numpy中的np.clip()函数和TensorFlow中的tf.clip_by_value()函数用法

Numpy 中clip函数的使用

numpy.clip(a, a_min, a_max, out=None)[source]

其中a是一个数组,后面两个参数分别表示最小和最大值,怎么用呢,老规矩,我们看代码:

import numpy as np
x=np.array([1,2,3,5,6,7,8,9])
np.clip(x,3,8)
Out[88]:
array([3, 3, 3, 5, 6, 7, 8, 8])
  • 1
  • 2
  • 3
  • 4
  • 5

也就是说clip这个函数将将数组中的元素限制在a_min, a_max之间,大于a_max的就使得它等于 a_max,小于a_min,的就使得它等于a_min。

x=np.array([[1,2,3,5,6,7,8,9],[1,2,3,5,6,7,8,9]])
np.clip(x,3,8)

Out[90]:
array([[3, 3, 3, 5, 6, 7, 8, 8],

[3, 3, 3, 5, 6, 7, 8, 8]])

值域范围 tf.clip_by_value的用
  

tf.clip_by_value的用法

tf.clip_by_value(A, min, max):输入一个张量A,把A中的每一个元素的值都压缩在min和max之间。小于min的让它等于min,大于max的元素的值等于max。

例如:

[python]  view plain  copy
  1. import tensorflow as tf;  
  2. import numpy as np;  
  3.   
  4. A = np.array([[1,1,2,4], [3,4,8,5]])  
  5.   
  6. with tf.Session() as sess:  
  7.     print sess.run(tf.clip_by_value(A, 25))  

输出:

[[2 2 2 4]
 [3 4 5 5]]

