ED-Pose icon indicating copy to clipboard operation
ED-Pose copied to clipboard

[ICLR 2023] Official implementation of the paper "Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation "

Results 17 ED-Pose issues
Sort by recently updated
recently updated
newest added

Thanks for your great works! We wonder why the last value of 'reference' from transformer is not utilized for getting final prediction. The progress of getting final prediction after calling...

Are we suppose to use `main.py` as endpoint for inference as well? I'd like to run inference on a single image (for single character) (no annotation) with provided checkpoints trained...

I want to try to train the coco dataset according to your prompt, but the following error is reported, and then I find the error source according to the prompt,...

Hallo, is there any script to visualize the annotations for the CrowdPose dataset? Thanks in advance.

Hi. I have a question about the reported metrics of Poseur in your paper. In the original Poseur paper, AP is 75.4 with ResNet-50 backbone. However, it is 74.2 in...

All keypoints seems to have the same score/confidence, which means all keypoints are used even when it's impossible to know the location. e.g. due to occlusion. Is this the expected...

usage: DETR training and evaluation script [-h] --config_file CONFIG_FILE [--options OPTIONS [OPTIONS ...]] [--dataset_file DATASET_FILE] [--coco_path COCO_PATH] [--remove_difficult] [--fix_size] [--output_dir OUTPUT_DIR] [--note NOTE] [--device DEVICE] [--seed SEED] [--resume RESUME] [--pretrain_model_path...

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.540 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.721 Average Precision...

Hello, has anyone successfully converted a PyTorch model of ED-Pose to ONNX? I've attempted the export, but it's progressing very slowly, so I'm uncertain if it will be completed successfully.