mirror of
https://github.com/wassname/CoordConv.git
synced 2026-09-09 11:13:34 +08:00
66 lines
1.9 KiB
Markdown
66 lines
1.9 KiB
Markdown
# CoordConv
|
|
|
|
 
|
|
|
|
Pytorch implementation of CoordConv for N-D ConvLayers, and the experiments.
|
|
|
|
Reference from the paper: [An intriguing failing of convolutional neural networks and the CoordConv solution](https://arxiv.org/abs/1807.03247)
|
|
|
|
Extends the CoordinateChannel concatenation from 2D to 1D and 3D tensors.
|
|
|
|
# Requirements
|
|
|
|
- pytorch 0.4.0
|
|
- torchvision 0.2.1
|
|
- torchsummary 1.3
|
|
- sklearn 0.19.1
|
|
|
|
# Usage
|
|
|
|
```python
|
|
from coordconv import CoordConv1d, CoordConv2d, CoordConv3d
|
|
|
|
class Net(nn.Module):
|
|
def __init__(self):
|
|
super(Net, self).__init__()
|
|
self.coordconv = CoordConv2d(2, 32, 1, with_r=True)
|
|
self.conv1 = nn.Conv2d(32, 64, 1)
|
|
self.conv2 = nn.Conv2d(64, 64, 1)
|
|
self.conv3 = nn.Conv2d(64, 1, 1)
|
|
self.conv4 = nn.Conv2d( 1, 1, 1)
|
|
|
|
def forward(self, x):
|
|
x = self.coordconv(x)
|
|
x = F.relu(self.conv1(x))
|
|
x = F.relu(self.conv2(x))
|
|
x = F.relu(self.conv3(x))
|
|
x = self.conv4(x)
|
|
x = x.view(-1, 64*64)
|
|
return x
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
net = Net().to(device)
|
|
```
|
|
|
|
# Experiments
|
|
|
|
Implement experiments from origin paper.
|
|
|
|
## Coordinate Classification
|
|
|
|
Use `experiments/generate_data.py` to generate `Uniform` and `Quadrant` datasets for Coordinate Classification task.
|
|
|
|
Use `experiments/train_and_test.py` to train and test neural network model.
|
|
|
|
### Uniform Datasets
|
|
|
|
|Train|Test|Predictions|
|
|
|:---:|:---:|:---:|
|
|
||||
|
|
|
|
|
|
### Quadrant Datasets
|
|
|
|
|Train|Test|Predictions|
|
|
|:---:|:---:|:---:|
|
|
|||| |