从本地数据集为CNN创建TensorFlow数据集

问题描述 投票:1回答:1

我有一个大的B / W图像数据集,有两个类,其中目录的名称是类的名称:

  • 目录SELECTION包含label = selection的所有图像;
  • 目录NEUTRAL包含label = neutral的所有图像。

我需要在TensorFlow数据集中加载所有这些图像,以便在this教程中更改MNIST数据集。

我试图按照this指南,它看起来不错,但有一些问题,我不知道如何解决。按照指南我到达这里:

    from __future__ import absolute_import, division, print_function
    import os
    import pathlib
    import IPython.display as display
    import tensorflow as tf
    import numpy as np
    import matplotlib.pyplot as plt
    np.set_printoptions(threshold=np.nan)

    tf.enable_eager_execution()
    tf.__version__
    os.system('clear')

    #### some tries for the SELECTION dataset ####

    data_root = pathlib.Path('/Users/matteo/Desktop/DATASET_X/SELECTION/TRAIN_IMG')

    all_image_paths = []
    all_image_labels = []
    for item in data_root.iterdir():
        item_tmp = str(item)
        if 'selection.png' in item_tmp:
            all_image_paths.append(str(item))
            all_image_labels.append(0)

    image_count = len(all_image_paths)
    label_names = ['selection', 'neutral']
    label_to_index = dict((name, index) for index, name in enumerate(label_names))
    img_path = all_image_paths[0]
    img_raw = tf.read_file(img_path)

    img_tensor = tf.image.decode_png(
        contents=img_raw,
        channels=1
    )
    print(img_tensor.numpy().min())
    print(img_tensor.numpy().max())
    #### it works fine till here ####

    #### trying to make a function ####
    #### problems from here ####

    def load_and_decode_image(path):
        print('[LOG:load_and_decode_image]: ' + str(path))
        image = tf.read_file(path)

        image = tf.image.decode_png(
            contents=image,
            channels=3
        )

        return image


    image_path = all_image_paths[0]
    label = all_image_labels[0]

    image = load_and_decode_image(image_path)
    print('[LOG:image.shape]: ' + str(image.shape))

    path_ds = tf.data.Dataset.from_tensor_slices(all_image_paths)

    print('shape: ', repr(path_ds.output_shapes))
    print('type: ', path_ds.output_types)
    print()
    print('[LOG:path_ds]:' + str(path_ds))

如果我只加载一个项目它可以工作,但当我尝试做:

path_ds = tf.data.Dataset.from_tensor_slices(all_image_paths)

如果我打印path_ds.shape它返回shape: TensorShape([])所以它似乎不起作用。如果我尝试继续使用此块的教程

image_ds = path_ds.map(load_and_decode_image, num_parallel_calls=AUTOTUNE)
plt.figure(figsize=(8, 8))
for n, image in enumerate(image_ds.take(4)):
    print('[LOG:n, image]: ' + str(n) + ', ' + str(image))
    plt.subplot(2, 2, n+1)
    plt.imshow(image)
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])
    plt.xlabel(' selection'.encode('utf-8'))
    plt.title(label_names[label].title())
plt.show()

它给我以下错误:

It's not possible open ' < string >': The file was not found (file: // /Users/matteo/Documents/GitHub/Cnn_Genetic/cnn_genetic/<string > ).

但问题是我不知道这个文件是什么以及它为什么要寻找它。我不是要绘制我的图像,但我想知道为什么它不起作用。如果我复制/粘贴教程代码我有同样的问题所以我认为新的tf版本存在问题。

所以......如果有人能告诉我哪里出错了,我会非常感激。谢谢你的时间。

python tensorflow dataset load local
1个回答
0
投票

您的问题是path_ds应该是图像路径作为字符串,但您尝试将它们转换为张量列表。

所以要获得张力,你只需要:

image_ds = all_image_paths.map(load_and_decode_image, num_parallel_calls=AUTOTUNE)
© www.soinside.com 2019 - 2024. All rights reserved.