Lin-Zhipeng

I also tried the experiment. lr = 3e-5 batch_size = 8 > Epoch : 1 - loss : 0.0648 - acc: 0.9752 - val_loss : 0.0592 - val_acc: 0.9782 >Epoch...

> I have the same error，if I switch the lines 96,97 > loss_c = loss_c.view(num, -1) > loss_c[pos] = 0 > in multibox_loss.py, this error disappear. > But come with...

链接：https://pan.baidu.com/s/14kQlCinB6wJuRaF_pS3hxA 提取码：xb8w You can use this Baidu Drive link to download it.

I also meet the same question.Have you solved it?

That also solved my problem. Thanks.

I just run the demo.py to visualization results. I set the threshold is very small. You can copy the link to browser to see the picture.