HomoGAN

HomoGAN copied to clipboard

 Hi, I see your method accuracy of about 0.5, but is the actual GT labeling accuracy so high?

DoongLi

没有video2img.py

1

下载数据集后，没有找到video2img.py

zhongchangxaing

Hello! Thank you for sharing your code. I have a question about visualizing the plane masks. How do I edit your code to get the mask in the center of...

Shunta-Shimizu

Bug. No such file or directory: './data//train.txt'

7

Thank you for sharing the repo! and for producing this awesome CVPR paper !!! It is very interesting to use unsupervised learning with GAN in extracting the dominant plane between...

GabbySuwichaya

请问从videl2img.py保存后的数据集结构是怎么样的，我在运行时和data_loader差距较大

zhongchangxaing

About the size of the picture

3

According to the README, the picture size should be (640, 360)  And the param.json provides that the crop_size is [384, 512]  And the rho should be 16 ...

Katono5

Obtaining .npy files

1

Hello! Thank you for sharing your repository, I do have some questions about evaluating the model using the .npy file. As per a [previous issue](https://github.com/megvii-research/HomoGAN/issues/3), the reply mentioned that the...

florallam

目前遇到以下问题 运行目录为: `$HomoGAN/` 设备为 CPU:48 GPU:A100 CUDA Version: 11. 目前遇到以下问题： 相互引用有python文件目录无法调用 HomoGAN/model/swin_multi.py 第5行 `import model.net as net` 改为 `from model import net` HomoGAN/dataset/data_loader.py 第164行 `self.list_path = self.base_path + '/{}.txt'.format( phase)`...

YiyaoZhang9527

Query about train and evaluation

1

Hello! Thank you for sharing your code, I do have a query about the training and evaluation portion of the code. In the pre-training phase, there is a [train_and_evaluate()](https://github.com/megvii-research/HomoGAN/blob/main/train.py#L207) function...

florallam

What is the time to train the code on different dataset?

pooja12295