([4]).
size mismatch for roi_head.mask_head.conv_logits.weight: copying a param with shape torch.Size([80, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 256, 1, 1]).
size mismatch for roi_head.mask_head.conv_logits.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([1]).
2023-03-28 02:17:28,709 - mmdet - INFO - Start running, host: root@21ec773421f3, work_dir: /content/tutorial_exps
2023-03-28 02:17:28,710 - mmdet - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH ) StepLrUpdaterHook 
(NORMAL ) CheckpointHook 
(LOW ) EvalHook 
(VERY_LOW ) TextLoggerHook 
 -------------------- 
before_train_epoch:
(VERY_HIGH ) StepLrUpdaterHook 
(NORMAL ) NumClassCheckHook 
(LOW ) IterTimerHook 
(LOW ) EvalHook 
(VERY_LOW ) TextLoggerHook 
 -------------------- 
before_train_iter:
(VERY_HIGH ) StepLrUpdaterHook 
(LOW ) IterTimerHook 
(LOW ) EvalHook 
 -------------------- 
after_train_iter:
(ABOVE_NORMAL) OptimizerHook 
(NORMAL ) CheckpointHook 
(LOW ) IterTimerHook 
(LOW ) EvalHook 
(VERY_LOW ) TextLoggerHook 
 -------------------- 
after_train_epoch:
(NORMAL ) CheckpointHook 
(LOW ) EvalHook 
(VERY_LOW ) TextLoggerHook 
 -------------------- 
before_val_epoch:
(NORMAL ) NumClassCheckHook 
(LOW ) IterTimerHook 
(VERY_LOW ) TextLoggerHook 
 -------------------- 
before_val_iter:
(LOW ) IterTimerHook 
 -------------------- 
after_val_iter:
(LOW ) IterTimerHook 
 -------------------- 
after_val_epoch:
(VERY_LOW ) TextLoggerHook 
 -------------------- 
after_run:
(VERY_LOW ) TextLoggerHook 
 -------------------- 
2023-03-28 02:17:28,713 - mmdet - INFO - workflow: [('train', 1)], max: 36 epochs
2023-03-28 02:17:28,717 - mmdet - INFO - Checkpoints will be saved to /content/tutorial_exps by HardDiskBackend.
2023-03-28 02:18:51,959 - mmdet - INFO - Saving checkpoint at 12 epochs
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 5/5, 1.3 task/s, elapsed: 4s, ETA: 0s2023-03-28 02:18:58,414 - mmdet - INFO - Evaluating bbox...
2023-03-28 02:18:58,446 - mmdet - INFO - 
 Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.112
 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.205
 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.065
 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.200
 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.018
 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = -1.000
 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.272
 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.272
 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.272
 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.400
 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.071
 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = -1.000

2023-03-28 02:18:58,447 - mmdet - INFO - Evaluating segm...
/usr/local/lib/python3.9/dist-packages/mmdet-2.28.2-py3.9.egg/mmdet/datasets/coco.py:470: UserWarning: The key "bbox" is deleted for more accurate mask AP of small/medium/large instances since v2.12.0. This does not change the overall mAP calculation.
 warnings.warn(
2023-03-28 02:18:58,480 - mmdet - INFO - 
 Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.077
 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.209
 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.008
 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.136
 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.015
 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = -1.000
 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.250
 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.250
 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.250
 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.382
 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.043
 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = -1.000

2023-03-28 02:18:58,481 - mmdet - INFO - Epoch(val) [12][5]	bbox_mAP: 0.1117, bbox_mAP_50: 0.2054, bbox_mAP_75: 0.0645, bbox_mAP_s: 0.2002, bbox_mAP_m: 0.0178, bbox_mAP_l: -1.0000, bbox_mAP_copypaste: 0.1117 0.2054 0.0645 0.2002 0.0178 -1.0000, segm_mAP: 0.0770, segm_mAP_50: 0.2095, segm_mAP_75: 0.0079, segm_mAP_s: 0.1363, segm_mAP_m: 0.0149, segm_mAP_l: -1.0000, segm_mAP_copypaste: 0.0770 0.2095 0.0079 0.1363 0.0149 -1.0000
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=0.02s).
Accumulating evaluation results...
DONE (t=0.01s).
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *segm*
DONE (t=0.02s).
Accumulating evaluation results...
DONE (t=0.01s).</code></pre>

jjungm4155

Posts