bump version 0.1.0 (#1)

* update lazy module and tests

* update README.md

* fix bug in lazy.py

* minor fix: add Tuple typing

* resolve expansion channel in lazy module

* log error

* debug warning lazy module

* fix code formatting

* update lazy.py

* update tests and remove warning in lazy module

README.md

@@ -19,7 +19,7 @@ An illustration of Depthwise Separable Convolution. Credit: [Depthwise Convoluti
   <a href="https://github.com/reshalfahsi/separableconv-torch/actions/workflows/package.yml"><img src="https://github.com/reshalfahsi/separableconv-torch/actions/workflows/package.yml/badge.svg" alt="package testing"></a>
 </div>
 
-PyTorch (unofficial) implementation of Depthwise Separable Convolution. This type of convolution is introduced by Chollet in [Xception: Deep Learning With Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357). This package provides ``SeparableConv1d``, ``SeparableConv2d``, and ``SeparableConv3d``. 
+PyTorch (unofficial) implementation of Depthwise Separable Convolution. This type of convolution is introduced by Chollet in [Xception: Deep Learning With Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357). This package provides ``SeparableConv1d``, ``SeparableConv2d``, ``SeparableConv3d``, ``LazySeparableConv1d``, ``LazySeparableConv2d``, and ``LazySeparableConv3d``. 
 
 
 ## Installation
@@ -135,3 +135,22 @@ output = m(input)
 ```
 </details>
 
+
+<details closed>
+<summary>For lazy 2-dimensional case.</summary>
+
+
+```python
+import torch
+import separableconv.nn as nn
+
+# set input
+input = torch.randn(4, 10, 100, 100)
+
+# define model
+m = nn.LazySeparableConv2d(30, 3)
+
+# process input through model
+output = m(input)
+```
+</details>

separableconv/nn/__init__.py

@@ -13,5 +13,6 @@
 
 
 from .conv import SeparableConv1d, SeparableConv2d, SeparableConv3d
+from .lazy import LazySeparableConv1d, LazySeparableConv2d, LazySeparableConv3d
 
 from torch.nn import *