Fewshot_Detection Problems for programing details.

Sorry for troubling you, but I don't know how to compute loss for meta-model and feature-extractor.

In my idea, we'll have predict vector with shape (B, N, 13, 13, A, (5+N)) after feature reweighting, where B is batch, N is classes and A is anchors. If so, should I split my ground truth to N vectors according to different classes and compute loss for each channel of N in predict vector? And the second question is the loss for meta-model and feature-extractor is the same one?

I fondly anticipate your reply, thanks.

Oct 22 '19 10:10 b10232031

Hi, actually, the shape for prediction is (B, N, 13, 13, A, (5+1)). In RegionLoss the number of classes is actually 1 instead of N, as shown in the config file athttps://github.com/bingykang/Fewshot_Detection/blob/20c0580356e273cd69ac16ae327226649419b44b/cfg/darknet_dynamic.cfg#L259.

Oct 23 '19 05:10 bingykang

Thanks for your correction, I'll try it later.

Oct 23 '19 06:10 b10232031

Hi, actually, the shape for prediction is (B, N, 13, 13, A, (5+1)). In RegionLoss the number of classes is actually 1 instead of N, as shown in the config file at

https://github.com/bingykang/Fewshot_Detection/blob/20c0580356e273cd69ac16ae327226649419b44b/cfg/darknet_dynamic.cfg#L259

.

So this means that model can only predict only 1 class? Because the model I retrain can only detect 1 class.

Nov 20 '19 07:11 yeefulian

The result is strange, I wonder that the model can only predict only one class ? predictions

Jun 04 '20 03:06 infrontofme

Hi, actually, the shape for prediction is (B, N, 13, 13, A, (5+1)). In RegionLoss the number of classes is actually 1 instead of N, as shown in the config file at https://github.com/bingykang/Fewshot_Detection/blob/20c0580356e273cd69ac16ae327226649419b44b/cfg/darknet_dynamic.cfg#L259

.

So this means that model can only predict only 1 class? Because the model I retrain can only detect 1 class.

Hi,could you please tell me which cfg file do you use while running detect.py,I just got so many bounding box in one picture and any of them are wrong bounding boxes！！

Dec 20 '20 12:12 YzLrc

The result is strange, I wonder that the model can only predict only one class ?

您好武汉的前辈我跑该源码时我遇到了如下问题这个问题前面也有人提到过但并未得到解答您可以解决吗？有偿 “ ”

Sep 18 '21 09:09 ZZY-666

The result is strange, I wonder that the model can only predict only one class ?

您好武汉的前辈我跑该源码时我遇到了如下问题这个问题前面也有人提到过但并未得到解答您可以解决吗？有偿 “ ”

我当时也遇到了相同的问题，原因是我更变了gpu的数量，一定要在配置文件中修改gpu的数量，比如有两块gpu，就是ngpu=0,1

May 02 '23 12:05 wxhnibr