DL之BigGAN:利用BigGAN算法实现超强炸天效果——画风的确skr、skr、skr,太特么的skr了
DL之BigGAN:利用BigGAN算法实现超强炸天效果——画风的确skr、skr、skr,太特么的skr了
导读
本博主刚刚利用代码进行测试,结果的确吊(不)炸(可)天(思议)!BigGAN的效果的确不可思议,但是关于GAN到底学了什么,仍需要理论研究支持,这个可视化的过渡阶段,倒是给了一个好的想象空间。还有,BigGAN的以假乱真,到底应该如何应用,这也是一个亟待解决的问题。
相关文章
Paper之BigGAN:ICLR 2019最新论文《LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS》论文研究中
输出效果
一、Explore BigGAN samples of a particular category
Try varying the truncation value.
1、ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus
PS:保护北极熊,阻止全球气候变暖,爱护环境,人人有责;绿色出行,低碳生活,从我做起!
2、sloth bear, Melursus ursinus, Ursus ursinus
3、ant, emmet, pismire
4、great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias
5、house finch, linnet, Carpodacus mexicanus
6、tiger cat
二、Interpolate between BigGAN samples
Try setting different categorys with the same noise_seeds, or the same categorys with different noise_seeds. Or go wild and set both any way you like!
1、pug, pug-dog→Persian cat
2、pug, pug-dogjian→lion, king of beasts, Panthera leo
3、pug, pug-dog → tiger, Panthera tigris
4、pug, pug-dog →brown bear, bruin, Ursus arctos
5、 golden retriever→coral fungus
6、golden retriever→toilet tissue, toilet paper, bathroom tissue
7、golden retriever→pineapple, ananas
8、golden retriever→banana
9、 goldfish, Carassius auratus→red wine
10、golf ball → starfish, sea star
实现代码
import cStringIO
import IPython.display
import numpy as np
import PIL.Image
from scipy.stats import truncnorm
import tensorflow as tf
import tensorflow_hub as hub
input_z = inputs['z']
input_y = inputs['y']
input_trunc = inputs['truncation']
dim_z = input_z.shape.as_list()[1]
vocab_size = input_y.shape.as_list()[1]
def truncated_z_sample(batch_size, truncation=1., seed=None):
state = None if seed is None else np.random.RandomState(seed)
values = truncnorm.rvs(-2, 2, size=(batch_size, dim_z), random_state=state)
return truncation * values
def one_hot(index, vocab_size=vocab_size):
index = np.asarray(index)
if len(index.shape) == 0:
index = np.asarray([index])
assert len(index.shape) == 1
num = index.shape[0]
output = np.zeros((num, vocab_size), dtype=np.float32)
output[np.arange(num), index] = 1
return output
def one_hot_if_needed(label, vocab_size=vocab_size):
label = np.asarray(label)
if len(label.shape) <= 1:
label = one_hot(label, vocab_size)
assert len(label.shape) == 2
return label
def sample(sess, noise, label, truncation=1., batch_size=8,
vocab_size=vocab_size):
noise = np.asarray(noise)
label = np.asarray(label)
num = noise.shape[0]
if len(label.shape) == 0:
label = np.asarray([label] * num)
if label.shape[0] != num:
raise ValueError('Got # noise samples ({}) != # label samples ({})'
.format(noise.shape[0], label.shape[0]))
label = one_hot_if_needed(label, vocab_size)
ims = []
for batch_start in xrange(0, num, batch_size):
s = slice(batch_start, min(num, batch_start + batch_size))
feed_dict = {input_z: noise[s], input_y: label[s], input_trunc: truncation}
ims.append(sess.run(output, feed_dict=feed_dict))
ims = np.concatenate(ims, axis=0)
assert ims.shape[0] == num
ims = np.clip(((ims + 1) / 2.0) * 256, 0, 255)
ims = np.uint8(ims)
return ims
def interpolate(A, B, num_interps):
alphas = np.linspace(0, 1, num_interps)
if A.shape != B.shape:
raise ValueError('A and B must have the same shape to interpolate.')
return np.array([(1-a)*A + a*B for a in alphas])
def imgrid(imarray, cols=5, pad=1):
if imarray.dtype != np.uint8:
raise ValueError('imgrid input imarray must be uint8')
pad = int(pad)
assert pad >= 0
cols = int(cols)
assert cols >= 1
N, H, W, C = imarray.shape
rows = int(np.ceil(N / float(cols)))
batch_pad = rows * cols - N
assert batch_pad >= 0
post_pad = [batch_pad, pad, pad, 0]
pad_arg = [[0, p] for p in post_pad]
imarray = np.pad(imarray, pad_arg, 'constant', constant_values=255)
H += pad
W += pad
grid = (imarray
.reshape(rows, cols, H, W, C)
.transpose(0, 2, 1, 3, 4)
.reshape(rows*H, cols*W, C))
if pad:
grid = grid[:-pad, :-pad]
return grid
def imshow(a, format='png', jpeg_fallback=True):
a = np.asarray(a, dtype=np.uint8)
str_file = cStringIO.StringIO()
PIL.Image.fromarray(a).save(str_file, format)
png_data = str_file.getvalue()
try:
disp = IPython.display.display(IPython.display.Image(png_data))
except IOError:
if jpeg_fallback and format != 'jpeg':
print ('Warning: image was too large to display in format "{}"; '
'trying jpeg instead.').format(format)
return imshow(a, format='jpeg')
else:
raise
return disp
tf.reset_default_graph()
print 'Loading BigGAN module from:', module_path
module = hub.Module(module_path)
inputs = {k: tf.placeholder(v.dtype, v.get_shape().as_list(), k)
for k, v in module.get_input_info_dict().iteritems()}
output = module(inputs)
print
print 'Inputs:\n', '\n'.join(
' {}: {}'.format(*kv) for kv in inputs.iteritems())
print
print 'Output:', output
tf.reset_default_graph()
print 'Loading BigGAN module from:', module_path
module = hub.Module(module_path)
inputs = {k: tf.placeholder(v.dtype, v.get_shape().as_list(), k)
for k, v in module.get_input_info_dict().iteritems()}
output = module(inputs)
print
print 'Inputs:\n', '\n'.join(
' {}: {}'.format(*kv) for kv in inputs.iteritems())
print
print 'Output:', output