poddo

> > > @layumi Thank you for your support. > I have split val set to `gallery` and `query` as following if it is right way: > > val/000341/ >...

I want to know how to train ocr too. and could we change the code for two layer plate recognition?

i trained my own dataset like voc datasets, but after trained 65 epochs its map is 0.0 and no boxes to nms, have you met this problem?

same issue.

in the readme.md, it says like that: PyTorch 1.3+ Torchvision 0.4.0+ (We need high version because Torchvision support nms now.) while the torchvision==0.4.0 should match torch==1.2.0, so which version of...

> > in the readme.md, it says like that: > > PyTorch 1.3+ > > Torchvision 0.4.0+ (We need high version because Torchvision support nms now.) > > while the...

thanks, just like the blog you wrote, change this line parser.add_argument('--network', default='efficientdet-d0', type=str, help='efficientdet-[d0, d1, ..]') to: parser.add_argument('--network', default='efficientdet-d1', type=str, help='efficientdet-[d0, d1, ..]') am i right? btw, i trained my...

i trained my own dataset like voc datasets, but after trained 65 epochs its map is 0.0 and no boxes to nms, have you met this problem?

Hi, i get this error when i trained my model over and start evaluate the model.  my val datasets contains 8871 images and the test batchsize is 8.

你好，请问下，我也是执行的sh. train_146.sh。但是trainval_net.py中--cfg这个参数不是默认的cfgs/res101_ls.yml吗？但是这个res101_ls.yml在cfgs下面并没有啊，还有我设置的resume为False，不管是默认还是传入--r False，但是出来的结果还是为True，你有遇到这个问题吗？