CenterNet icon indicating copy to clipboard operation
CenterNet copied to clipboard

Object detection, 3D detection, and pose estimation using center point detection:

Results 152 CenterNet issues
Sort by recently updated
recently updated
newest added

(FR1) [root@localhost src]# python demo.py ctdet --demo ../images --load_model ../models/ctdet_coco_dla_2x.pth Traceback (most recent call last): File "demo.py", line 11, in from detectors.detector_factory import detector_factory File "/users_4/d00477216/4_CenterNet-master/src/lib/detectors/detector_factory.py", line 5, in from...

(measure) C:\Users\IFL\Desktop\Liu\Detector\CenterNet\src>python demo.py ctdet --demo webcam --load_model ../models/ctdet_coco_dla_2x.pth Fix size testing. training chunk_sizes: [32] The output will be saved to C:\Users\IFL\Desktop\Liu\Detector\CenterNet\src\lib\..\..\exp\ctdet\default heads {'hm': 80, 'wh': 2, 'reg': 2} Creating model......

Hi, Xingyi I notice that you set batch size to 1 while validating and testing, why not use larger batch size to make it fast? Any harm? Thx!

Hi, I'm interested in training your detector with hourglass but using my dataset. In particoular is composed by an half million basket images, so with just a 'people' cathegory. Trying...

When testing ,a test.json file is needed to compute APs shown in the picture. ![ee](https://user-images.githubusercontent.com/14086114/64930920-5fae4b80-d867-11e9-9620-f53cda42ef15.png) Usually no annotated test files are available.How to obtain numerical class predictions and bboxes results...

这个问题简单来讲其实不是个问题:在各种修改和操作了一番之后,发现coco数据的格式图似乎不太明确,val2017,train2017和test2017这几个存放图片的文件夹应该和 annotations是同一级目录,然后就没有报错了。

![image](https://user-images.githubusercontent.com/38750855/126446370-49b0f498-c200-4a25-9afc-14c2f7f81170.png) look https://github.com/ttanzhiqiang/onnx_tensorrt_project