Wang Zhaodi

I want to get the anchor setting of my dataset, the example you showed is as follows: pyodi train-config generation \\ $TINY_COCO_ANIMAL/annotations/train.json \\ --input-size [1280,720] \\ --n-ratios 3 --n-scales 3...

Hello，I found that results(AP50tiny) of some experiments are not provided here, like exp3.4. So where can I find the results to judge whether my training is right or not? Or...

It's already December 8th. @VisDrone

Excuse me, I noticed that you will implement multiple GPU training in Ampligraph 2.0. ( #89 ) I just wonder whether it's published? The training time is so long now....

老师，您好！ 我在D_Y_15K_V2数据集上进行Alinet的实验，为什么hits指标的结果基本为0呢？并且随着迭代，指标并没有上升，导致early stop。 我的语句为 python main_from_args.py ./args/alinet_args_15K.json D_Y_15K_V2 721_5fold/1/ 结果为 accurate results: hits@[1,5,10,50]=[0.029 0.038 0.152 0.933]%, mr=4695.347, mrr=0.001430,time=4.345s

Hello, I read your code and paper in recent days. However, I have one question. what does the pretrained model you share corresponds to ? The pixel-level, the feature-level or...