  • 2
    点赞
  • 11
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
逐行详细解释以下代码并加注释from tensorflow import keras import matplotlib.pyplot as plt base_image_path = keras.utils.get_file( "coast.jpg", origin="https://img-datasets.s3.amazonaws.com/coast.jpg") plt.axis("off") plt.imshow(keras.utils.load_img(base_image_path)) #instantiating a model from tensorflow.keras.applications import inception_v3 model = inception_v3.InceptionV3(weights='imagenet',include_top=False) #配置各层对DeepDream损失的贡献 layer_settings = { "mixed4": 1.0, "mixed5": 1.5, "mixed6": 2.0, "mixed7": 2.5, } outputs_dict = dict( [ (layer.name, layer.output) for layer in [model.get_layer(name) for name in layer_settings.keys()] ] ) feature_extractor = keras.Model(inputs=model.inputs, outputs=outputs_dict) #定义损失函数 import tensorflow as tf def compute_loss(input_image): features = feature_extractor(input_image) loss = tf.zeros(shape=()) for name in features.keys(): coeff = layer_settings[name] activation = features[name] loss += coeff * tf.reduce_mean(tf.square(activation[:, 2:-2, 2:-2, :])) return loss #梯度上升过程 @tf.function def gradient_ascent_step(image, learning_rate): with tf.GradientTape() as tape: tape.watch(image) loss = compute_loss(image) grads = tape.gradient(loss, image) grads = tf.math.l2_normalize(grads) image += learning_rate * grads return loss, image def gradient_ascent_loop(image, iterations, learning_rate, max_loss=None): for i in range(iterations): loss, image = gradient_ascent_step(image, learning_rate) if max_loss is not None and loss > max_loss: break print(f"... Loss value at step {i}: {loss:.2f}") return image #hyperparameters step = 20. num_octave = 3 octave_scale = 1.4 iterations = 30 max_loss = 15. #图像处理方面 import numpy as np def preprocess_image(image_path): img = keras.utils.load_img(image_path) img = keras.utils.img_to_array(img) img = np.expand_dims(img, axis=0) img = keras.applications.inception_v3.preprocess_input(img) return img def deprocess_image(img): img = img.reshape((img.shape[1], img.shape[2], 3)) img /= 2.0 img += 0.5 img *= 255. img = np.clip(img, 0, 255).astype("uint8") return img #在多个连续 上运行梯度上升 original_img = preprocess_image(base_image_path) original_shape = original_img.shape[1:3] successive_shapes = [original_shape] for i in range(1, num_octave): shape = tuple([int(dim / (octave_scale ** i)) for dim in original_shape]) successive_shapes.append(shape) successive_shapes = successive_shapes[::-1] shrunk_original_img = tf.image.resize(original_img, successive_shapes[0]) img = tf.identity(original_img) for i, shape in enumerate(successive_shapes): print(f"Processing octave {i} with shape {shape}") img = tf.image.resize(img, shape) img = gradient_ascent_loop( img, iterations=iterations, learning_rate=step, max_loss=max_loss ) upscaled_shrunk_original_img = tf.image.resize(shrunk_original_img, shape) same_size_original = tf.image.resize(original_img, shape) lost_detail = same_size_original - upscaled_shrunk_original_img img += lost_detail shrunk_original_img = tf.image.resize(original_img, shape) keras.utils.save_img("DeepDream.png", deprocess_image(img.numpy()))
06-07
这段代码是一个使用 DeepDream 技术对一张图像进行处理的例子。下面对每一部分进行详细解释: 1. 导入所需的库 ```python from tensorflow import keras import matplotlib.pyplot as plt ``` 导入了 TensorFlow 和 Keras 库,以及用于绘制图像的 Matplotlib 库。 2. 加载图像 ```python base_image_path = keras.utils.get_file( "coast.jpg", origin="https://img-datasets.s3.amazonaws.com/coast.jpg") plt.axis("off") plt.imshow(keras.utils.load_img(base_image_path)) ``` 使用 `keras.utils.get_file` 函数从亚马逊 S3 存储桶下载名为 "coast.jpg" 的图像,并使用 `keras.utils.load_img` 函数加载该图像。`plt.axis("off")` 和 `plt.imshow` 函数用于绘制该图像并关闭坐标轴。 3. 实例化模型 ```python from tensorflow.keras.applications import inception_v3 model = inception_v3.InceptionV3(weights='imagenet',include_top=False) ``` 使用 Keras 库的 InceptionV3 模型对图像进行处理。`weights='imagenet'` 表示使用预训练的权重,`include_top=False` 表示去掉模型的顶层(全连接层)。 4. 配置 DeepDream 损失 ```python layer_settings = { "mixed4": 1.0, "mixed5": 1.5, "mixed6": 2.0, "mixed7": 2.5, } outputs_dict = dict( [(layer.name, layer.output) for layer in [model.get_layer(name) for name in layer_settings.keys()]] ) feature_extractor = keras.Model(inputs=model.inputs, outputs=outputs_dict) ``` 通过配置不同层对 DeepDream 损失的贡献来控制图像的风格。该代码块的 `layer_settings` 字典定义了每层对损失的贡献,`outputs_dict` 变量将每层的输出保存到一个字典,`feature_extractor` 变量实例化一个新模型来提取特征。 5. 定义损失函数 ```python import tensorflow as tf def compute_loss(input_image): features = feature_extractor(input_image) loss = tf.zeros(shape=()) for name in features.keys(): coeff = layer_settings[name] activation = features[name] loss += coeff * tf.reduce_mean(tf.square(activation[:, 2:-2, 2:-2, :])) return loss ``` 定义了一个计算 DeepDream 损失的函数。该函数首先使用 `feature_extractor` 模型提取输入图像的特征,然后计算每层对损失的贡献并相加,最终返回总损失。 6. 梯度上升过程 ```python @tf.function def gradient_ascent_step(image, learning_rate): with tf.GradientTape() as tape: tape.watch(image) loss = compute_loss(image) grads = tape.gradient(loss, image) grads = tf.math.l2_normalize(grads) image += learning_rate * grads return loss, image def gradient_ascent_loop(image, iterations, learning_rate, max_loss=None): for i in range(iterations): loss, image = gradient_ascent_step(image, learning_rate) if max_loss is not None and loss > max_loss: break print(f"... Loss value at step {i}: {loss:.2f}") return image ``` 定义了一个用于实现梯度上升过程的函数。`gradient_ascent_step` 函数计算输入图像的损失和梯度,然后对图像进行梯度上升并返回更新后的图像和损失。`gradient_ascent_loop` 函数使用 `gradient_ascent_step` 函数实现多次迭代,每次迭代都会计算损失和梯度,并对输入图像进行更新。 7. 设置超参数 ```python step = 20. num_octave = 3 octave_scale = 1.4 iterations = 30 max_loss = 15. ``` 设置了一些 DeepDream 算法的超参数,例如梯度上升步长、金字塔层数、金字塔缩放比例、迭代次数和损失上限。 8. 图像处理 ```python import numpy as np def preprocess_image(image_path): img = keras.utils.load_img(image_path) img = keras.utils.img_to_array(img) img = np.expand_dims(img, axis=0) img = keras.applications.inception_v3.preprocess_input(img) return img def deprocess_image(img): img = img.reshape((img.shape[1], img.shape[2], 3)) img /= 2.0 img += 0.5 img *= 255. img = np.clip(img, 0, 255).astype("uint8") return img ``` 定义了两个函数,`preprocess_image` 函数将输入图像进行预处理,`deprocess_image` 函数将处理后的图像进行还原。 9. DeepDream 算法过程 ```python original_img = preprocess_image(base_image_path) original_shape = original_img.shape[1:3] successive_shapes = [original_shape] for i in range(1, num_octave): shape = tuple([int(dim / (octave_scale ** i)) for dim in original_shape]) successive_shapes.append(shape) successive_shapes = successive_shapes[::-1] shrunk_original_img = tf.image.resize(original_img, successive_shapes[0]) img = tf.identity(original_img) for i, shape in enumerate(successive_shapes): print(f"Processing octave {i} with shape {shape}") img = tf.image.resize(img, shape) img = gradient_ascent_loop( img, iterations=iterations, learning_rate=step, max_loss=max_loss ) upscaled_shrunk_original_img = tf.image.resize(shrunk_original_img, shape) same_size_original = tf.image.resize(original_img, shape) lost_detail = same_size_original - upscaled_shrunk_original_img img += lost_detail shrunk_original_img = tf.image.resize(original_img, shape) keras.utils.save_img("DeepDream.png", deprocess_image(img.numpy())) ``` 使用预先定义的函数和变量实现了 DeepDream 算法的过程。首先对原始图像进行预处理,然后根据金字塔层数和缩放比例生成多个连续的图像,对每个图像进行梯度上升处理,最终将所有处理后的图像进行合并,并使用 `keras.utils.save_img` 函数保存最终结果。
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值