如何在 tensorflow 中使用 flow_from_directory 函数加载验证数据

Question

[已解决]

在 tensorflow 模块 tensorflow.keras.preprocessing.image 中使用 flow_from_directory 函数时遇到问题

我可以加载我的所有数据来训练我的模型，但我无法加载我的数据来验证训练...

我的代码（编辑）[工作！]：

# Import
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, models
from tensorflow.keras.preprocessing.image import ImageDataGenerator

train_data_dir = '../data/train'
validation_data_dir = '../data/validation'

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,
    #validation_split=0.20
    )

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)

def create_dataset(train_data_dir, validation_data_dir, img_height, img_width, batch_size):

    train_generator = train_datagen.flow_from_directory(
        train_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        shuffle=True,
        class_mode='categorical',
        subset = 'training',
        )

    validation_generator = train_datagen.flow_from_directory(
        validation_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        shuffle=True,
        class_mode='categorical',
        subset = 'validation',
        )

    return train_generator, validation_generator

我的数据集位于我在 CNN 模型上调用的函数中，当我运行它时，它总是返回：

Found 0 images belonging to 6 classes.
Epoch 1/5Found 5732 images belonging to 6 classes.
Found 0 images belonging to 6 classes.
Epoch 1/5

编辑： 这是我在 model.py 文件中调用函数 create_dataset 的部分：

image_height = 100
image_width = 100
batch_size = 32

ds_train, ds_validation = create_dataset("../data/train", "../data/validation", image_height, image_width, batch_size)

C ñ ñ ...

model.fit(ds_train, epochs=5, verbose=2)
model.evaluate(ds_validation, verbose=2)
model.save('../complete_saved_model/')

有人可以帮我解决这个问题吗？

Answer 1

在您的 train_generator 中删除代码子集 = 'training'。同样在你的 validation_generator 移除代码子集 = 'validation'。