IGEV

IGEV copied to clipboard

如何训练自己的数据集

2

你好博主，我想请教一下如果训练自己的数据集，在数据加载、数据格式转化、数据预处理方面需要做哪些修改，如能告知，万分感谢。

zzr0127

Hi! Thank you for the great works! I was just wondering whether the output of input data for training effect the outcome of the model! If so, how high resolution...

idra79haza

Need help to do inference for gray scale image

4

Want to run the network for gray scale images (single channel) I get this error while running network on gray images Traceback (most recent call last): File "demo_imgs.py", line 100,...

mkothule

关于网络模型泛化能力的问题

4

您好，感谢您开源的代码 对于网络结构，我想问一下，您是如何提高模型的泛化能力的，我使用了其他网络模型来预测我自己拍的图像，但是效果十分差，但是用了您的IGEV网络跑出来的效果还是比较可观的，想咨询一下您是如何做到这么强的泛化性的。谢谢

Yu-Cheung

算法调用咨询

1

作者您好，我尝试了一下将IGEV-Stereo里面的模型转换为onnx模型进行c++的调用，但没能转换成功；请问您有相关代码提供或者文档吗

xiaojia2324

"Hello, author. I'm training the SceneFlow dataset with IGEV, and the EPE keeps increasing, reaching more than 4000. Could you please provide guidance on how to solve this issue?"

sunny-liulyw

视差图上色的代码应该用哪个

1

我用了下面两种，但是效果都不怎么好，部分地方颜色异常 plt.imsave(file_stem, disp, cmap='jet') cv2.imwrite(file_stem, cv2.applyColorMap(cv2.convertScaleAbs(disp, alpha=0.01),cv2.COLORMAP_JET))

yxg19991231

n_downsample can't be changed

1

To reduce the size of the model, I want to retrain the network with lower resolution of the disparity field. I've already done this with the RAFT-Stereo network. However, when...

gutcBrEl

AttributeError: 'EfficientNetFeatures' object has no attribute 'act1'

2

Thank you for sharing the code for your great work! I had this problem when I tried to run demo_imgs.py！ self.act1 = model.act1 AttributeError: 'EfficientNetFeatures' object has no attribute 'act1'...

zza1617

Would you advise extending IGEV-Stereo for the special case of a trifocal tensor estabishing the geometric projection between three views, or would IGEV-MVS be a more natural choice? In the...

KevinCain