DeconvNet

show more

Implementations

Figure 1. Overall architecture of the proposed network. On top of the convolution network based on VGG 16-layer net, we put a multilayer deconvolution network to generate the accurate segmentation map of an input proposal. Given a feature representation obtained from the convolution network, dense pixel-wise class prediction map is constructed through multiple series of unpooling, deconvolution and rectification operations.

Model: http://cvlab.postech.ac.kr/research/deconvnet/model/DeconvNet/DeconvNet_inference_deploy.prototxt

Link: http://cvlab.postech.ac.kr/research/deconvnet/

Tensorflow implementation of Learning Deconvolution Network for Semantic Segmentation.

from DeconvNet import DeconvNet

deconvNet = DeconvNet() # will start collecting the VOC2012 data
deconvNet.train(epochs=20, steps_per_epoch=500, batch_size=64)
deconvNet.save()
prediction = deconvNet.predict(any_image)

Model: https://github.com/fabianbormann/Tensorflow-DeconvNet-Segmentation/blob/master/DeconvNet.py

Github: https://github.com/fabianbormann/Tensorflow-DeconvNet-Segmentation

segmentationdeconvnet
How helpful was this page?