axis 1 is out of bounds for array of dimension 1

# code:
https://www.kaggle.com/code/liuweiq/coincide-separation-detectron2-training
## Environment:
kaggle
# error:

```
[07/16 13:14:44 d2.engine.defaults]: Model:
GeneralizedRCNN(
(backbone): FPN(
(fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(top_block): LastLevelMaxPool()
(bottom_up): ResNet(
(stem): BasicStem(
(conv1): Conv2d(
3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
)
(res2): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv1): Conv2d(
64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
)
(res3): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv1): Conv2d(
256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
)
(res4): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv1): Conv2d(
512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(4): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(5): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
)
(res5): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv1): Conv2d(
1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
)
)
)
(proposal_generator): RPN(
(rpn_head): StandardRPNHead(
(conv): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
(activation): ReLU()
)
(objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
(anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
)
(anchor_generator): DefaultAnchorGenerator(
(cell_anchors): BufferList()
)
)
(roi_heads): StandardROIHeads(
(box_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
)
)
(box_head): FastRCNNConvFCHead(
(flatten): Flatten(start_dim=1, end_dim=-1)
(fc1): Linear(in_features=12544, out_features=1024, bias=True)
(fc_relu1): ReLU()
(fc2): Linear(in_features=1024, out_features=1024, bias=True)
(fc_relu2): ReLU()
)
(box_predictor): FastRCNNOutputLayers(
(cls_score): Linear(in_features=1024, out_features=3, bias=True)
(bbox_pred): Linear(in_features=1024, out_features=8, bias=True)
)
(mask_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(14, 14), spatial_scale=0.25, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
)
)
(mask_head): MaskRCNNConvUpsampleHead(
(mask_fcn1): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
(activation): ReLU()
)
(mask_fcn2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
(activation): ReLU()
)
(mask_fcn3): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
(activation): ReLU()
)
(mask_fcn4): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
(activation): ReLU()
)
(deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
(deconv_relu): ReLU()
(predictor): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
)
)
)
[07/16 13:14:44 d2.data.datasets.coco]: Loaded 161 images in COCO format from /kaggle/input/coco-data/instances.json
[07/16 13:14:44 d2.data.build]: Removed 0 images with no usable annotations. 161 images left.
[07/16 13:14:44 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip()]
[07/16 13:14:44 d2.data.build]: Using training sampler TrainingSampler
[07/16 13:14:44 d2.data.common]: Serializing the dataset using:
[07/16 13:14:44 d2.data.common]: Serializing 161 elements to byte tensors and concatenating them all ...
[07/16 13:14:44 d2.data.common]: Serialized dataset takes 0.11 MiB
[07/16 13:14:44 d2.data.build]: Making batched data loader with batch_size=2
[07/16 13:14:44 d2.checkpoint.detection_checkpoint]: [DetectionCheckpointer] Loading from https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl ...
