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

Hello Team, I have my own dataset for fish detection in COCO format. While testing, I am getting error in evaluation part. Seems like the inference result is in python...

I compared YOLO and CenterNet against FPS and MAP on my computer. Fps may vary in different computer environments, but at least the **fps on Centernet must be greater than...

After running `python demo.py ctdet --demo /path/to/image/or/folder/or/video --load_model ../models/ctdet_coco_dla_2x.pth`, i am getting an output like ``` Fix size testing. training chunk_sizes: [1] The output will be saved to /content/drive/MyDrive/CenterNet2/CenterNet/src/lib/../../exp/ctdet/default heads...

Hello @xingyizhou , I used my own dataset which consists of 13 keypoints ( eyes, ears are excluded) I checked the coco_hp.py and it has 17 key points. I made...

after running `./make.sh`, I am getting errors as follows- ``` Traceback (most recent call last): File "build.py", line 21, in raise ValueError('CUDA is not available') ValueError: CUDA is not available...

Hello, does anyone know? why the model train using CPU instead of GPU? I already have 4 GPU, but none of them are used for training.

I run dla_34 ctdet model on t4 and the inference time when I run test.py. ``` default |############################### | [1054/1056]|Tot: 0:02:09 |ETA: 0:00:01 |tot 0.122 |load 0.068 |pre 0.014 |net...

Is there CenterNet implementatation with ResNet50 backbone inherently implemented?

bbox[:2] = affine_transform(bbox[:2], trans_output) bbox[2:] = affine_transform(bbox[2:], trans_output) bbox = np.clip(bbox, 0, output_res - 1)