State of the Art Neural Networks for Deep Learning
Project description
pyradox
This python library helps you with implementing various state of the art neural networks in a totally customizable fashion using Tensorflow 2
Installation
pip install pyradox
or
pip install git+https://github.com/Ritvik19/pyradox.git
Usage
Modules
Module | Description | Input Shape | Output Shape | Usage |
---|---|---|---|---|
Rescale | A layer that rescales the input: x_out = (x_in -mu) / sigma |
Arbitrary | Same shape as input | check here |
Convolution 2D | Applies 2D Convolution followed by Batch Normalization (optional) and Dropout (optional) | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Densely Connected | Densely Connected Layer followed by Batch Normalization (optional) and Dropout (optional) | 2D tensor with shape (batch_size, input_dim) | 2D tensor with shape (batch_size, n_units) | check here |
DenseNet Convolution Block | A Convolution block for DenseNets | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
DenseNet Convolution Block | A Convolution block for DenseNets | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
DenseNet Transition Block | A Transition block for DenseNets | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Dense Skip Connection | Implementation of a skip connection for densely connected layer | 2D tensor with shape (batch_size, input_dim) | 2D tensor with shape (batch_size, n_units) | check here |
VGG Module | Implementation of VGG Modules with slight modifications, Applies multiple 2D Convolution followed by Batch Normalization (optional), Dropout (optional) and MaxPooling | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Inception Conv | Implementation of 2D Convolution Layer for Inception Net, Convolution Layer followed by Batch Normalization, Activation and optional Dropout | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Inception Block | Implementation on Inception Mixing Block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Xception Block | A customised implementation of Xception Block (Depthwise Separable Convolutions) | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net Block | Implementation of Efficient Net Block (Depthwise Separable Convolutions) | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Conv Skip Connection | Implementation of Skip Connection for Convolution Layer | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net Block | Customized Implementation of ResNet Block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net V2 Block | Customized Implementation of ResNetV2 Block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res NeXt Block | Customized Implementation of ResNeXt Block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Inception Res Net Conv 2D | Implementation of Convolution Layer for Inception Res Net: Convolution2d followed by Batch Norm | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Inception Res Net Block | Implementation of Inception-ResNet block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | block 8 Block 17 Block 35 |
NAS Net Separable Conv Block | Adds 2 blocks of Separable Conv Batch Norm | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
NAS Net Adjust Block | Adjusts the input previous path to match the shape of the input |
|||
NAS Net Normal A Cell | Normal cell for NASNet-A | |||
NAS Net Reduction A Cell | Reduction cell for NASNet-A | |||
Mobile Net Conv Block | Adds an initial convolution layer with batch normalization and activation | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Mobile Net Depth Wise Conv Block | Adds a depthwise convolution block. A depthwise convolution block consists of a depthwise conv, batch normalization, activation, pointwise convolution, batch normalization and activation | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Inverted Res Block | Adds an Inverted ResNet block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
SEBlock | Adds a Squeeze Excite Block | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
ConvNets
Module | Description | Input Shape | Output Shape | Usage |
---|---|---|---|---|
Generalized Dense Nets | A generalization of Densely Connected Convolutional Networks (Dense Nets) | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Densely Connected Convolutional Network 121 | A modified implementation of Densely Connected Convolutional Network 121 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Densely Connected Convolutional Network 169 | A modified implementation of Densely Connected Convolutional Network 169 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Densely Connected Convolutional Network 201 | A modified implementation of Densely Connected Convolutional Network 201 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Generalized VGG | A generalization of VGG network | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D or 2D tensor | usage 1 usage 2 |
VGG 16 | A modified implementation of VGG16 network | 4D tensor with shape (batch_shape, rows, cols, channels) | 2D tensor with shape (batch_shape, new_dim) | usage 1 usage 2 |
VGG 19 | A modified implementation of VGG19 network | 4D tensor with shape (batch_shape, rows, cols, channels) | 2D tensor with shape (batch_shape, new_dim) | usage 1 usage 2 |
Inception V3 | Customized Implementation of Inception Net | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Generalized Xception | Generalized Implementation of XceptionNet (Depthwise Separable Convolutions) | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Xception Net | A Customised Implementation of XceptionNet | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net | Generalized Implementation of Effiecient Net | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B0 | Customized Implementation of Efficient Net B0 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B1 | Customized Implementation of Efficient Net B1 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B2 | Customized Implementation of Efficient Net B2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B3 | Customized Implementation of Efficient Net B3 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B4 | Customized Implementation of Efficient Net B4 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B5 | Customized Implementation of Efficient Net B5 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B6 | Customized Implementation of Efficient Net B6 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Efficient Net B7 | Customized Implementation of Efficient Net B7 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net | Customized Implementation of Res Net | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net 50 | Customized Implementation of Res Net 50 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net 101 | Customized Implementation of Res Net 101 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net 152 | Customized Implementation of Res Net 152 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net V2 | Customized Implementation of Res Net V2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net 50 V2 | Customized Implementation of Res Net 50 V2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net 101 V2 | Customized Implementation of Res Net 101 V2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res Net 152 V2 | Customized Implementation of Res Net 152 V2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res NeXt | Customized Implementation of Res NeXt | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res NeXt 50 | Customized Implementation of Res NeXt 50 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res NeXt 101 | Customized Implementation of Res NeXt 101 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Res NeXt 152 | Customized Implementation of Res NeXt 152 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
Inception Res Net V2 | Customized Implementation of Inception Res Net V2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
NAS Net | Generalised Implementation of NAS Net | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
NAS Net Mobile | Customized Implementation of NAS Net Mobile | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
NAS Net Large | Customized Implementation of NAS Net Large | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | check here |
MobileNet | Customized Implementation of MobileNet | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | usage 1 usage 2 |
Mobile Net V2 | Customized Implementation of Mobile Net V2 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | usage 1 usage 2 |
Mobile Net V3 | Customized Implementation of Mobile Net V3 | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, new_rows, new_cols, new_channels) | usage 1 usage 2 |
Seg Net | Generalised Implementation of SegNet for Image Segmentation Applications | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, rows, cols, channels) | check here |
U Net | Generalised Implementation of UNet for Image Segmentation Applications | 4D tensor with shape (batch_shape, rows, cols, channels) | 4D tensor with shape (batch_shape, rows, cols, channels) | check here |
DenseNets
Module | Description | Input Shape | Output Shape | Usage |
---|---|---|---|---|
Densely Connected Network | Network of Densely Connected Layers followed by Batch Normalization (optional) and Dropout (optional) | 2D tensor with shape (batch_size, input_dim) | 2D tensor with shape (batch_size, new_dim) | check here |
Densely Connected Resnet | Network of skip connections for densely connected layer | 2D tensor with shape (batch_size, input_dim) | 2D tensor with shape (batch_size, new_dim) | check here |
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pyradox-1.0.1.tar.gz
(25.8 kB
view hashes)