# -*- coding: utf-8 -*-
"""
Created on Sat Feb 16 12:01:19 2019
@author:
"""
import scipy.io
import numpy as np
import tensorflow as tf
import os
import scipy.misc
import matplotlib.pyplot as plt
#%%
def _conv_layer(_input,_weights,_biases):
_conv=tf.nn.conv2d(_input,tf.constant(_weights),strides=(1,1,1,1),padding='SAME')
return tf.nn.bias_add(_conv,_biases)
def _pooling_layer(_input):
return tf.nn.max_pool(_input,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
def preprocess(image,mean_pixel):
return image-mean_pixel
def unprocess(image,mean_pixel):
return image+mean_pixel
def imread(path):
return scipy.misc.imread(path).astype(np.float)
def imsave(path,img):
img=np.clip(image,0,255).astype(np.uint8)
scipy.misc.imsave(path,img)
print("function for VGG ready")
#%%
def net(data_path,_input_image):
layers=('conv1_1','relu1_1','conv1_2','relu1_2','pool1',
'conv2_1','relu2_1','conv2_2','relu2_2','pool2',
'conv3_1','relu3_1','conv3_2','relu3_2','conv3_3','relu3_3','conv3_4','relu3_4','pool3',
'conv4_1','relu4_1','conv4_2','relu4_2','conv4_3','relu4_3','conv4_4','relu4_4','pool4',
'conv5_1','relu5_1','conv5_2','relu5_2','conv5_3','relu5_3','conv5_4','relu5_4'
)
data=scipy.io.loadmat(data_path)
mean=data['normalization'][0][0][0]
mean_pixel=np.mean(mean,axis=(0,1))
weights=data['layers'][0]
net={}
current=_input_image
for i,name in enumerate(layers):
print('i=',i)
kind=name[:4]
if kind=='conv':
kernels,bias=weights[i][0][0][0][0]
'''
matconvnet:weights are [width,,height,in_channels,out_channels]
tensorflow: weights are [height,width,in_channels,out_channels]
'''
kernels=np.transpose(kernels,(1,0,2,3))
bias=bias.reshape(-1)
current=_conv_layer(current,kernels,bias)
elif kind=='relu':
current=tf.nn.relu(current)
elif kind=='pool':
current=_pooling_layer(current)
net[name]=current
assert len(net)==len(layers)
return net,mean_pixel,layers
print('network for VGG ready')
#%%
cwd=os.getcwd()
VGG_PATH=cwd+'/data/imagenet-vgg-verydeep-19.mat'
IMG_PATH=cwd+'/data/cat1.jpg'
input_image=imread(IMG_PATH)
shape=(1,input_image.shape[0],input_image.shape[1],input_image.shape[2])
image=tf.placeholder('float',shape=shape)
nets,mean_pixel,all_layers=net(VGG_PATH,image)
input_image_pre=np.array([preprocess(input_image,mean_pixel)])
layers=all_layers
#%%
with tf.Session() as sess:
for i,layer in enumerate(layers):
print('[%d/%d] %s'%(i+1,len(layers),len(layer)))
features=nets[layer].eval(feed_dict={image:input_image_pre})
print('type of feature is ',type(features))
print('shape of features is ',features.shape)
if 1:
plt.figure(i+1,figsize=(10,5))
plt.matshow(features[0,:,:,0],cmap=plt.cm.gray,fignum=i+1)
plt.title(''+layer)
plt.colorbar()
plt.show()
