2

I use some code similar to the following - for data augmentation:

    from torchvision import transforms

    #...

    augmentation = transforms.Compose([
        transforms.RandomApply([
            transforms.RandomRotation([-30, 30])
        ], p=0.5),
        transforms.RandomHorizontalFlip(p=0.5),
    ])

During my testing I want to fix random values to reproduce the same random parameters each time I change the model training settings. How can I do it?

I want to do something similar to np.random.seed(0) so each time I call random function with probability for the first time, it will run with the same rotation angle and probability. In other words, if I do not change the code at all, it must reproduce the same result when I rerun it.

Alternatively I can separate transforms, use p=1, fix the angle min and max to a particular value and use numpy random numbers to generate results, but my question if I can do it keeping the code above unchanged.

4

2 回答 2

2

在__getitem__您的数据集类中制作一个 numpy 随机种子。

def __getitem__(self, index):      
    img = io.imread(self.labels.iloc[index,0])
    target = self.labels.iloc[index,1]

    seed = np.random.randint(2147483647) # make a seed with numpy generator 
    random.seed(seed) # apply this seed to img transforms
    if self.transform is not None:
        img = self.transform(img)

    random.seed(seed) # apply this seed to target transforms
    if self.target_transform is not None:
        target = self.target_transform(target)

    return img, target
于 2019-12-29T08:16:57.240 回答
0

只是补充@conv3d 的答案。因为它被放在这个 gh问题上。一起使用两个种子分配很重要，因为并非所有转换都是统一的。

random.seed(seed)
torch.manual_seed(seed)

所以代码会是这样的：

>>>
seed = np.random.randint(2147483647) 
random.seed(seed) 
torch.manual_seed(seed)
if self.transform is not None:
    img = self.transform(img)
<<<
于 2021-12-23T20:55:14.410 回答