WenyaoZhang issues

Results 24 issues of


                                            WenyaoZhang

which node publish /image_elevation?

I want to add some other limitations of traversability, but I don't know how to correct the code and which CPP file?

there is an error when i apply it on

How to run on cifar_100?

Thanks for your great work! And I want to know how to run on cifar_100?

How to combine with CAM or Grad-CAM?

为什么训练时，在LFW数据集的得分一直是0.500000+-0.0000

我用的自己的模型，刚开始还是0.78多，后面就一直是0.5了。

If the text embedding can be recovered to text?

Thanks for your excellent work! I want to know if the text embedding can be recovered to text.

When I change the code , the result will dropp considerably！

Thanks for your great work！ The previous issue has been solved， but I find a new issue. If I change the code (https://github.com/KaiyangZhou/CoOp/blob/ff61507c790454bce7c5052c3ac39e60772f1f89/trainers/coop.py#L248) as self.register_model("model", self.model, self.optim, self.sched). The result...

When I train my network on oxford_flower(epoch=200), it get a different result.

Dear Zhou: When I train my network on oxford_flower(epoch=200), it get a great result as follows: => result * total: 2,463 * correct: 2,268 * accuracy: 92.1% * error: 7.9%...

I employ my backbone and the trained loss is lower than bevdet-r50, but the performance is worse than bevdet-r50, can you give me some advice? I think whether the trained weights are not fully saved or other problems?

Thanks for your great work！ I meet this issue ： I employ my backbone and the trained loss is lower than bevdet-r50, but the performance is worse than bevdet-r50, can...