-
hello,
I've just tried training on my own dataset 4 classes , 24 images.
but after 90k iterations loss has not progressed passed 1.56:
iter: 90000 loss: 1.5658 (1.5819) loss_cls: 0.0000 (0.0114…
-
## 🚀 Feature
A clear and concise description of the feature proposal.
## Motivation & Examples
Now, in Detectron2, AP of each class is calculated by IoU @ 0.50:0.95. Although i tried to find …
-
I dont know what the iou threshold in the F1 score of adjacency relationships is.
Beacuse the iou threshold in cell detect is 0.5, I want to know if the iou threshold in the F1 score of adjacency r…
-
I finetuned your base-class weight on MS COCO dataset using RTX4070ti after 100 epochs with the batch size of 1 while other hyperparamter settings remain the same in accordance with the scripts you pr…
-
Hi All,
I have around 39k training images of 500x500 size and in validation set is 10% of the entire dataset (~4800 images). My class to predict the mask for ground feature building in the aerial i…
-
How to reproduce:
- Run `cmd_test` with uncertainty active
See:
-
Hello,
I want to calculate `IoU class` (`Jaccard Index, commonly known as the PASCAL VOC intersection-over-union metric`) value for FCN models (FCN AlexNet and FCN-8s) to compare them with this lis…
-
So I've encountered this new problem which happens rarely but atleast once / epoch on my custom dataset where the iou's are empty and the code crashes. What needs to be changed to handle this case ele…
-
I have a customized dataset which image is 1600X1200 resolution, and a few kinds of labeled object's resolution is about 20X20. I train detector model with yolo-voc.cfg just modify the **classes** and…
lqian updated
6 years ago
-
你好，我在AI-TOD的test set上运行了detectors_cascade_rcnn_r50_aitod_rpn_nwd.py，但性能未达到论文中报告的精度（20.8 AP）。
我对detectors_cascade_rcnn_r50_aitod_rpn_nwd.py进行了以下修改：
1）在训练时，将detectors_cascade_rcnn_r50_aitod_rpn_nwd修改为…