Pytorch 0.4 更新學習筆記
阿新 • • 發佈：2019-01-28
一.Tensor 和 Variable合併為Tensor。
Tensor可以追蹤計算圖。所以沒必要使用Variable了。
type(x) -> x.type()
使用detach()來獲取Tensor的數值。
二.棄用volatile
使用torch.no_grad()/torch.set_grad_enabled(grad_mode)來遮蔽計算圖。
>>> x = torch.zeros(1, requires_grad=True)
>>> with torch.no_grad():
... y = x * 2
>>> 三.三個類torch.dtype/torch.device/torch.layout
torch.dtype(使用Tensor的的dtype屬性獲取資料型別)
| Data type | torch.dtype | Tensor types |
|---|---|---|
| 32-bit floating point | torch.float32 or torch.float | torch.*.FloatTensor |
| 64-bit floating point | torch.float64 or torch.double | torch.*.DoubleTensor |
| 16-bit floating point | torch.float16 or torch.half | torch.*.HalfTensor |
| 8-bit integer (unsigned) | torch.uint8 | torch.*.ByteTensor |
| 8-bit integer (signed) | torch.int8 | torch.*.CharTensor |
| 16-bit integer (signed) | torch.int16 or torch.short | torch.*.ShortTensor |
| 32-bit integer (signed) | torch.int32 or torch.int | torch.*.IntTensor |
| 64-bit integer (signed) | torch.int64 or torch.long | torch.*.LongTensor |
torch.device(使用Tensor的device屬性獲取Tensor的位置，cpu或gpu)
torch.device('cpu')/torch.device('cuda')
建立Tensor的方法
>>> device = torch.device("cuda:1")
>>> x = torch.randn(3, 3, dtype=torch.float64, device=device>>> cuda = torch.device("cuda")
>>> torch.tensor([[1], [2], [3]], dtype=torch.half, device=cuda) >>> x = torch.randn(3, dtype=torch.float64)
>>> torch.zeros_like(x)
tensor([ 0., 0., 0.], dtype=torch.float64) >>> x = torch.randn(3, dtype=torch.float64)
>>> x.new_ones(2)
tensor([ 1., 1.], dtype=torch.float64)