[07/16 13:14:44 d2.engine.train_loop]: Starting training from iteration 0
[07/16 13:14:49 d2.utils.events]: eta: 0:08:08 iter: 19 total_loss: 2.388 loss_cls: 0.5612 loss_box_reg: 0.5152 loss_mask: 0.6743 loss_rpn_cls: 0.2725 loss_rpn_loc: 0.234 time: 0.2471 last_time: 0.2480 data_time: 0.0182 last_data_time: 0.0076 lr: 0.0005 max_mem: 2758M
[07/16 13:14:54 d2.utils.events]: eta: 0:08:10 iter: 39 total_loss: 1.896 loss_cls: 0.3904 loss_box_reg: 0.7147 loss_mask: 0.5105 loss_rpn_cls: 0.0675 loss_rpn_loc: 0.2052 time: 0.2511 last_time: 0.2110 data_time: 0.0075 last_data_time: 0.0074 lr: 0.0005 max_mem: 2758M
[07/16 13:14:59 d2.utils.events]: eta: 0:08:03 iter: 59 total_loss: 1.697 loss_cls: 0.3442 loss_box_reg: 0.682 loss_mask: 0.3977 loss_rpn_cls: 0.0367 loss_rpn_loc: 0.187 time: 0.2512 last_time: 0.2547 data_time: 0.0082 last_data_time: 0.0085 lr: 0.0005 max_mem: 2760M
[07/16 13:15:04 d2.utils.events]: eta: 0:08:00 iter: 79 total_loss: 1.581 loss_cls: 0.311 loss_box_reg: 0.681 loss_mask: 0.3736 loss_rpn_cls: 0.02267 loss_rpn_loc: 0.1788 time: 0.2510 last_time: 0.2624 data_time: 0.0079 last_data_time: 0.0081 lr: 0.0005 max_mem: 2760M
[07/16 13:15:09 d2.utils.events]: eta: 0:07:54 iter: 99 total_loss: 1.489 loss_cls: 0.3167 loss_box_reg: 0.6183 loss_mask: 0.3583 loss_rpn_cls: 0.01854 loss_rpn_loc: 0.1595 time: 0.2506 last_time: 0.2538 data_time: 0.0079 last_data_time: 0.0074 lr: 0.0005 max_mem: 2760M
[07/16 13:15:15 d2.utils.events]: eta: 0:07:51 iter: 119 total_loss: 1.481 loss_cls: 0.3209 loss_box_reg: 0.6435 loss_mask: 0.3739 loss_rpn_cls: 0.01431 loss_rpn_loc: 0.1781 time: 0.2525 last_time: 0.2795 data_time: 0.0081 last_data_time: 0.0086 lr: 0.0005 max_mem: 2760M
[07/16 13:15:20 d2.utils.events]: eta: 0:07:48 iter: 139 total_loss: 1.421 loss_cls: 0.2869 loss_box_reg: 0.6089 loss_mask: 0.3471 loss_rpn_cls: 0.009652 loss_rpn_loc: 0.1751 time: 0.2532 last_time: 0.2746 data_time: 0.0076 last_data_time: 0.0076 lr: 0.0005 max_mem: 2760M
[07/16 13:15:25 d2.utils.events]: eta: 0:07:42 iter: 159 total_loss: 1.42 loss_cls: 0.297 loss_box_reg: 0.6114 loss_mask: 0.3572 loss_rpn_cls: 0.01175 loss_rpn_loc: 0.1626 time: 0.2536 last_time: 0.2537 data_time: 0.0074 last_data_time: 0.0081 lr: 0.0005 max_mem: 2760M
[07/16 13:15:30 d2.utils.events]: eta: 0:07:36 iter: 179 total_loss: 1.343 loss_cls: 0.2586 loss_box_reg: 0.5469 loss_mask: 0.3461 loss_rpn_cls: 0.009276 loss_rpn_loc: 0.1687 time: 0.2530 last_time: 0.2379 data_time: 0.0082 last_data_time: 0.0081 lr: 0.0005 max_mem: 2760M
[07/16 13:15:35 d2.utils.events]: eta: 0:07:31 iter: 199 total_loss: 1.45 loss_cls: 0.2805 loss_box_reg: 0.6134 loss_mask: 0.3579 loss_rpn_cls: 0.008294 loss_rpn_loc: 0.173 time: 0.2525 last_time: 0.2530 data_time: 0.0081 last_data_time: 0.0081 lr: 0.0005 max_mem: 2760M
[07/16 13:15:40 d2.utils.events]: eta: 0:07:26 iter: 219 total_loss: 1.382 loss_cls: 0.2553 loss_box_reg: 0.5704 loss_mask: 0.3324 loss_rpn_cls: 0.009328 loss_rpn_loc: 0.1638 time: 0.2528 last_time: 0.2514 data_time: 0.0082 last_data_time: 0.0073 lr: 0.0005 max_mem: 2760M
[07/16 13:15:45 d2.utils.events]: eta: 0:07:22 iter: 239 total_loss: 1.34 loss_cls: 0.2805 loss_box_reg: 0.5728 loss_mask: 0.3491 loss_rpn_cls: 0.01016 loss_rpn_loc: 0.1435 time: 0.2536 last_time: 0.2491 data_time: 0.0078 last_data_time: 0.0079 lr: 0.0005 max_mem: 2760M
[07/16 13:15:49 d2.data.datasets.coco]: Loaded 135 images in COCO format from /kaggle/input/coco-data-val/instances.json
[07/16 13:15:49 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(800, 800), max_size=1333, sample_style='choice')]
[07/16 13:15:49 d2.data.common]: Serializing the dataset using:
[07/16 13:15:49 d2.data.common]: Serializing 135 elements to byte tensors and concatenating them all ...
