图像分类：train_datagen.flow_from_directory 没有拾取任何图像

Question

我将图像拆分为训练 val 和测试文件夹，用于 keras 图像分类 CNN。但是， train_datagen.flow_from_directory 没有拾取任何图像。它说：找到属于 21 个类别的 0 个图像。我检查了目录，它们看起来很好。 '''

import splitfolders
splitfolders.ratio('imagetype', output="output", seed=1337, ratio=(.8, 0.1,0.1)) 
import tensorflow as tf
from tensorflow import keras
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.metrics import categorical_crossentropy
from tensorflow.keras.preprocessing.image import ImageDataGenerator

train_path = "/home/ubuntu/imageTrain_dobby/SKJEWELLERY/BC4U/google_version/v1.1/lingyau_lee/output/train/"
val_path = "/home/ubuntu/imageTrain_dobby/SKJEWELLERY/BC4U/google_version/v1.1/lingyau_lee/output/val/"
test_path = "/home/ubuntu/imageTrain_dobby/SKJEWELLERY/BC4U/google_version/v1.1/lingyau_lee/output/test/"

img_width, img_height = 225,225 #1000, 1143
batch_size = 10

train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)
 
test_datagen = ImageDataGenerator(rescale=1. / 255)
 
train_generator = train_datagen.flow_from_directory(
    train_path,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode="categorical")
 
validation_generator = test_datagen.flow_from_directory(
    val_path,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode="categorical")

'''

Answer 1

路径应该指向带有类的文件夹，对于每个类，应该有 1 个文件夹。