-
I am trying to train the model with a training schedule where the lr is reduced /10 every few epochs. For example, heads trained for 10 epochs at lr, 4+ for next 10 epochs at lr/10, all layers for ano…
-
### 请提出你的问题 Please ask your question
环境：
1）想编译最新版PaddlePaddle版本：3.0
2）CPU：Phytium,FT-2000+/64 aarch64
3）XPU：R200
4）系统环境：kylinv10
5）gcc/g++ ：8.2
6）python版本：3.9
安装方式
cm…
-
@AlexeyAB according to
https://github.com/AlexeyAB/darknet#how-to-improve-object-detection
I used
darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -height 416 to gene…
-
Hi, I encountered one bug while using the detector over video. I detects 'ghosts'. I noticed that it draw bounding boxes where people are not present. maybe it is something with the conversion to boun…
-
Hi Tony607,
Thank you for this mmdetection object detection demo. I got an issue when running the demo: !python tools/train.py {config_fname}
got these errors:
2019-10-02 09:08:06,271 - INFO -…
-
Hi
Im trying to detect multiple small and large objects (workers on the construction field can have small size if image was taken from far distance or large if it was closed). I include two sample …
-
Hi @AlexeyAB
how to generate out own anchors and set it against various masks for custom data using yolov3-tiny.cfg tinyyoloV3. I have read your instructions from
https://github.com/AlexeyAB/dar…
-
Help me to clear this KeyError :8
Traceback (most recent call last):
File "train.py", line 184, in
tf.app.run()
File "C:\Users\Sathiesh Kumar\AppData\Local\Continuum\anaconda3\envs\ret…
-
Generating anchor boxes for training images and annotation...
Average IOU for 9 anchors: 0.86
Anchor Boxes generated.
Detection configuration saved in /content/drive/My Drive/Dataset/json/detectio…
-
# YOLO V3
## Reference
- 2015 **YOLO V1** You Only Look Once: Unified, Real-Time Object Detection [[paper](https://arxiv.org/pdf/1506.02640.pdf)] [[netscope](http://ethereon.github.io/netscope/#…