https://github.com/titu1994/Keras-DualPathNetworks

Dual Path Networks for Keras 2.0+
https://github.com/titu1994/Keras-DualPathNetworks

deep-learning dpn dual-path-networks keras tensorflow

Last synced: 3 days ago
JSON representation

Dual Path Networks for Keras 2.0+

• Host: GitHub
• URL: https://github.com/titu1994/Keras-DualPathNetworks
• Owner: titu1994
• License: apache-2.0
• Created: 2017-08-08T22:17:33.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2020-02-09T15:54:15.000Z (over 4 years ago)
• Last Synced: 2024-10-27T12:31:02.482Z (7 days ago)
• Topics: deep-learning, dpn, dual-path-networks, keras, tensorflow
• Language: Python
• Size: 417 KB
• Stars: 114
• Watchers: 10
• Forks: 52
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-image-classification - unoffical-keras : https://github.com/titu1994/Keras-DualPathNetworks
• awesome-image-classification - unoffical-keras : https://github.com/titu1994/Keras-DualPathNetworks

README

        
# Dual Path Networks in Keras

[Dual Path Networks](https://arxiv.org/abs/1707.01629) are highly efficient networks which combine the strength of both ResNeXt [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/abs/1611.05431) and DenseNets [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993).

Note: Weights have not been ported over yet.

## Dual Path Connections



## Usage

Several of the standard Dual Path Network models have been included. They can be initialized as : 

```

from dual_path_network import DPN92, DPN98, DPN107, DPN137

model = DPN92(input_shape=(224, 224, 3)) # same for the others

```

To create a custom DualPathNetwork, use the DualPathNetwork builder method : 

```

from dual_path_network import DualPathNetwork

model = DualPathNetwork(input_shape=(224, 224, 3),

                        initial_conv_filters=64,

                        depth=[3, 4, 20, 3],

                        filter_increment=[16, 32, 24, 128],

                        cardinality=32,

                        width=3,

                        weight_decay=0,

                        include_top=True,

                        weights=None,

                        input_tensor=None,

                        pooling=None,

                        classes=1000)

```

## Performance



## Support 

- Keras does not have inbuilt support for grouped convolutions. Therefore I had to use lambda layers to match the ResNeXt paper implementation. When grouped convolution support is added, I hope to add it in this as well.

- Mean-Max Global Pooling support is present with the help of Lambda layer to scale the sum.

- Depth and Filter_Increment must be lists for now, and must be lists of same length. Will think about adding support for integers, but I think list support is far more useful anyway, so I may not implement it.

- Weight decay support is added, but disabled by default. The DPN paper does not mention it, but ResNet, WRN and ResNeXt paper may all use small weight regularization. Use a small value of `1e-4` or `5e-4` if you wish to use it.