Bailin He

TypeErrorTypeError: meshgrid() got an unexpected keyword argument 'indexing'

2

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question File "/mnt/data/anaconda/envs/yolov8/lib/python3.8/site-packages/ultralytics/nn/modules/transformer.py", line 107, in build_2d_sincos_position_embedding grid_w, grid_h =...

Creating custom datasets

1

Hello，thank you for your job。 I want to create my own MegaDepth dataset. How was the. h5 file corresponding to the image generated？

检测出来非常多的重叠框

6

既然是端到端的检测，不使用nms，是可以处理重叠问题的吧，而且我在推理的时候就算设置iou=0.5也是不起作用的 

How was pair_infos obtained in the npz file？

推理出来的特别多的检测框

3

使用的配置文件是co_dino_5scale_vit_large_coco.py这个配置，test_cfg的配置我把score_thr设置为0.9仍然没什么用，推理出来的框有1000个，就是设置的max_per_img=1000，好像score_thr和nms没有发挥作用？ ``` test_cfg=[ dict( max_per_img=1000, nms=dict(type='soft_nms', iou_threshold=0.8)), dict( rpn=dict( nms_pre=8000, max_per_img=2000, nms=dict(type='nms', iou_threshold=0.9), min_bbox_size=0), rcnn=dict( score_thr=0.9, mask_thr_binary=0.5, nms=dict(type='soft_nms', iou_threshold=0.5), max_per_img=1000)), dict( nms_pre=1000, min_bbox_size=0, score_thr=0.9, nms=dict(type='soft_nms', iou_threshold=0.6), max_per_img=100), # soft-nms is...

fp16 setting

3

Traceback (most recent call last): File "tools/train.py", line 245, in main() File "tools/train.py", line 241, in main meta=meta) File "/mnt/data/Co-DETR/tools/mmdet/apis/train.py", line 187, in train_detector elif distributed and 'type' not in...

在coco数据集上只使用12个epochs就足够了吗

1

我准备在自己的数据集上做训练，epochs用12会不会少了点？

How do you download an init checkpoint, such as init checkpoint：maskconver_seg_mnv3p5rf_coco_200k/43437096，Does it download automatically, or do I need to download it locally? If so, how can I find the download...

Maskconver pre-trained model couldn’t load

1

tensorflow/models/official/projects/maskconver/configs/experiments/maskconver_mobilenetv3p5_rf_640_coco.yaml where the init_checkpoint: 'maskconver_seg_mnv3p5rf_coco_200k/43437096' report an error:tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for maskconver_seg_mnv3p5rf_coco_200k/43437096

dataset

1

panoptic_semseg_train2017 panoptic_semseg_val2017 How are these two folders generated?