How to get moving image.

CGC1031 commented 4 years ago

Thank you for your patient reply before.Your advice is helpful to me. I have successfully get the real_flow, warped_moving and image_fixed pictures. Through add keys = ['real_flow', 'image_fixed', 'warped_moving'] . For the purpose of getting moving image, following the previous method, I attempted to add the following key words to keys. ['image_moving'] / ['img_moving'] / ['moving'] . But they are all failed. QQ图片20200702184725 Prompt us for keyword error['img_moving']. 1、Can you tell me what the key words correspond to the moving image？ 2、Or how do you get moving images？Can you give me some ideas？ Looking forward to your reply!

zsyzzsoft commented 4 years ago

Please also add a key here, e.g., 'img_moving': img2, at https://github.com/microsoft/Recursive-Cascaded-Networks/blob/0709490fe010e4acc6357990d1d871c170e3ef31/network/recursive_cascaded_networks.py#L176

CGC1031 commented 4 years ago

Thank you for your reply. I have achieved it successfully. Thanks again.

Hoodini-Gzj commented 2 years ago

您好，请问是把eval.py中keys = ['pt_mask', 'landmark_dists', 'jaccs', 'dices', 'jacobian_det', ]替换为keys = ['real_flow', 'image_fixed', 'warped_moving']就可以了吗？还需要修改其他地方吗？

Hoodini-Gzj commented 2 years ago

期待您的回复。

CGC1031 commented 2 years ago

尊敬的赵博士您好！我研究您“Recursive cascaded networks for unsupervised medical image registration”三年了，并在您的工作基础上做了一些研究作为自己的毕设。最近毕业论文的审核老师提出一个疑问，我自己也难以解答，所以冒昧致信向您求教，还望赵博士帮我解解疑惑。下图中仿射子网络Affine和形变子网络Dense您分别用两个损失函数来进行约束，我想请问一个网络训练为什么会有两个损失函数呢？假设一：您是不是先用仿射配准子网络的损失函数loss1训练好仿射配准网络的12个形变参数，然后将其固定；再用形变配准子网络的损失函数loss2去训练形变网络的参数。总之就是训练时只有一个loss在起作用，Affine是一个部分，后面的所有形变网络是一个部分，分开训练的。假设二：loss1指导Affine训练，loss2指导Dense训练，但是二者是同步的，一直训练到结束。整个训练过程中，两个loss同时工作，同时指导Affine和Dense网络参数地不断优化（我也不知道卷积神经网络是否可以同时被两个损失函数所指导？）非常期待您回复，感谢您！

zsyzzsoft commented 2 years ago

The whole network can optimize multiple objectives simultaneously.

microsoft / Recursive-Cascaded-Networks

How to get moving image. #33