轉:https://blog.csdn.net/UESTC_C2_403/article/details/72699260
tensorflow裏面用於改變圖像大小的函數是tf.image.resize_images(image, (w, h), method):image表示需要改變此存的圖像,第二個參數改變之後圖像的大小,method用於表示改變圖像過程用的差值方法。0:雙線性差值。1:最近鄰居法。2:雙三次插值法。3:面積插值法。
import matplotlib.pyplot as plt;
import tensorflow as tf;
image_raw_data_jpg = tf.gfile.FastGFile('11.jpg', 'r').read()
with tf.Session() as sess:
img_data_jpg = tf.image.decode_jpeg(image_raw_data_jpg)
img_data_jpg = tf.image.convert_image_dtype(img_data_jpg, dtype=tf.float32)
resize_0 = tf.image.resize_images(img_data_jpg, (500, 500), method=0)
resize_1 = tf.image.resize_images(img_data_jpg, (500, 500), method=1)
resize_2 = tf.image.resize_images(img_data_jpg, (500, 500), method=2)
resize_3 = tf.image.resize_images(img_data_jpg, (500, 500), method=3)
print resize_0.get_shape
plt.figure(0)
plt.imshow(resize_0.eval())
plt.figure(1)
plt.imshow(resize_1.eval())
plt.figure(2)
plt.imshow(resize_2.eval())
plt.figure(3)
plt.imshow(resize_3.eval())
plt.show()