为什么“I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version”无法完成

Question

这是我的数据。它有 7 个图像：

我autokeras 用来训练：

import tensorflow as tf
import numpy as np
import autokeras as ak
from tensorflow.keras.preprocessing import image

BATCH_SIZE = 32
IMG_HEIGHT = 224
IMG_WIDTH = 224
train_data_dir = "E:\\DemoTensorflow\\NhanDienDoiTuong\\Data\\Traintest"


def preprocess(img):
    img = image.array_to_img(img, scale=False)
    img = img.resize((IMG_WIDTH, IMG_HEIGHT))
    img = image.img_to_array(img)
    return img / 255.0


image_generator = tf.keras.preprocessing.image.ImageDataGenerator(
    rescale=1.0 / 255,
    horizontal_flip=True,
    validation_split=0.2,
    preprocessing_function=preprocess,
)

train_generator = image_generator.flow_from_directory(
    directory=train_data_dir,
    batch_size=BATCH_SIZE,
    shuffle=True,
    target_size=(IMG_HEIGHT, IMG_WIDTH),
    subset="training",
)

val_generator = image_generator.flow_from_directory(
    directory=train_data_dir,
    batch_size=BATCH_SIZE,
    shuffle=True,
    # class_mode="categorical",
    target_size=(IMG_HEIGHT, IMG_WIDTH),
    subset="validation",
)


def callable_iterator(generator):
    for img_batch, targets_batch in generator:
        yield img_batch, targets_batch


train_dataset = tf.data.Dataset.from_generator(
    lambda: callable_iterator(train_generator),
    output_types=(tf.float32, tf.int8),
    output_shapes=(
        tf.TensorShape([None, 224, 224, 3]),
        tf.TensorShape([None, 2]),
    ),
)
val_dataset = tf.data.Dataset.from_generator(lambda: callable_iterator(val_generator),output_types=(tf.float32, tf.float32))

clf = ak.ImageClassifier(max_trials=10)
clf.fit(train_dataset, epochs=10)
print(clf.evaluate(val_dataset))

结果：执行时无法完成：在此命令处挂起很长时间： StreamExecutor device (0): Host, Default Version

为什么不能完成我的训练？

我的操作系统是 Win7、python 3.8、tensorflow 2.3、autokeras 1.0.8