[07/16 13:15:49 d2.data.common]: Serialized dataset takes 0.02 MiB
[07/16 13:15:49 d2.data.datasets.coco]: Loaded 135 images in COCO format from /kaggle/input/coco-data-val/instances.json
[07/16 13:15:49 d2.evaluation.evaluator]: Start inference on 135 batches
ERROR [07/16 13:15:49 d2.engine.train_loop]: Exception during training:
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/site-packages/detectron2/engine/train_loop.py", line 156, in train
self.after_step()
File "/opt/conda/lib/python3.10/site-packages/detectron2/engine/train_loop.py", line 190, in after_step
h.after_step()
File "/opt/conda/lib/python3.10/site-packages/detectron2/engine/hooks.py", line 556, in after_step
self._do_eval()
File "/opt/conda/lib/python3.10/site-packages/detectron2/engine/hooks.py", line 529, in _do_eval
results = self._func()
File "/opt/conda/lib/python3.10/site-packages/detectron2/engine/defaults.py", line 457, in test_and_save_results
self._last_eval_results = self.test(self.cfg, self.model)
File "/opt/conda/lib/python3.10/site-packages/detectron2/engine/defaults.py", line 621, in test
results_i = inference_on_dataset(model, data_loader, evaluator)
File "/opt/conda/lib/python3.10/site-packages/detectron2/evaluation/evaluator.py", line 172, in inference_on_dataset
evaluator.process(inputs, outputs)
File "/tmp/ipykernel_34/3164767280.py", line 37, in process
self.scores.append(score(out, targ))
File "/tmp/ipykernel_34/3164767280.py", line 18, in score
tp, fp, fn = precision_at(t, ious)
File "/tmp/ipykernel_34/3164767280.py", line 6, in precision_at
true_positives = np.sum(matches, axis=1) == 1 # Correct objects
File "/opt/conda/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 2313, in sum
return _wrapreduction(a, np.add, 'sum', axis, dtype, out, keepdims=keepdims,
File "/opt/conda/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 88, in _wrapreduction
return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
numpy.exceptions.AxisError: axis 1 is out of bounds for array of dimension 1
[07/16 13:15:49 d2.engine.hooks]: Overall training speed: 247 iterations in 0:01:02 (0.2544 s / it)
[07/16 13:15:49 d2.engine.hooks]: Total training time: 0:01:04 (0:00:01 on hooks)
[07/16 13:15:49 d2.utils.events]: eta: 0:07:19 iter: 249 total_loss: 1.29 loss_cls: 0.2537 loss_box_reg: 0.5709 loss_mask: 0.3331 loss_rpn_cls: 0.009182 loss_rpn_loc: 0.1365 time: 0.2534 last_time: 0.2509 data_time: 0.0077 last_data_time: 0.0082 lr: 0.0005 max_mem: 2760M
---------------------------------------------------------------------------
AxisError Traceback (most recent call last)
Cell In[9], line 34
32 trainer = Trainer(cfg) # without data augmentation
33 trainer.resume_or_load(resume=False)
---> 34 trainer.train()

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/defaults.py:488, in DefaultTrainer.train(self)
481 def train(self):
482 """
483 Run training.
484
485 Returns:
486 OrderedDict of results, if evaluation is enabled. Otherwise None.
487 """
--> 488 super().train(self.start_iter, self.max_iter)
489 if len(self.cfg.TEST.EXPECTED_RESULTS) and comm.is_main_process():
490 assert hasattr(
491 self, "_last_eval_results"
492 ), "No evaluation results obtained during training!"

