Scratch pytorch for Softmax regression

1. The implementation of Softmax regression from scratch

insert image description here
The input is a vector 784, which is the pixel length x width of the image.

784 = 28 * 28

insert image description here
keepdim means keep dimension. Adding in the direction of 0 means removing the dimension of row, that is, the result is 1row; adding in the direction of 1 means removing the dimension of col, that is, the result is 1col.
insert image description here
insert image description here
insert image description here
X.reshape((-1, W.shape[0])), the dimension is changed to bathSize * 784,bathSize = 256
insert image description here

insert image description here

insert image description here
insert image description here
insert image description here
insert image description here
insert image description here
insert image description here

insert image description here
insert image description here

insert image description here
insert image description here
insert image description here

2. A concise implementation of Softmax regression in pytorch

insert image description here
insert image description here
insert image description here

insert image description here

insert image description here
insert image description here

refer to

https://www.bilibili.com/video/BV1K64y1Q7wu

Guess you like

Origin blog.csdn.net/zgpeace/article/details/123768541
Recommended