我用python（v3.8.3）编写了一个简单的CNN。我试图优化网络，我想要更多关于它未能预测的信息。我试图添加一个混淆矩阵，我需要tensorflow.math.confusion_matrix（）测试标签。

我的问题是，我无法弄清楚如何从tf.keras.preprocessing.image创建的数据集对象访问标签_dataset_from_directory（）

我的图像被组织在具有标签作为名称的目录中。留档表示函数返回tf.data.Dataset对象。

If label_mode is None, it yields float32 tensors of shape (batch_size, image_size[0], image_size[1], num_channels), encoding

图像（有关num_channels的规则见下文）。否则，它会生成一个元组（图像、标签），其中图像具有形状（batch_size、image_size[0]、image_size[1]、num_channels），标签遵循下面描述的格式。

代码如下：

import tensorflow as tf
from tensorflow.keras import layers
#import matplotlib.pyplot as plt
import numpy as np
import random

import PIL
import PIL.Image

import os
import pathlib

#load the IMAGES
dataDirectory = '/p/home/username/tensorflow/newBirds'

dataDirectory = pathlib.Path(dataDirectory)
imageCount = len(list(dataDirectory.glob('*/*.jpg')))
print('Image count: {0}\n'.format(imageCount))

#test display an image
# osprey = list(dataDirectory.glob('OSPREY/*'))
# ospreyImage = PIL.Image.open(str(osprey[random.randint(1,100)]))
# ospreyImage.show()

# nFlicker = list(dataDirectory.glob('NORTHERN FLICKER/*'))
# nFlickerImage = PIL.Image.open(str(nFlicker[random.randint(1,100)]))
# nFlickerImage.show()

#set parameters
batchSize = 32
height=224
width=224

(trainData, trainLabels) = tf.keras.preprocessing.image_dataset_from_directory(
    dataDirectory,
    labels='inferred',
    label_mode='categorical',
    validation_split=0.2,
    subset='training',
    seed=324893,
    image_size=(height,width),
    batch_size=batchSize)

testData = tf.keras.preprocessing.image_dataset_from_directory(
    dataDirectory,
    labels='inferred',
    label_mode='categorical',
    validation_split=0.2,
    subset='validation',
    seed=324893,
    image_size=(height,width),
    batch_size=batchSize)

#class names and sampling a few images
classes = trainData.class_names
testClasses = testData.class_names
#plt.figure(figsize=(10,10))
# for images, labels in trainData.take(1):
#     for i in range(9):
#         ax = plt.subplot(3, 3, i+1)
#         plt.imshow(images[i].numpy().astype("uint8"))
#         plt.title(classes[labels[i]])
#         plt.axis("off")
# plt.show()

#buffer to hold the data in memory for faster performance
autotune = tf.data.experimental.AUTOTUNE
trainData = trainData.cache().shuffle(1000).prefetch(buffer_size=autotune)
testData = testData.cache().prefetch(buffer_size=autotune)

#augment the dataset with zoomed and rotated images
#use convolutional layers to maintain spatial information about the images
#use max pool layers to reduce
#flatten and then apply a dense layer to predict classes
model = tf.keras.Sequential([
    #layers.experimental.preprocessing.RandomFlip('horizontal', input_shape=(height, width, 3)),
    #layers.experimental.preprocessing.RandomRotation(0.1),
    #layers.experimental.preprocessing.RandomZoom(0.1),
    layers.experimental.preprocessing.Rescaling(1./255, input_shape=(height, width, 3)),
    layers.Conv2D(16, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(32, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(64, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(128, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(256, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    # layers.Conv2D(512, 3, padding='same', activation='relu'),
    # layers.MaxPooling2D(),
    #layers.Conv2D(1024, 3, padding='same', activation='relu'),
    #layers.MaxPooling2D(),
    #dropout prevents overtraining by not allowing each node to see each datapoint
    #layers.Dropout(0.5),
    layers.Flatten(),
    layers.Dense(512, activation='relu'),
    layers.Dense(len(classes))
    ])

model.compile(optimizer='adam',
              loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])
model.summary()
    
epochs=2
history = model.fit(
    trainData,
    validation_data=testData,
    epochs=epochs
    )

#create confusion matrix
predictions = model.predict_classes(testData)
confusionMatrix = tf.math.confusion_matrix(labels=testClasses, predictions=predictions).numpy()

我试过使用（foo，foo1）=tf。克拉斯。预处理。图像\u数据集\u来自\u目录（dataDirectory等），但我得到（trainData，trainLabels）=tf。克拉斯。预处理。来自\u目录的图像\u数据集\u（值错误：要解压缩的值太多（应为2个）

如果我尝试作为一个变量返回，然后将其拆分为：

train = tf.keras.preprocessing.image_dataset_from_directory(
    dataDirectory,
    labels='inferred',
    label_mode='categorical',
    validation_split=0.2,
    subset='training',
    seed=324893,
    image_size=(height,width),
    batch_size=batchSize)
trainData = train[0]
trainLabels = train[1]

我得到TypeError:“BatchDataset”对象不可下标

我可以访问标签通过testClass=testData.class_names，但我得到：

2020-11-03 14:15:14.643300： W tenstorflow/core/框架/op_kernel.cc:1740]OP_REQUIRES在cast_op.cc:121失败：未实现：不支持将字符串转换为int64 Traceback（最近的调用最后）： File"birdFake.py"， line 115， inConfusionMatrix=tf.math.confusion_matrix（标签=测试类，预测=预测）. Numpy（）File"/p/home/username/minicon da3/lib/python3.8/site-包/tensorflow/python/util/dispatch.py"，第201行，在包装器返回目标（*args，**kwargs）File"/p/home/username/minicon da3/lib/python3.8/site-packages/tensorflow/python/ops/confusion_matrix.py"，第159行，在confusion_matrix标签=math_ops.cast（标签，dtypes.int64）File"/p/home/username/minicon da3/lib/python3.8/site-包/tenstorflow/python/util/dispatch.py"，第201行，在包装器返回目标（*args，**kwargs）File"/p/home/username/minicon da3/lib/python3.8/site-pack/tenorflow/python/ops/math_ops.py"，第966行，在铸x=gen_math_ops.cast（x，base_type，name=name）File"/p/home/username/miniconda3/lib/python3.8/site-packages/tensorflow/python/ops/gen_math_ops.py"，第1827行，_ops.raise_from_not_ok_status（e，name）File"/p/home/username/minicon da3/lib/python3.8/site-包/tenstorflow/python/框架/ops.py"，第6862行，raise_from_not_ok_statussix.raise_from（core._status_to_exception（e.code，消息），无）File"，第3行，raise_fromtensorflow.python.framework.errors_impl。不支持将字符串转换为int64[Op： Cast]

我对任何将这些标签放入混淆矩阵的方法都持开放态度。任何关于为什么我所做的事情不起作用的想法也将受到赞赏。

更新：我尝试了Alexandre Catalano提出的方法，我得到了以下错误

Traceback（最近的调用最后）： File"./birdFake.py"，第118行，在标签=np.concatenate（[标签，np.argmax（y.numpy（），轴=-1）]）File"

我打印了标签数组的第一个元素，它是零