官术网_书友最值得收藏!

Slicing tensors 

A common thing to do with a tensor is to slice a portion of it. A simple example could be choosing the first five elements of a one-dimensional tensor; let's call the tensor sales. We use a simple notation, sales[:slice_index] where slice_index represents the index where you want to slice the tensor:

sales = torch.FloatTensor([1000.0,323.2,333.4,444.5,1000.0,323.2,333.4,444.5])

sales[:5]
1000.0000
323.2000
333.4000
444.5000
1000.0000
[torch.FloatTensor of size 5]

sales[:-5]
1000.0000
323.2000
333.4000
[torch.FloatTensor of size 3]

Let's do more interesting things with our panda image, such as see what the panda image looks like when only one channel is chosen and see how to select the face of the panda.

Here, we select only one channel from the panda image:

plt.imshow(panda_tensor[:,:,0].numpy())
#0 represents the first channel of RGB

 The output is as follows:

Now, lets crop the image. Say we want to build a face detector for pandas and we need just the face of a panda for that. We crop the tensor image such that it contains only the panda's face:

plt.imshow(panda_tensor[25:175,60:130,0].numpy())

 The output is as follows: 

Another common example would be where you need to pick a specific element of a tensor:

#torch.eye(shape) produces an diagonal matrix with 1 as it diagonal #elements.
sales = torch.eye(3,3)
sales[0,1]

Output- 0.00.0

We will revisit image data in Chapter 5Deep Learning for Computer Vision, when we discuss using CNNs to build image classifiers.

Most of the PyTorch tensor operations are very similar to NumPy operations .
主站蜘蛛池模板: 江永县| 潮州市| 房产| 湖南省| 瓦房店市| 扎兰屯市| 沅江市| 北京市| 宜君县| 溆浦县| 松原市| 江津市| 永福县| 南康市| 安化县| 屏东市| 莱阳市| 邢台县| 炎陵县| 佛冈县| 桃江县| 伊吾县| 宣武区| 镶黄旗| 霍林郭勒市| 黄冈市| 罗甸县| 乐东| 焉耆| 塘沽区| 黄梅县| 茌平县| 肇州县| SHOW| 吴江市| 德惠市| 育儿| 恭城| 新津县| 新建县| 都昌县|