SuperGlue-pytorch
SuperGlue-pytorch copied to clipboard
yingxin-jia
[SuperGlue: Learning Feature Matching with Graph Neural Networks] This repo includes PyTorch code for training the SuperGlue matching network on top of SIFT keypoints and descriptors.
您好，非常感谢您的开源工作，您代码中的损失函数为：  论文中的损失函数为：  您好像是故意删除了未匹配部分的损失函数，请问这样做是出于什么考虑的呢？精度的损失是否主要因这个操作造成的？谢谢您的关注和回复
Thank you very much for your work, but how to train superglue using superpoint tips?
After using the COCO data set for training, 1、 how to evaluate and test the accuracy, 2、the training efficiency is too low. Has anyone tried to modify it to batch...
Can I use my dataset to train the model? (It's always wrong when I use ma dataset) Why there is a mistake as soon as I change the batch-size? Looking...
https://github.com/HeatherJiaZG/SuperGlue-pytorch/blob/e8a9edf44034b78bbbe79320fff44087701c8d68/models/utils.py#L304 the correct mean of focal length should be calculated by `K0[0, 0], K0[1, 1], K1[0, 0], K1[1, 1]`
您好！！！首先非常感谢您能放出训练代码，我这个数据是在phototourism上进行训练的，但是在训练过程中会出现nan这个问题，但是感觉loss也不会出现nan的情况，因此想请教一下您在训练出出现过这种bug么？
when i trained several steps, i encountered the following problem: ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 32, 1]) i have no idea...
I think line 30 of the load_data.py file should be: `height, width = image.shape[:2]`
Metadata
Owner
Metadata
[SuperGlue: Learning Feature Matching with Graph Neural Networks] This repo includes PyTorch code for training the SuperGlue matching network on top of SIFT keypoints and descriptors.