如何在Tensorflow中为预取的数据集绘制混淆矩阵 [英] How to plot confusion matrix for prefetched dataset in Tensorflow
问题描述
我正在尝试使用以下代码为图像分类器绘制混淆矩阵,但出现错误消息:"PrefetchDataset"对象没有属性"classes"
I was trying to plot a confusion matrix for my image classifier with the following code but I got an error message: 'PrefetchDataset' object has no attribute 'classes'
Y_pred = model.predict(validation_dataset)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(validation_dataset.classes, y_pred)) # ERROR message generated
推荐答案
您可以使用 tf.stack
来连接所有数据集值.像这样:
You can use tf.stack
to concatenate all the dataset values. Like so:
true_categories = tf.concat([y for x, y in test_dataset], axis=0)
为了可重复性,假设您有一个数据集,一个神经网络和一个训练循环:
For reproducibility, let's say you have a dataset, a neural network, and a training loop:
import tensorflow_datasets as tfds
import tensorflow as tf
from sklearn.metrics import confusion_matrix
data, info = tfds.load('iris', split='train',
as_supervised=True,
shuffle_files=True,
with_info=True)
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_dataset = data.take(120).batch(4).prefetch(buffer_size=AUTOTUNE)
test_dataset = data.skip(120).take(30).batch(4).prefetch(buffer_size=AUTOTUNE)
model = tf.keras.Sequential([
tf.keras.layers.Dense(8, activation='relu'),
tf.keras.layers.Dense(16, activation='relu'),
tf.keras.layers.Dense(info.features['label'].num_classes, activation='softmax')
])
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam',
metrics='accuracy')
history = model.fit(train_dataset, validation_data=test_dataset, epochs=50, verbose=0)
现在您的模型已经拟合,您可以预测测试集:
Now that your model has been fitted, you can predict the test set:
y_pred = model.predict(test_dataset)
array([[2.2177568e-05, 3.0841196e-01, 6.9156587e-01],
[4.3539176e-06, 1.2779665e-01, 8.7219906e-01],
[1.0816366e-03, 9.2667454e-01, 7.2243840e-02],
[9.9921310e-01, 7.8686583e-04, 9.8775059e-09]], dtype=float32)
这将是一个(n_samples,3)
数组,因为我们正在处理三个类别.我们需要一个(n_samples,1)
数组用于 sklearn.metrics.confusion_matrix
,因此采用argmax:
This is going to be a (n_samples, 3)
array because we're working with three categories. We want a (n_samples, 1)
array for sklearn.metrics.confusion_matrix
, so take the argmax:
predicted_categories = tf.argmax(y_pred, axis=1)
<tf.Tensor: shape=(30,), dtype=int64, numpy=
array([2, 2, 2, 0, 2, 2, 2, 2, 1, 1, 2, 0, 0, 2, 1, 1, 1, 2, 0, 2, 1, 2,
1, 0, 2, 0, 1, 2, 1, 0], dtype=int64)>
然后,我们可以从预取数据集中获取所有 y
值:
Then, we can take all the y
values from the prefetch dataset:
true_categories = tf.concat([y for x, y in test_dataset], axis=0)
[<tf.Tensor: shape=(4,), dtype=int64, numpy=array([1, 1, 1, 0], dtype=int64)>,
<tf.Tensor: shape=(4,), dtype=int64, numpy=array([2, 2, 2, 2], dtype=int64)>,
<tf.Tensor: shape=(4,), dtype=int64, numpy=array([1, 1, 1, 0], dtype=int64)>,
<tf.Tensor: shape=(4,), dtype=int64, numpy=array([0, 2, 1, 1], dtype=int64)>,
<tf.Tensor: shape=(4,), dtype=int64, numpy=array([1, 2, 0, 2], dtype=int64)>,
<tf.Tensor: shape=(4,), dtype=int64, numpy=array([1, 2, 1, 0], dtype=int64)>,
<tf.Tensor: shape=(4,), dtype=int64, numpy=array([2, 0, 1, 2], dtype=int64)>,
<tf.Tensor: shape=(2,), dtype=int64, numpy=array([1, 0], dtype=int64)>]
然后,您就可以获取混淆矩阵:
Then, you are ready to get the confusion matrix:
confusion_matrix(predicted_categories, true_categories)
array([[ 9, 0, 0],
[ 0, 9, 0],
[ 0, 2, 10]], dtype=int64)
(9 + 9 + 10)/30 = 0.933
是准确性得分.它对应于 model.evaluate(test_dataset)
:
(9 + 9 + 10) / 30 = 0.933
is the accuracy score. It corresponds to model.evaluate(test_dataset)
:
8/8 [==============================] - 0s 785us/step - loss: 0.1907 - accuracy: 0.9333
结果也与 sklearn.metrics.classification_report
一致:
precision recall f1-score support
0 1.00 1.00 1.00 8
1 0.82 1.00 0.90 9
2 1.00 0.85 0.92 13
accuracy 0.93 30
macro avg 0.94 0.95 0.94 30
weighted avg 0.95 0.93 0.93 30
这是完整的代码:
import tensorflow_datasets as tfds
import tensorflow as tf
from sklearn.metrics import confusion_matrix
data, info = tfds.load('iris', split='train',
as_supervised=True,
shuffle_files=True,
with_info=True)
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_dataset = data.take(120).batch(4).prefetch(buffer_size=AUTOTUNE)
test_dataset = data.skip(120).take(30).batch(4).prefetch(buffer_size=AUTOTUNE)
model = tf.keras.Sequential([
tf.keras.layers.Dense(8, activation='relu'),
tf.keras.layers.Dense(16, activation='relu'),
tf.keras.layers.Dense(info.features['label'].num_classes, activation='softmax')
])
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam',
metrics='accuracy')
history = model.fit(train_dataset, validation_data=test_dataset, epochs=50, verbose=0)
y_pred = model.predict(test_dataset)
predicted_categories = tf.argmax(y_pred, axis=1)
true_categories = tf.concat([y for x, y in test_dataset], axis=0)
confusion_matrix(predicted_categories, true_categories)
这篇关于如何在Tensorflow中为预取的数据集绘制混淆矩阵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!