python可以做哪些有趣的事

发布网友 发布时间：2022-03-03 16:22

我来回答

共2个回答

热心网友 时间：2022-03-03 17:51

画画

在本地用keras搭建风格转移平台

1.相关依赖库的安装

# 命令行安装keras、h5py、tensorflow
pip3 install keras
pip3 install h5py
pip3 install tensorflow

如果tensorflowan命令行安装失败，可以在这里下载whl包Python Extension Packages for Windows（进入网址后ctrl+F输入tensorflow可以快速搜索）

2.配置运行环境

下载VGG16模型z 放入如下目录当中

3.代码编写

from __future__ import print_functionfrom keras.preprocessing.image import load_img, img_to_arrayfrom scipy.misc import imsaveimport numpy as npfrom scipy.optimize import fmin_l_bfgs_bimport timeimport argparsefrom keras.applications import vgg16from keras import backend as Kparser = argparse.ArgumentParser(description='Neural style transfer with Keras.')parser.add_argument('base_image_path', metavar='base', type=str,
help='Path to the image to transform.')parser.add_argument('style_reference_image_path', metavar='ref', type=str,
help='Path to the style reference image.')parser.add_argument('result_prefix', metavar='res_prefix', type=str,
help='Prefix for the saved results.')parser.add_argument('--iter', type=int, default=10, required=False,
help='Number of iterations to run.')parser.add_argument('--content_weight', type=float, default=0.025, required=False,
help='Content weight.')parser.add_argument('--style_weight', type=float, default=1.0, required=False,
help='Style weight.')parser.add_argument('--tv_weight', type=float, default=1.0, required=False,
help='Total Variation weight.')args = parser.parse_args()base_image_path = args.base_image_pathstyle_reference_image_path = args.style_reference_image_pathresult_prefix = args.result_prefixiterations = args.iter# these are the weights of the different loss componentstotal_variation_weight = args.tv_weightstyle_weight = args.style_weightcontent_weight = args.content_weight# dimensions of the generated picture.width, height = load_img(base_image_path).sizeimg_nrows = 400img_ncols = int(width * img_nrows / height)# util function to open, resize and format pictures into appropriate tensorsdef preprocess_image(image_path):
img = load_img(image_path, target_size=(img_nrows, img_ncols))
img = img_to_array(img)
img = np.expand_dims(img, axis=0)
img = vgg16.preprocess_input(img)
return img# util function to convert a tensor into a valid imagedef deprocess_image(x):
if K.image_data_format() == 'channels_first':
x = x.reshape((3, img_nrows, img_ncols))
x = x.transpose((1, 2, 0))
else:
x = x.reshape((img_nrows, img_ncols, 3))
# Remove zero-center by mean pixel
x[:, :, 0] += 103.939
x[:, :, 1] += 116.779
x[:, :, 2] += 123.68
# 'BGR'->'RGB'
x = x[:, :, ::-1]
x = np.clip(x, 0, 255).astype('uint8')
return x# get tensor representations of our imagesbase_image = K.variable(preprocess_image(base_image_path))style_reference_image = K.variable(preprocess_image(style_reference_image_path))# this will contain our generated imageif K.image_data_format() == 'channels_first':
combination_image = K.placeholder((1, 3, img_nrows, img_ncols))else:
combination_image = K.placeholder((1, img_nrows, img_ncols, 3))# combine the 3 images into a single Keras tensorinput_tensor = K.concatenate([base_image,
style_reference_image,
combination_image], axis=0)# build the VGG16 network with our 3 images as input# the model will be loaded with pre-trained ImageNet weightsmodel = vgg16.VGG16(input_tensor=input_tensor,
weights='imagenet', include_top=False)print('Model loaded.')# get the symbolic outputs of each "key" layer (we gave them unique names).outputs_dict = dict([(layer.name, layer.output) for layer in model.layers])# compute the neural style loss# first we need to define 4 util functions# the gram matrix of an image tensor (feature-wise outer proct)def gram_matrix(x):
assert K.ndim(x) == 3
if K.image_data_format() == 'channels_first':
features = K.batch_flatten(x)
else:
features = K.batch_flatten(K.permute_dimensions(x, (2, 0, 1)))
gram = K.dot(features, K.transpose(features))
return gram# the "style loss" is designed to maintain# the style of the reference image in the generated image.# It is based on the gram matrices (which capture style) of# feature maps from the style reference image# and from the generated imagedef style_loss(style, combination):
assert K.ndim(style) == 3
assert K.ndim(combination) == 3
S = gram_matrix(style)
C = gram_matrix(combination)
channels = 3
size = img_nrows * img_ncols
return K.sum(K.square(S - C)) / (4. * (channels ** 2) * (size ** 2))# an auxiliary loss function# designed to maintain the "content" of the# base image in the generated imagedef content_loss(base, combination):
return K.sum(K.square(combination - base))# the 3rd loss function, total variation loss,# designed to keep the generated image locally coherentdef total_variation_loss(x):
assert K.ndim(x) == 4
if K.image_data_format() == 'channels_first':
a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] - x[:, :, 1:, :img_ncols - 1])
b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] - x[:, :, :img_nrows - 1, 1:])
else:
a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] - x[:, 1:, :img_ncols - 1, :])
b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] - x[:, :img_nrows - 1, 1:, :])
return K.sum(K.pow(a + b, 1.25))# combine these loss functions into a single scalarloss = K.variable(0.)layer_features = outputs_dict['block4_conv2']base_image_features = layer_features[0, :, :, :]combination_features = layer_features[2, :, :, :]loss += content_weight * content_loss(base_image_features,
combination_features)feature_layers = ['block1_conv1', 'block2_conv1',
'block3_conv1', 'block4_conv1',
'block5_conv1']for layer_name in feature_layers:
layer_features = outputs_dict[layer_name]
style_reference_features = layer_features[1, :, :, :]
combination_features = layer_features[2, :, :, :]
sl = style_loss(style_reference_features, combination_features)
loss += (style_weight / len(feature_layers)) * slloss += total_variation_weight * total_variation_loss(combination_image)# get the gradients of the generated image wrt the lossgrads = K.gradients(loss, combination_image)outputs = [loss]if isinstance(grads, (list, tuple)):
outputs += gradselse:
outputs.append(grads)f_outputs = K.function([combination_image], outputs)def eval_loss_and_grads(x):
if K.image_data_format() == 'channels_first':
x = x.reshape((1, 3, img_nrows, img_ncols))
else:
x = x.reshape((1, img_nrows, img_ncols, 3))
outs = f_outputs([x])
loss_value = outs[0]
if len(outs[1:]) == 1:
grad_values = outs[1].flatten().astype('float64')
else:
grad_values = np.array(outs[1:]).flatten().astype('float64')
return loss_value, grad_values# this Evaluator class makes it possible# to compute loss and gradients in one pass# while retrieving them via two separate functions,# "loss" and "grads". This is done because scipy.optimize# requires separate functions for loss and gradients,# but computing them separately would be inefficient.class Evaluator(object):

