chrisabbott

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

chrisabbott

###########################################################################################################
# Pretraining on Tiny Imagenet for use in a modified, minitiarized version of Joseph Redmon's YOLO: 
#        You Only Look Once: Unified, Real-Time Object Detection
#        https://arxiv.org/abs/1506.02640
###########################################################################################################

import os
import copy
import numpy as np
import tensorflow as tf

chrisabbott

(unet) Christians-MacBook-Pro:model christian$ python3 unet.py 
Tensor("UNet/ContractingPath/ContractingBlock_0/conv2d_1/Relu:0", shape=(1, 568, 568, 64), dtype=float32)
Tensor("UNet/ContractingPath/ContractingBlock_1/conv2d_1/Relu:0", shape=(1, 280, 280, 128), dtype=float32)
Tensor("UNet/ContractingPath/ContractingBlock_2/conv2d_1/Relu:0", shape=(1, 136, 136, 256), dtype=float32)
Tensor("UNet/ContractingPath/ContractingBlock_3/conv2d_1/Relu:0", shape=(1, 64, 64, 512), dtype=float32)
Tensor("UNet/Bridge/conv2d_1/Relu:0", shape=(1, 28, 28, 1024), dtype=float32)
Tensor("UNet/ExpansivePath/ExpansiveBlock_0/conv2d_2/Relu:0", shape=(1, 52, 52, 512), dtype=float32)
Tensor("UNet/ExpansivePath/ExpansiveBlock_1/conv2d_2/Relu:0", shape=(1, 100, 100, 256), dtype=float32)
Tensor("UNet/ExpansivePath/ExpansiveBlock_2/conv2d_2/Relu:0", shape=(1, 196, 196, 128), dtype=float32)
Tensor("UNet/ExpansivePath/ExpansiveBlock_3/conv2d_3/Relu:0", shape=(1, 388, 388, 64), dtype=float32)