-
Notifications
You must be signed in to change notification settings - Fork 2
/
utils.py
159 lines (136 loc) · 5.29 KB
/
utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
#-*- coding: utf-8 -*-
"""
Most codes from https://github.com/carpedm20/DCGAN-tensorflow
"""
from __future__ import division
import math
import random
import pprint
import scipy.misc
import scipy as sp
import scipy.io
import numpy as np
from glob import glob
import sys
import pickle
from time import gmtime, strftime
#from six.moves import xrange
import matplotlib.pyplot as plt
import lmdb
import os, gzip
from scipy.io import loadmat
import tensorflow as tf
import tensorflow.contrib.slim as slim
class ImageData:
def __init__(self, load_size, channels):
self.load_size = load_size
self.channels = channels
def image_processing(self, filename):
x = tf.read_file(filename)
x_decode = tf.image.decode_jpeg(x, channels=self.channels)
img = tf.image.resize_images(x_decode, [self.load_size, self.load_size])
img = tf.cast(img, tf.float32) / 127.5 - 1
return img
def load_batch(fpath):
with open(fpath, 'rb') as f:
if sys.version_info > (3, 0):
# Python3
d = pickle.load(f, encoding='latin1')
else:
# Python2
d = pickle.load(f)
data = d["data"]
labels = d["labels"]
return data, labels
def check_folder(log_dir):
if not os.path.exists(log_dir):
os.makedirs(log_dir)
return log_dir
#显示所有变量的tensor类型
def show_all_variables():
model_vars = tf.trainable_variables()
slim.model_analyzer.analyze_vars(model_vars, print_info=True)
def get_image(image_path, input_height, input_width, resize_height=64, resize_width=64, crop=True, grayscale=False):
image = imread(image_path, grayscale)
return transform(image, input_height, input_width, resize_height, resize_width, crop)
def save_images(images, size, image_path):
return imsave(inverse_transform(images), size, image_path)
def imread(path, grayscale=False):
if (grayscale):
return scipy.misc.imread(path, flatten=True).astype(np.float)
else:
return scipy.misc.imread(path).astype(np.float)
def merge_images(images, size):
return inverse_transform(images)
def merge(images, size):
h, w = images.shape[1], images.shape[2]
if (images.shape[3] in (3,4)):
c = images.shape[3]
img = np.zeros((h * size[0], w * size[1], c))
for idx, image in enumerate(images):
i = idx % size[1]
j = idx // size[1]
img[j * h:j * h + h, i * w:i * w + w, :] = image
return img
elif images.shape[3]==1:
img = np.zeros((h * size[0], w * size[1]))
for idx, image in enumerate(images):
i = idx % size[1]
j = idx // size[1]
img[j * h:j * h + h, i * w:i * w + w] = image[:,:,0]
return img
else:
raise ValueError('in merge(images,size) images parameter ''must have dimensions: HxW or HxWx3 or HxWx4')
def imsave(images, size, path):
image = np.squeeze(merge(images, size))
return scipy.misc.imsave(path, image)
def center_crop(x, crop_h, crop_w, resize_h=64, resize_w=64):
if crop_w is None:
crop_w = crop_h
h, w = x.shape[:2]
j = int(round((h - crop_h)/2.))
i = int(round((w - crop_w)/2.))
return scipy.misc.imresize(x[j:j+crop_h, i:i+crop_w], [resize_h, resize_w])
def transform(image, input_height, input_width, resize_height=64, resize_width=64, crop=True):
if crop:
cropped_image = center_crop(image, input_height, input_width, resize_height, resize_width)
else:
cropped_image = scipy.misc.imresize(image, [resize_height, resize_width])
return np.array(cropped_image)/127.5 - 1.
def inverse_transform(images):
return (images+1.)/2.
""" Drawing Tools """
# borrowed from https://github.com/ykwon0407/variational_autoencoder/blob/master/variational_bayes.ipynb
def save_scattered_image(z, id, z_range_x, z_range_y, name='scattered_image.jpg'):
N = 10
plt.figure(figsize=(8, 6))
# 此处的np.argmax(id, 1)是用来判断此处的类别到底是几,如np.argmax([[0,0,1,0,0,0,0,0,0,0]],1)=2,输出最大的数所在的第二维度数字
plt.scatter(z[:, 0], z[:, 1], c=np.argmax(id, 1), marker='o', edgecolor='none', cmap=discrete_cmap(N, 'jet'))
plt.colorbar(ticks=range(N))
axes = plt.gca()
axes.set_xlim([-z_range_x, z_range_x])
axes.set_ylim([-z_range_y, z_range_y])
plt.grid(True)
plt.savefig(name)
plt.close()
# borrowed from https://gist.github.com/jakevdp/91077b0cae40f8f8244a
def discrete_cmap(N, base_cmap=None):
"""Create an N-bin discrete colormap from the specified input map"""
# Note that if base_cmap is a string or None, you can simply do
# return plt.cm.get_cmap(base_cmap, N)
# The following works for string, None, or a colormap instance:
base = plt.cm.get_cmap(base_cmap)
color_list = base(np.linspace(0, 1, N))
cmap_name = base.name + str(N)
return base.from_list(cmap_name, color_list, N)
def get_pix_image(Image, random_index, ih=256, iw=256, oh=64, ow=64):
batch_images_files = np.array(Image)[random_index]
batch_I = [
get_image(batch_file,
input_height=ih,
input_width=iw,
resize_height=oh,
resize_width=ow,
) for batch_file in batch_images_files]
batch_images = np.array(batch_I).astype(np.float32)
return batch_images