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/train_loop.py:156, in TrainerBase.train(self, start_iter, max_iter)
154 self.before_step()
155 self.run_step()
--> 156 self.after_step()
157 # self.iter == max_iter can be used by `after_train` to
158 # tell whether the training successfully finished or failed
159 # due to exceptions.
160 self.iter += 1

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/train_loop.py:190, in TrainerBase.after_step(self)
188 def after_step(self):
189 for h in self._hooks:
--> 190 h.after_step()

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/hooks.py:556, in EvalHook.after_step(self)
553 if self._period > 0 and next_iter % self._period == 0:
554 # do the last eval in after_train
555 if next_iter != self.trainer.max_iter:
--> 556 self._do_eval()

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/hooks.py:529, in EvalHook._do_eval(self)
528 def _do_eval(self):
--> 529 results = self._func()
531 if results:
532 assert isinstance(
533 results, dict
534 ), "Eval function must return a dict. Got {} instead.".format(results)

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/defaults.py:457, in DefaultTrainer.build_hooks..test_and_save_results()
456 def test_and_save_results():
--> 457 self._last_eval_results = self.test(self.cfg, self.model)
458 return self._last_eval_results

File /opt/conda/lib/python3.10/site-packages/detectron2/engine/defaults.py:621, in DefaultTrainer.test(cls, cfg, model, evaluators)
619 results[dataset_name] = {}
620 continue
--> 621 results_i = inference_on_dataset(model, data_loader, evaluator)
622 results[dataset_name] = results_i
623 if comm.is_main_process():

File /opt/conda/lib/python3.10/site-packages/detectron2/evaluation/evaluator.py:172, in inference_on_dataset(model, data_loader, evaluator, callbacks)
169 total_compute_time += time.perf_counter() - start_compute_time
171 start_eval_time = time.perf_counter()
--> 172 evaluator.process(inputs, outputs)
173 total_eval_time += time.perf_counter() - start_eval_time
175 iters_after_start = idx + 1 - num_warmup * int(idx >= num_warmup)

Cell In[7], line 37, in MAPIOUEvaluator.process(self, inputs, outputs)
35 else:
36 targ = self.annotations_cache[inp['image_id']]
---> 37 self.scores.append(score(out, targ))

Cell In[7], line 18, in score(pred, targ)
16 prec = []
17 for t in np.arange(0.5, 1.0, 0.05):
---> 18 tp, fp, fn = precision_at(t, ious)
19 p = tp / (tp + fp + fn)
20 prec.append(p)

Cell In[7], line 6, in precision_at(threshold, iou)
4 def precision_at(threshold, iou):
5 matches = iou > threshold
----> 6 true_positives = np.sum(matches, axis=1) == 1 # Correct objects
7 false_positives = np.sum(matches, axis=0) == 0 # Missed objects
8 false_negatives = np.sum(matches, axis=1) == 0 # Extra objects

File /opt/conda/lib/python3.10/site-packages/numpy/core/fromnumeric.py:2313, in sum(a, axis, dtype, out, keepdims, initial, where)
2310 return out
2311 return res
-> 2313 return _wrapreduction(a, np.add, 'sum', axis, dtype, out, keepdims=keepdims,
2314 initial=initial, where=where)

File /opt/conda/lib/python3.10/site-packages/numpy/core/fromnumeric.py:88, in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs)
85 else:
86 return reduction(axis=axis, out=out, **passkwargs)
---> 88 return ufunc.reduce(obj, axis, dtype, out, **passkwargs)

AxisError: axis 1 is out of bounds for array of dimension 1
```

Start by opening the linked Kaggle notebook and reproducing the reported error in its environment, then inspect the full traceback beyond the model summary. Done means identifying whether the failure is in Detectron2 or the notebook's data/configuration and documenting a reproducible cause and next step.

Written by the indexing model from the issue text.