TensorFLow 不同大小图片的TFrecords存取实例
程序员文章站
2023-11-27 14:19:16
全部存入一个tfrecords文件,然后读取并显示第一张。
不多写了,直接贴代码。
from pil import image
import numpy as np
i...
全部存入一个tfrecords文件,然后读取并显示第一张。
不多写了,直接贴代码。
from pil import image import numpy as np import matplotlib.pyplot as plt import tensorflow as tf image_path = 'test/' tfrecord_file = image_path + 'test.tfrecord' writer = tf.python_io.tfrecordwriter(tfrecord_file) def _int64_feature(value): return tf.train.feature(int64_list=tf.train.int64list(value=[value])) def _bytes_feature(value): return tf.train.feature(bytes_list=tf.train.byteslist(value=[value])) def get_image_binary(filename): """ you can read in the image using tensorflow too, but it's a drag since you have to create graphs. it's much easier using pillow and numpy """ image = image.open(filename) image = np.asarray(image, np.uint8) shape = np.array(image.shape, np.int32) return shape, image.tobytes() # convert image to raw data bytes in the array. def write_to_tfrecord(label, shape, binary_image, tfrecord_file): """ this example is to write a sample to tfrecord file. if you want to write more samples, just use a loop. """ # write label, shape, and image content to the tfrecord file example = tf.train.example(features=tf.train.features(feature={ 'label': _int64_feature(label), 'h': _int64_feature(shape[0]), 'w': _int64_feature(shape[1]), 'c': _int64_feature(shape[2]), 'image': _bytes_feature(binary_image) })) writer.write(example.serializetostring()) def write_tfrecord(label, image_file, tfrecord_file): shape, binary_image = get_image_binary(image_file) write_to_tfrecord(label, shape, binary_image, tfrecord_file) # print(shape) def main(): # assume the image has the label chihuahua, which corresponds to class number 1 label = [1,2] image_files = [image_path + 'a.jpg', image_path + 'b.jpg'] for i in range(2): write_tfrecord(label[i], image_files[i], tfrecord_file) writer.close() batch_size = 2 filename_queue = tf.train.string_input_producer([tfrecord_file]) reader = tf.tfrecordreader() _, serialized_example = reader.read(filename_queue) img_features = tf.parse_single_example( serialized_example, features={ 'label': tf.fixedlenfeature([], tf.int64), 'h': tf.fixedlenfeature([], tf.int64), 'w': tf.fixedlenfeature([], tf.int64), 'c': tf.fixedlenfeature([], tf.int64), 'image': tf.fixedlenfeature([], tf.string), }) h = tf.cast(img_features['h'], tf.int32) w = tf.cast(img_features['w'], tf.int32) c = tf.cast(img_features['c'], tf.int32) image = tf.decode_raw(img_features['image'], tf.uint8) image = tf.reshape(image, [h, w, c]) label = tf.cast(img_features['label'],tf.int32) label = tf.reshape(label, [1]) # image = tf.image.resize_images(image, (500,500)) #image, label = tf.train.batch([image, label], batch_size= batch_size) with tf.session() as sess: coord = tf.train.coordinator() threads = tf.train.start_queue_runners(coord=coord) image, label=sess.run([image, label]) coord.request_stop() coord.join(threads) print(label) plt.figure() plt.imshow(image) plt.show() if __name__ == '__main__': main()
全部存入一个tfrecords文件,然后按照batch_size读取,注意需要将图片变成一样大才能按照batch_size读取。
from pil import image import numpy as np import matplotlib.pyplot as plt import tensorflow as tf image_path = 'test/' tfrecord_file = image_path + 'test.tfrecord' writer = tf.python_io.tfrecordwriter(tfrecord_file) def _int64_feature(value): return tf.train.feature(int64_list=tf.train.int64list(value=[value])) def _bytes_feature(value): return tf.train.feature(bytes_list=tf.train.byteslist(value=[value])) def get_image_binary(filename): """ you can read in the image using tensorflow too, but it's a drag since you have to create graphs. it's much easier using pillow and numpy """ image = image.open(filename) image = np.asarray(image, np.uint8) shape = np.array(image.shape, np.int32) return shape, image.tobytes() # convert image to raw data bytes in the array. def