cmjkqyl

'NoneType' object has no attribute 'update' when running Meta -RCNN

1

2023-06-17 14:01:26,887 - mmfewshot - INFO - Hooks will be executed in the following order: before_run: -------------------- 2023-06-17 14:01:26,888 - mmfewshot - INFO - workflow: [('train', 1)], max: 120000 iters...

Referring to README, the data is organized as follows: mmfewshot ├── mmfewshot ├── tools ├── configs ├── data │ ├── coco │ │ ├── annotations │ │ ├── train2014 │...

How can I get the corresponding RECALL when the iou threshold is 0.5？

5

I changed iou_thrs in mmdet/datasets/coco.py to [0.5], and then got the verification results as shown below.  I want to know if the 0.887 in the picture is the correct...

Why the mAP is lower after distillation in VOC?

1

I use retinanet to train and test on VOC dataset. I found that the accuracy of retinanet after training with FGD is even lower than the original retinanet. It seems...

I trained yolov4-pacsp-s on my own dataset and got: P=0.667 R=0.807 mAP50=80.9 the P is quite low and weird compared with the yolov4 trained on other repos, such as: P=92.7...

Thank you for your excellent work. How to batch evaluate the image quality in the path and output the average quality index？