# 设置

``````import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
``````
```TensorFlow 2.x selected.
```

# 准备和检查图像

## 下载图像

``````img_path = tf.keras.utils.get_file('tensorflow.png','https://tensorflow.org/images/tf_logo.png')
``````
```Downloading data from https://tensorflow.org/images/tf_logo.png
40960/39781 [==============================] - 0s 1us/step
```

## 检查图像

### TensorFlow 图标

``````img_raw = tf.io.read_file(img_path)
img = tf.io.decode_image(img_raw)
img = tf.image.convert_image_dtype(img, tf.float32)
img = tf.image.resize(img, [500,500])

plt.title("TensorFlow Logo with shape {}".format(img.shape))
_ = plt.imshow(img)
``````

### 制作黑白版本

``````bw_img = 1.0 - tf.image.rgb_to_grayscale(img)

_ = plt.imshow(bw_img[...,0], cmap='gray')
``````

# 使用 tfa.image

## 均值滤波

``````mean = tfa.image.mean_filter2d(img, filter_shape=11)
_ = plt.imshow(mean)
``````

## 旋转

``````rotate = tfa.image.rotate(img, tf.constant(np.pi/8))
_ = plt.imshow(rotate)
``````

## 变换

``````transform = tfa.image.transform(img, [1.0, 1.0, -250, 0.0, 1.0, 0.0, 0.0, 0.0])
_ = plt.imshow(transform)
``````

## YIQ 中的随机 HSV

``````delta = 0.5
lower_saturation = 0.1
upper_saturation = 0.9
lower_value = 0.2
upper_value = 0.8
rand_hsvinyiq = tfa.image.random_hsv_in_yiq(img, delta, lower_saturation, upper_saturation, lower_value, upper_value)
_ = plt.imshow(rand_hsvinyiq)
``````

## 调整 YIQ 中的 HSV

``````delta = 0.5
saturation = 0.3
value = 0.6
``````

## 密集图像变形

``````input_img = tf.image.convert_image_dtype(tf.expand_dims(img, 0), tf.dtypes.float32)

flow_shape = [1, input_img.shape[1], input_img.shape[2], 2]
init_flows = np.float32(np.random.normal(size=flow_shape) * 2.0)
dense_img_warp = tfa.image.dense_image_warp(input_img, init_flows)
dense_img_warp = tf.squeeze(dense_img_warp, 0)
_ = plt.imshow(dense_img_warp)
``````

## 欧氏距离变换

• 注：它仅获取二进制图像并生成变换后的图像。如果指定不同的图像，将产生具有单一值的图像
``````gray = tf.image.convert_image_dtype(bw_img,tf.uint8)
# The op expects a batch of images, so add a batch dimension
gray = tf.expand_dims(gray, 0)
eucid = tfa.image.euclidean_dist_transform(gray)
eucid = tf.squeeze(eucid, (0, -1))
_ = plt.imshow(eucid, cmap='gray')
``````

[]
[]