在PyTorch中对2D和3D图像进行线性插值和网格化
项目描述
torch-image-lerp
PyTorch中的线性2D/3D图像插值和网格化。
为什么?
此包提供了一个简单、一致的API,用于
- 从2D/3D图像中采样(
sample_image_2d()
/sample_image_3d()
) - 将值插入到2D/3D图像中(
insert_into_image_2d()
,insert_into_image_3d
)
操作是可微分的,并支持从复值图像中采样。
安装
pip install torch-image-lerp
使用
从图像中采样
import torch
import numpy as np
from torch_image_lerp import sample_image_2d
image = torch.rand((28, 28))
# make an arbitrary stack (..., 2) of 2d coords
coords = torch.tensor(np.random.uniform(low=0, high=27, size=(6, 7, 8, 2)))
# sampling returns a (6, 7, 8) array of samples obtained by linear interpolation
samples = sample_image_2d(image=image, coordinates=coords)
API对于3D是相同的,但使用(..., 3)
坐标和(d, h, w)
图像。
插入到图像中
import torch
import numpy as np
from torch_image_lerp import insert_into_image_2d
image = torch.zeros((28, 28))
# make an arbitrary stack (..., 2) of 2d coords
coords = torch.tensor(np.random.uniform(low=0, high=27, size=(3, 4, 2)))
# generate random values to place at coords
values = torch.rand(size=(3, 4))
# sampling returns a (6, 7, 8) array of samples obtained by linear interpolation
samples = insert_into_image_2d(values, image=image, coordinates=coords)
API对于3D是相同的,但使用(..., 3)
坐标和(d, h, w)
图像。
项目详情
关闭
torch_image_lerp-0.0.3.tar.gz 的哈希值
算法 | 哈希摘要 | |
---|---|---|
SHA256 | a9df4406d412bee0c82c604742a4d18e8dbfa4ab42f8688549a120a2115dcdfb |
|
MD5 | 1071f521238dae2f5d7125cb3580526c |
|
BLAKE2b-256 | 9c3fc347f0fd7afdcb50eb8dace2b59866c7801325ebec3bdfaa17a5164f2e6b |
关闭
torch_image_lerp-0.0.3-py3-none-any.whl 的哈希值
算法 | 哈希摘要 | |
---|---|---|
SHA256 | ef729f68045e31de5c5fce579529607f6598144d06dfcb9bbd2a4c9b57e39fdc |
|
MD5 | f13adf86935a75bbea4d5f2d3102b265 |
|
BLAKE2b-256 | 539af727af79e13edf2ed80a434db72b4cb91b9afb63a9d59eb70e3e9c72849d |