def __init__(self):
self.loss_value = None
self.grads_values = None

def loss(self, x):
assert self.loss_value is None
loss_value, grad_values = eval_loss_and_grads(x)
self.loss_value = loss_value
self.grad_values = grad_values
return self.loss_value

def grads(self, x):
assert self.loss_value is not None
grad_values = np.copy(self.grad_values)
self.loss_value = None
self.grad_values = None
return grad_valuesevaluator = Evaluator()# run scipy-based optimization (L-BFGS) over the pixels of the generated image# so as to minimize the neural style lossif K.image_data_format() == 'channels_first':
x = np.random.uniform(0, 255, (1, 3, img_nrows, img_ncols)) - 128.else:
x = np.random.uniform(0, 255, (1, img_nrows, img_ncols, 3)) - 128.for i in range(iterations):
print('Start of iteration', i)
start_time = time.time()
x, min_val, info = fmin_l_bfgs_b(evaluator.loss, x.flatten(),
fprime=evaluator.grads, maxfun=20)
print('Current loss value:', min_val)
# save current generated image
img = deprocess_image(x.copy())
fname = result_prefix + '_at_iteration_%d.png' % i
imsave(fname, img)
end_time = time.time()
print('Image saved as', fname)print('Iteration %d completed in %ds' % (i, end_time - start_time))

复制上述代码保存为neural_style_transfer.py(随便命名)

4.运行

新建一个空文件夹，把上一步骤的文件neural_style_transfer.py放入这个空文件夹中。然后把相应的模板图片，待转化图片放入该文件当中。

python neural_style_transfer.py   你的待转化图片路径    模板图片路径   保存的生产图片路径加名称（注意不需要有.jpg等后缀）
python neural_style_transfer.py './me.jpg' './starry_night.jpg' './me_t'

迭代结果截图：

迭代过程对比

热心网友 时间：2022-03-03 19:09