-
-
源码中的标签生成逻辑是：
1.利用预测框与gt的l1距离筛选出topk个锚点，再利用锚点与gt的l1距离筛选出topk个锚点，将之作为预选正例锚点。
2.将预选正例锚点依据iou与gt匹配，滤除与锚点iou小于0.15的预选正例锚点
3.将gt与预测框iou
-
Click to expand!
### Issue Type
Bug
### Source
binary
### Tensorflow Version
2.10
### Custom Code
No
### OS Platform and Distribution
Linux Ubuntu 20.04
### Mobile …
-
### Description of the bug | 错误描述
我在isseue看到了相似的问题，但他们的解决方式都不适合我。命令行运行报错。请大佬帮我看看。
magic-pdf == 0.6.2b1
### How to reproduce the bug | 如何复现
**1. 命令**
`magic-pdf pdf-command --pdf "testfile_1.pdf" …
-
I have trained Detectron2 for Page Layout Detection on a PC _with_ GPU and it is giving satisfactory results.
If I try to use the trained model on _non-CUDA_ Detectron2 environment on same PC, or a…
-
Master Issue : #10532
Tasks :
- [x] #11341
- [x] #11342
- [x] #11344
- [x] #11357 (folder is removed in main)
- [x] #11421
- [x] #11422
- [x] #11423
- [x] #11425
- [x] #11424
- [x] #11…
-
Thanks for your working. I found the test scale is 800, which is larger than it in other papers in this field.
-
Hi, thank you for your sharing.
I have an issue when I train on my own dataset. The model is not saved and the keypoint loss stay at 0.
Could you help me please ?
[here is the link to the fil…
eaedk updated
3 years ago
-
If you do not know the root cause of the problem, please post according to this template:
## Instructions To Reproduce the Issue:
Check https://stackoverflow.com/help/minimal-reproducible-exampl…
-
Right now Turicreate supports YOLO for object detection. YOLO is nice, but I've personally found Faster R-CNNs and SSDs to be more accurate and easier to train (but at the expense of model size). Comb…