DL之BigGAN：利用BigGAN算法實現超強炸天效果——畫風的確skr、skr、skr，太特么的skr了

導讀
? ??本博主剛剛利用代碼進行測試，結果的確吊(不)炸(可)天(思議)！BigGAN的效果的確不可思議，但是關于GAN到底學了什么，仍需要理論研究支持，這個可視化的過渡階段，倒是給了一個好的想象空間。還有，BigGAN的以假亂真，到底應該如何應用，這也是一個亟待解決的問題。

?

?

目錄

輸出效果

實現代碼

---

?

?

?

相關文章
Paper之BigGAN：ICLR 2019最新論文《LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS》論文研究中

輸出效果

一、Explore BigGAN samples of a particular category
Try varying the truncation value.

1、ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus
PS：保護北極熊，阻止全球氣候變暖，愛護環境，人人有責；綠色出行，低碳生活，從我做起！

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

?

實現代碼

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 hubinput_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 * valuesdef one_hot(index, vocab_size=vocab_size):index = np.asarray(index)if len(index.shape) == 0:index = np.asarray([index])assert len(index.shape) == 1num = index.shape[0]output = np.zeros((num, vocab_size), dtype=np.float32)output[np.arange(num), index] = 1return outputdef 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) == 2return labeldef 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] == numims = np.clip(((ims + 1) / 2.0) * 256, 0, 255)ims = np.uint8(ims)return imsdef 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 >= 0cols = int(cols)assert cols >= 1N, H, W, C = imarray.shaperows = int(np.ceil(N / float(cols)))batch_pad = rows * cols - Nassert batch_pad >= 0post_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 += padW += padgrid = (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 griddef 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:raisereturn disptf.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:', outputtf.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

?

?

?

?

?

?

?

?

?

?

?

?

?

?

?

?

?

總結

以上是生活随笔為你收集整理的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了的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。