Y.W

why i first run train.py then run yolo.py . having an issue

13

I first run train.py then model.save '.h' files. But when I test it using yolo.py and change the load h5 file path. But it errors.... why

I have tested crop function in data augmentation for object function.. it sounds wrong

1

tl.prepro.obj_box_crop when I set “is_center=False, is_random=True ” the changed label is not in the correct position I just found.... did I use this function wrong? I cannot post pic...

应该是ckpt里面diffusion model部分按照论文的说法可以适配其他sd1.5的unet是吗？但是字典里面的key对齐有人成功了吗

[https://gluon.mxnet.io/chapter08_computer-vision/object-detection.html](url) It seems the network output the offset on (xmin, ymin, xmax, ymax) Because I see the output... But in the paper and before version [https://zh.gluon.ai/chapter_computer-vision/ssd.html#%E6%95%B0%E6%8D%AE%E9%9B%86](url) I seem the network...