Python Pytorch 张量到 numpy 数组
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/49768306/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Pytorch tensor to numpy array
提问by DukeLover
I have a pytorchTensor of size torch.Size([4, 3, 966, 1296])
我有一个pytorch大小的张量torch.Size([4, 3, 966, 1296])
I want to convert it to numpyarray using the following code:
我想numpy使用以下代码将其转换为数组：
imgs = imgs.numpy()[:, ::-1, :, :]
imgs = imgs.numpy()[:, ::-1, :, :]
Can anyone please explain what this code is doing ?
谁能解释一下这段代码在做什么？
采纳答案by Maaz Bin Musa
There are 4 dimensions of the tensor you want to convert.
您要转换的张量有 4 个维度。
[:, ::-1, :, :]
:means that the first dimension should be copied as it is and converted, same goes for the third and fourth dimension.
:意味着第一个维度应该按原样复制和转换，第三个和第四个维度也是如此。
::-1means that for the second axes it reverses the the axes
::-1意味着对于第二个轴，它反转轴
回答by Azizbro
I believe you also have to use .detach(). I had to convert my Tensor to a numpy array on Colab which uses CUDA and GPU. I did it like the following:
我相信你也必须使用.detach(). 我不得不在使用 CUDA 和 GPU 的 Colab 上将我的 Tensor 转换为一个 numpy 数组。我是这样做的：
# this is just my embedding matrix which is a Torch tensor object
embedding = learn.model.u_weight
embedding_list = list(range(0, 64382))
input = torch.cuda.LongTensor(embedding_list)
tensor_array = embedding(input)
# the output of the line bwlow is a numpy array
tensor_array.cpu().detach().numpy()
回答by Muhammad Bilal
You can use this syntax if some grads are attached with your variables.
如果您的变量附加了一些 grads，您可以使用此语法。
y=torch.Tensor.cpu(x).detach().numpy()[:,:,:,-1]
y=torch.Tensor.cpu(x).detach().numpy()[:,:,:,-1]
