# 比较与torchvision.transforms.ToTensor的功能差异
## torchvision.transforms.ToTensor
```python
class torchvision.transforms.ToTensor
```
更多内容详见[torchvision.transforms.ToTensor](https://pytorch.org/vision/0.10/transforms.html#torchvision.transforms.ToTensor)。
## mindspore.dataset.vision.ToTensor
```python
class mindspore.dataset.vision.ToTensor(
output_type=np.float32
)
```
更多内容详见[mindspore.dataset.vision.ToTensor](https://mindspore.cn/docs/zh-CN/r2.0.0-alpha/api_python/dataset_vision/mindspore.dataset.vision.ToTensor.html#mindspore.dataset.vision.ToTensor)。
## 使用方式
PyTorch：将PIL类型的Image或numpy 数组转换为 torch中的Tensor, 输入的numpy数组通常是格式且取值在[0, 255]范围，输出是格式且取值在[0.0, 1.0]的torch Tensor。
MindSpore：输入为PIL类型的图像或格式且取值在[0, 255]范围内的numpy数组，输出为[0.0, 1.0]范围内且具有格式的numpy数组；等同于在原始输入图像上做了通道转换及像素值归一化两种操作。
## 代码示例
```python
import numpy as np
from PIL import Image
from torchvision import transforms
import mindspore.dataset.vision as vision
# In MindSpore, ToTensor convert PIL Image into numpy array.
img_path = "/path/to/test/1.jpg"
img = Image.open(img_path)
to_tensor = vision.ToTensor()
img_data = to_tensor(img)
print("img_data type:", type(img_data))
print("img_data dtype:", img_data.dtype)
# Out:
#img_data type:
#img_data dtype: float32
# In torch, ToTensor transforms the input to tensor.
img_path = "/path/to/test/1.jpg"
image_transform = transforms.Compose([transforms.ToTensor()])
img = np.array(Image.open(img_path))
img_data = image_transform(img)
print(img_data.shape)
# Out:
# torch.Size([3, 2268, 4032])
```