如何为 tensorflow 创建正确的文本文件?

本文介绍了如何为 tensorflow 创建正确的文本文件?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

限时送ChatGPT账号..

Tensorflow 找不到从数据帧创建的文本文件.下面的代码给了我错误:

Tensorflow cannot find the text files created from a dataframe. The code below gives me the error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-8-d5b632e1e805> in <module>
      2 seed = 123
      3 
----> 4 train_ds = tf.keras.preprocessing.text_dataset_from_directory(directory='data_tf/train', batch_size=batch_size, validation_split=0.2,subset='training', seed=seed,label_mode='binary',labels=[0,1])
      5 
      6 val_ds = tf.keras.preprocessing.text_dataset_from_directory(directory='data_tf/train', batch_size=batch_size, validation_split=0.2,subset='validation', seed=seed,labels=[0,1],label_mode='binary')

~/my_repo//venv/lib64/python3.7/site-packages/tensorflow/python/keras/preprocessing/text_dataset.py in text_dataset_from_directory(directory, labels, label_mode, class_names, batch_size, max_length, shuffle, seed, validation_split, subset, follow_links)
    155       file_paths, labels, validation_split, subset)
    156   if not file_paths:
--> 157     raise ValueError('No text files found.')
    158 
    159   dataset = paths_and_labels_to_dataset(

ValueError: No text files found.

但在崩溃前也会显示此内容 找到属于 2 个类的 2 个文件.使用 2 个文件进行训练.

but also displays this before crashing Found 2 files belonging to 2 classes. Using 2 files for training.

train_ds = tf.keras.preprocessing.text_dataset_from_directory(directory='data_tf/train', batch_size=batch_size, validation_split=0.2,subset='training', seed=seed,label_mode='binary',labels=[0,1])`

文件夹结构正确，如下:
data_tf >火车 >0 >neg.txt/data_tf >火车 >1 >位置.txt

The folder structure is correct and is the following:
data_tf > train > 0 > neg.txt / data_tf > train > 1 > pos.txt

我使用 to_csv() 函数创建了文本文件:pos_df.to_csv(r'data_tf/train/1/pos.txt', header=None, index=None, sep=' ', mode='a').

I created the text files using to_csv() function : pos_df.to_csv(r'data_tf/train/1/pos.txt', header=None, index=None, sep=' ', mode='a').

我应该用另一种方法创建文本文件，以便 tensorflow 接受它吗?谢谢.

Should I created the text files with another method so it is accepted by tensorflow? Thanks.

推荐答案

每个目录中至少需要两个文本文件，否则无法运行.

You need minimum two text files in each directory, else it won't work.

这篇关于如何为 tensorflow 创建正确的文本文件?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！