Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] =-1.000

[white-black66]

Hello, when I do evaluation, run the following code, GPUS_PER_NODE=8 ./tools/run_dist_launch.sh $1 eval_r50 $2 configs/r50_eval_multi.sh and all the results are -1： Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] =-1.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] =-1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] =-1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000

Code hints please run evaluate() first,but I don't know what to do... Can you give me some advice?

[Zagreus98]

This looks like a problem with the evaluation dataset. What dataset are you using for evaluation?

[white-black66]

I am using my own dataset, each image frame contains multiple targets, the above question preliminarily determines that it may be a problem with JSON files, please ask me how is the JSON file of the dataset is generated? Thank you~

[Zagreus98]

@white-black66 Well I trained on my own dataset too. And I build the coco_vid format annotations inspired by this script. This implementation needs to be changed for you own dataset format. It should look similar to this. Also pay attention to the bbox format to be xywh.

[white-black66]

Thank you very much for your help, I used the code you provided to generate a JSON file, but the output is still -1, Can you give me your modified code for reference? thank you very much~

[ResonWang]

@white-black66 你好，请问你的问题后来解决了吗？我在自己的数据上使用这个模型，他的单帧模型结果正常，60% ，但多帧Map低于1%，不知道是为什么