-
-
I used your fastconvmae train imgnet data.
In your code, you said the output should be:
![image](https://user-images.githubusercontent.com/41125918/183908655-4b73bfa0-7c7a-442e-b7e9-2b4db42da3be…
-
转pnnx或者onnx, 再转ncnn
您的代码写的特别精妙，我们工程中想应用起来比较困难，有木有计划出一个轻量化的模型呢？
-
I am truly grateful to the authors for open-sourcing code, which introduces a novel approach. However, I seem to have encountered an issue. For datasets like Flowers102, Chaoyang, PMNIST, ClipArt, Inf…
-
Out of curiosity, may i ask is there any possibility to make a version of CNN based CROCO self-supervised pipeline?
-
Thank you for your excellent work. I have some questions about the training process of SPM.
I encounter a problem when I use the script in train_mixformer.sh to train SPM module.
`python tracking/…
-
The work is commendable!
However, while attempting to train mixformer_convmae_online to utilize the PrRoIPool2D module, I encountered difficulty creating the layer. I was unable to resolve the issue…
-
您好，在我阅读代码的过程中，由于个人的代码理解能力有限，没有找到训练用模型中根据Score进行模板更新的部分代码在哪里和实现的方式，仅找到了测试模型中的更新代码。根据论文中的描述，似乎在训练时没有进行模板更新对吗？如果有的话，能否请您指点一下？
-
ConvMAE-v2 is much better than v1, what is the difference？please
-
您好，首先非常感谢您的工作！我在跑got10k验证集时出现'MixFormerOnline' object has no attribute 'online_sizes'，暂时不知道该如何解决？