支持PyTorch的einops张量操作神器用法示例详解

pip install einops

from einops import rearrange
 
# rearrange elements according to the pattern
output_tensor = rearrange(input_tensor, 'h w c -> c h w')

from einops import rearrange
import torch
 
a = torch.randn(3, 9, 9)  # [3, 9, 9]
output = rearrange(a, 'c (r p) w -> c r p w', p=3)
print(output.shape)   # [3, 3, 3, 9]

from einops import repeat
import torch
 
a = torch.randn(9, 9)  # [9, 9]
output_tensor = repeat(a, 'h w -> c h w', c=3)  # [3, 9, 9]

from einops import reduce
import torch
 
a = torch.randn(9, 9)  # [9, 9]
output_tensor = reduce(a, 'b c (h h2) (w w2) -> b h w c', 'mean', h2=2, w2=2)

# example given for pytorch, but code in other frameworks is almost identical  
from torch.nn import Sequential, Conv2d, MaxPool2d, Linear, ReLU
from einops.layers.torch import Rearrange
 
model = Sequential(
    Conv2d(3, 6, kernel_size=5),
    MaxPool2d(kernel_size=2),
    Conv2d(6, 16, kernel_size=5),
    MaxPool2d(kernel_size=2),
    # flattening
    Rearrange('b c h w -> b (c h w)'),  
    Linear(16*5*5, 120), 
    ReLU(),
    Linear(120, 10), 
)