Output 1 of SplitWithSizesBackward0 is a view and is being modified inplace.

最新推荐文章于 2023-05-26 21:48:58 发布

日月凌空11

最新推荐文章于 2023-05-26 21:48:58 发布

阅读量1.2k

点赞数 1

文章标签： pytorch 人工智能 python

本文链接：https://blog.csdn.net/weixin_47988506/article/details/125284589

版权

ESRGCCNN 代码修复错误解决图像处理深度学习

关键词由CSDN通过智能技术生成

1）在运行esrgcnn代码的过程中遇到了些许的坑，最难解决的、也是最后一个困难终于算是解决了。

2）在运行代码测试自己的图片时候，一直报错：

Output 1 of SplitWithSizesBackward0 is a view and is being modified inplace. This view is the output of a function that returns multiple views. Such functions do not allow the output views to be modified inplace. You should replace the inplace operation by an out-of-place one.

复制粘贴到百度后，仔细研读各位大佬的代码后，解决了这个问题。

！！！我严格按照代码里的readme文档重新安装了软件

！！！我分析了tcw_sample_b.py中的代码。发现了确实有一个变量有些许问题，就做了稍许修改。

for step, (hr, lr, name) in enumerate(dataset):

        if "DIV2K" in dataset.name:

           t1 = time.time()

            h, w = lr.size()[1:]

            h_half, w_half = int(h/2), int(w/2)

            h_chop, w_chop = h_half + cfg.shave, w_half + cfg.shave

%%%%%%%%%%%%%%%%%%%%%%%%%%

            lr=lr_patch

%%%%%%%%%%%%%%%%%%%%%%%%%%%%

            lr_patch = torch.tensor((4, 3, h_chop, w_chop), dtype=torch.float)

            lr_patch[0].copy_(lr[:, 0:h_chop, 0:w_chop])

            lr_patch[1].copy_(lr[:, 0:h_chop, w-w_chop:w])

            lr_patch[2].copy_(lr[:, h-h_chop:h, 0:w_chop])

            lr_patch[3].copy_(lr[:, h-h_chop:h, w-w_chop:w])

            lr_patch = lr_patch.to(device)

添加了一行lr=lr_patch，加上新版本的代码，就可以正常运行啦。输出结果如下：

 python tcw_sample_b.py --model esrgcnn --test_data_dir dataset/Set5 --scale 2 --ckpt_path checkpoint/esrgcnn.pth --sample_dir samples_singlemodel_urban100_x2
{
    "ckpt_path": "checkpoint/esrgcnn.pth", 
    "cuda": false, 
    "group": 1, 
    "model": "esrgcnn", 
    "sample_dir": "samples_singlemodel_urban100_x2", 
    "scale": 2, 
    "shave": 20, 
    "test_data_dir": "dataset/Set5"
}
('img_001_SRF_2_HR.png', 38.75975078879017, 0.9661591341475728)
('img_002_SRF_2_HR.png', 42.86924067767056, 0.9891173914544316)
('img_003_SRF_2_HR.png', 35.15641205205168, 0.9767552401292521)
('img_004_SRF_2_HR.png', 35.94780702489556, 0.8894667598159965)
('img_005_SRF_2_HR.png', 36.23858183086506, 0.9730289258091539)
(37.794358474854604, 0.9589054902712815)