NNSVG inspired network structure drawer for deep learning
dnnsvg has intuitive interface which enables building svgs for common neural network architecture
svg = SVGBuilder(height=height, width=width) \
.add_layer(Convolution2D(in_channels=None, out_channels=96, ksize=11, stride=4)) \
.add_layer(MaxPooling(ksize=3, stride=2)) \
.add_layer(Convolution2D(in_channels=96, out_channels=256, ksize=5, stride=1, pad=2)) \
.add_layer(MaxPooling(ksize=3, stride=2)) \
.add_layer(Convolution2D(in_channels=256, out_channels=384, ksize=3, stride=1, pad=1)) \
.add_layer(Convolution2D(in_channels=384, out_channels=384, ksize=3, stride=1, pad=1)) \
.add_layer(Convolution2D(in_channels=384, out_channels=256, ksize=3, stride=1, pad=1)) \
.add_layer(MaxPooling(ksize=3, stride=2)) \
.add_layer(Reshape(output_shape=(1, 9216))) \
.add_layer(FullyConnected(output_shape=(1, 4096))) \
.add_layer(FullyConnected(output_shape=(1, 4096))) \
.add_layer(FullyConnected(output_shape=(1, 1000))) \
.build(input_tensor)
python setup.py install
or if you prefer using pip
pip install .
It is recommended to use develop instead of install option to reflect changes in the directory
python setup.py develop
or if you prefer using pip
pip install -e .