lmolhw5252
lmolhw5252
Hi thanks for reply, there is my result: ```python >>> from imageio import imread >>> depth = imread('/data1/lhw/workspace/HoHoNet/data/stanford2D3D/area_5a/depth/camera_e7c078fec2414967b99f65c847b9d38a_office_11_frame_equirectangular_domain_depth.png') >>> print(depth.min(), depth.max(), depth[depth!=65535].max()) 0 65535 65534 >>> rgb = imread('/data1/lhw/workspace/HoHoNet/data/stanford2D3D/area_5a/rgb/camera_e7c078fec2414967b99f65c847b9d38a_office_11_frame_equirectangular_domain_rgb.png') >>>...
您好，非常感谢您的解答，但是我还是有一些问题我按照您的https://github.com/sunset1995/HoHoNet/blob/master/README_prepare_data_s2d3d.md 准备的方法，生成对应的文件。 ```python from imageio import imread rgb = imread('/home/lmolhw/workspace/HoHoNet/Data_test/Stanford/area_5a/rgb/camera_e7c078fec2414967b99f65c847b9d38a_office_11_frame_equirectangular_domain_rgb.png') print((rgb==0).all(-1).mean()) depth = imread('/home/lmolhw/workspace/HoHoNet/Data_test/Stanford/area_5a/depth/camera_e7c078fec2414967b99f65c847b9d38a_office_11_frame_equirectangular_domain_depth.png') print(depth.min(), depth.max(), depth[depth!=65535].max()) ``` ``` 0.25 0 65535 65534 ``` 另外还有几个问题： - 这个数据的prepare对模型的训练结果会有影响么？ - 每个模型大概训练了多少个epoch呢？ -...
Hi @rohit12 I got the same problem in your closed issues, Traceback (most recent call last): File "chainer_model/train_svhn.py", line 76, in train_dataset, validation_dataset = curriculum.load_dataset(0) File "/home/user/PycharmProjects/see/chainer_model/utils/baby_step_curriculum.py", line 38, in...
@Bartzi Thank you for your reply!!! Do you mean this item? `Add one line to the beginning of each ground truth file: (both values need to be separated by a...
@rohit12 The `train.cvs` file's format should be this? `4 4 /path/to/image/0.png 1 1 1 1 1 1 1` I can‘t download the dataset by #6 , so I want to...
@Bartzi Hi,I got a problem about your paper,that the number **N** used in STN does not say how to set. I had read paper recurrent STN, this paper use 3...
Are these output sizes same? 
@Bartzi And I got another qusetion,when I train network with STN, the network is difficult to converge.Do you have any trick about training STN? I use image with 1 word.
Thanks a lot about your reply!
请问这个问题解决了么？