write_to_tfrecord(label, shape, binary_image, tfrecord_file): """ this example is to write a sample to tfrecord file. if you want to write more samples, just use a loop. """ # write label, shape, and image content to the tfrecord file example = tf.train.example(features=tf.train.features(feature={ 'label': _int64_feature(label), 'h': _int64_feature(shape[0]), 'w': _int64_feature(shape[1]), 'c': _int64_feature(shape[2]), 'image': _bytes_feature(binary_image) })) writer.write(example.serializetostring()) def write_tfrecord(label, image_file, tfrecord_file): shape, binary_image = get_image_binary(image_file) write_to_tfrecord(label, shape, binary_image, tfrecord_file) # print(shape) def main(): # assume the image has the label chihuahua, which corresponds to class number 1 label = [1,2] image_files = [image_path + 'a.jpg', image_path + 'b.jpg'] for i in range(2): write_tfrecord(label[i], image_files[i], tfrecord_file) writer.close() batch_size = 2 filename_queue = tf.train.string_input_producer([tfrecord_file]) reader = tf.tfrecordreader() _, serialized_example = reader.read(filename_queue) img_features = tf.parse_single_example( serialized_example, features={ 'label': tf.fixedlenfeature([], tf.int64), 'h': tf.fixedlenfeature([], tf.int64), 'w': tf.fixedlenfeature([], tf.int64), 'c': tf.fixedlenfeature([], tf.int64), 'image': tf.fixedlenfeature([], tf.string), }) h = tf.cast(img_features['h'], tf.int32) w = tf.cast(img_features['w'], tf.int32) c = tf.cast(img_features['c'], tf.int32) image = tf.decode_raw(img_features['image'], tf.uint8) image = tf.reshape(image, [h, w, c]) label = tf.cast(img_features['label'],tf.int32) label = tf.reshape(label, [1]) image = tf.image.resize_images(image, (224,224)) image = tf.reshape(image, [224, 224, 3]) image, label = tf.train.batch([image, label], batch_size= batch_size) with tf.session() as sess: coord = tf.train.coordinator() threads = tf.train.start_queue_runners(coord=coord) image, label=sess.run([image, label]) coord.request_stop() coord.join(threads) print(image.shape) print(label) plt.figure() plt.imshow(image[0,:,:,0]) plt.show() plt.figure() plt.imshow(image[0,:,:,1]) plt.show() image1 = image[0,:,:,:] print(image1.shape) print(image1.dtype) im = image.fromarray(np.uint8(image1)) #参考numpy和图片的互转:http://blog.csdn.net/zywvvd/article/details/72810360 im.show() if __name__ == '__main__': main()
输出是
(2, 224, 224, 3) [[1] [2]] 第一张图片的三种显示(略)
封装成函数:
# -*- coding: utf-8 -*- """ created on fri sep 8 14:38:15 2017 @author: wayne """ ''' 本文参考了以下代码,在多个不同大小图片存取方面做了重新开发: https://github.com/chiphuyen/stanford-tensorflow-tutorials/blob/master/examples/09_tfrecord_example.py http://blog.csdn.net/hjxu2016/article/details/76165559 https://*.com/questions/41921746/tensorflow-varlenfeature-vs-fixedlenfeature https://github.com/tensorflow/tensorflow/issues/10492 后续: -存入多个tfrecords文件的例子见 http://blog.csdn.net/xierhacker/article/details/72357651 -如何作shuffle和数据增强 string_input_producer (需要理解tf的数据流,标签队列的工作方式等等) http://blog.csdn.net/liuchonge/article/details/73649251 ''' from pil import image import numpy as np import matplotlib.pyplot as plt import tensorflow as tf image_path = 'test/' tfrecord_file = image_path + 'test.tfrecord' writer = tf.python_io.tfrecordwriter(tfrecord_file) def _int64_feature(value): return tf.train.feature(int64_list=tf.train.int64list(value=[value])) def _bytes_feature(value): return tf.train.feature(bytes_list=tf.train.byteslist(value=[value])) def get_image_binary(filename): """ you can read in the image using tensorflow too, but it's a drag since you have to create graphs. it's much easier using pillow and numpy """ image = image.open(filename) image = np.asarray(image, np.uint8) shape = np.array(image.shape, np.int32) return shape, image.tobytes() # convert image to raw data bytes in the array. def write_to_tfrecord(label, shape, binary_image, tfrecord_file): """ this example is to write a sample to tfrecord file. if you want to write more samples, just use a loop. """ # write label, shape, and image content to the tfrecord file example = tf.train.example(features=tf.train.features(feature={ 'label': _int64_feature(label), 'h': _int64_feature(shape[0]), 'w': _int64_feature(shape[1]), 'c': _int64_feature(shape[2]), 'image': _bytes_feature(binary_image) })) writer.write(example.serializetostring()) def write_tfrecord(label, image_file, tfrecord_file): shape, binary_image = get_image_binary(image_file) write_to_tfrecord(label, shape, binary_image, tfrecord_file) def read_and_decode(tfrecords_file, batch_size): '''''read and decode tfrecord file, generate (image, label) batches args: tfrecords_file: the directory of tfrecord file batch_size: number of images in each batch returns: image: 4d tensor - [batch_size, width, height, channel] label: 1d tensor - [batch_size] ''' # make an input queue from the tfrecord file filename_queue = tf.train.string_input_producer([tfrecord_file]) reader = tf.tfrecordreader() _, serialized_example = reader.read(filename_queue) img_features = tf.parse_single_example( serialized_example, features={ 'label': tf.fixedlenfeature([], tf.int64), 'h': tf.fixedlenfeature([], tf.int64), 'w': tf.fixedlenfeature([], tf.int64), 'c': tf.fixedlenfeature([], tf.int64), 'image': tf.fixedlenfeature([], tf.string), }) h = tf.cast(img_features['h'], tf.int32) w = tf.cast(img_features['w'], tf.int32) c = tf.cast(img_features['c'], tf.int32) image = tf.decode_raw(img_features['image'], tf.uint8) image = tf.reshape(image, [h, w, c]) label = tf.cast(img_features['label'],tf.int32) label = tf.reshape(label, [1]) ########################################################## # you can put data augmentation here # distorted_image = tf.random_crop(images, [530, 530, img_channel]) # distorted_image = tf.image.random_flip_left_right(distorted_image) # distorted_image = tf.image.random_brightness(distorted_image, max_delta=63) # distorted_image = tf.image.random_contrast(distorted_image, lower=0.2, upper=1.8) # distorted_image = tf.image.resize_images(distorted_image, (imagesize,imagesize)) # float_image = tf.image.per_image_standardization(distorted_image) image = tf.image.resize_images(image, (224,224)) image = tf.reshape(image, [224, 224, 3]) #image, label = tf.train.batch([image, label], batch_size= batch_size) image_batch, label_batch = tf.train.batch([image, label], batch_size= batch_size, num_threads= 64, capacity = 2000) return image_batch, tf.reshape(label_batch, [batch_size]) def read_tfrecord2(tfrecord_file, batch_size): train_batch, train_label_batch = read_and_decode(tfrecord_file, batch_size) with tf.session() as sess: coord = tf.train.coordinator() threads = tf.train.start_queue_runners(coord=coord) train_batch, train_label_batch = sess.run([train_batch, train_label_batch]) coord.request_stop() coord.join(threads) return train_batch, train_label_batch def main(): # assume the image has the label chihuahua, which corresponds to class number 1 label = [1,2] image_files = [image_path + 'a.jpg', image_path + 'b.jpg'] for i in range(2): write_tfrecord(label[i], image_files[i], tfrecord_file) writer.close() batch_size = 2 # read_tfrecord(tfrecord_file) # 读取一个图 train_batch, train_label_batch = read_tfrecord2(tfrecord_file, batch_size) print(train_batch.shape) print(train_label_batch) plt.figure() plt.imshow(train_batch[0,:,:,0]) plt.show() plt.figure() plt.imshow(train_batch[0,:,:,1]) plt.show() train_batch1 = train_batch[0,:,:,:] print(train_batch.shape) print(train_batch1.dtype) im = image.fromarray(np.uint8(train_batch1)) #参考numpy和图片的互转:http://blog.csdn.net/zywvvd/article/details/72810360 im.show() if __name__ == '__main__': main()
以上这篇tensorflow 不同大小图片的tfrecords存取实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
上一篇: 基于Python获取照片的GPS位置信息
下一篇: Java基础之方法重写和多态示例