-
Hi,
I'm training the model on my custom dataset which has format similar to SemanticKITTI. I get good results during training on validation set:
```
val: 100%|██████████| 30/30 [00:46
-
### System information
- **What is the top-level directory of the model you are using**: /mrtstorage/users/
- **Have I written custom code (as opposed to using a stock example script provided in Ten…
-
I want to train my dataset, but I always get nan values. I have fife images of dataset. Would be very thankful if someone could help me. :)
Region 82 Avg IOU: 0.455252, Class: 0.582400, Obj: 0.58…
-
单类别小目标检测在yolo.py文件中修改confidence,nms_iou值对map,recall,precision结果没有作用？是confidence,nms_iou值不在yolo.py文件里面改吗？我看utitle.box.py和getmap.py文件都有 ，utitle.box.py改了confidence,nms_iou也没用，只有getmap.py文件改了confidence=0.…
-
作者您好：
感谢您的贡献！您的这篇论文我读了好多遍，源码也成功的复现了。
但我一直对您的这篇论文的CDN这一部分的改进有一点困惑：
假设某一张特征图有两个Init Anchors（一个IOU是0.7,另一个IOU是0.5），原来的Matching会直接把这两个Anchors直接预测给一个物体，但经过CDN后，CDN会把IOU为0.7的直接归为正样本，IOU为0.5的归类为负样本（…
-
In this portion of code from preprocessing.py:
```
def _change_obj_position(self, y_batch, anchors_map, idx, box, iou):
bkp_box = y_batch[idx[0], idx[1], idx[2], idx[3], 0:4].copy()**
…
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有报过同样bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/iss…
-
I wanted to point out that the line 269 in [augmentations.py](https://github.com/amdegroot/ssd.pytorch/blob/master/utils/augmentations.py) is incorrect:
```
if overlap.min() < min_iou and max_iou < …
-
I follow the instruction by README,yet get a very low AP ,i tried many times in different GPU,still got 69AP in MPII val set and 11.5AP in COCO val set. detail in the following:
root@db8a72eec293…
-
## Background
- 3가지 모델에 대해 (효석님, 동우님, 경륜 각각 1개씩) WBF로 앙상블을 한 결과 성능 대폭 상승함
- 여러 앙상블 실험을 통해 실험 결과를 공유할 예정
## Content
- parser 파라미터들을 간단하게 설명하자면,
- `--csv_folder_path` : 내가 앙상블하고 싶은 csv 파일들이 저장되어 …