Getting an error TypeError: cannot unpack non-iterable float object

Question

我想评估我的 ML 模型，但收到此错误：

TypeError: cannot unpack non-iterable float object

我的代码如下：

# mlp for the blobs multi-class classification problem with cross-entropy loss
from sklearn.datasets import make_blobs
from keras.layers import Dense
from keras.models import Sequential
from keras.optimizers import SGD
from tensorflow.keras.utils import to_categorical
from matplotlib import pyplot

# evaluate the model
_, train_acc = model.evaluate(trainX, trainY, verbose=2)
_, test_acc = model.evaluate(testX, testY, verbose=2)
print('Train: %.3f, Test: %.3f' % (train_acc, test_acc))

Answer 1

很可能您的模型没有准确率指标，model.evaluate() returns 只有损失。您可以像这样检查可用指标：

print(model.metrics_names)

可能它的输出只是 ['loss']，并且没有准确度指标，因为您没有在 model.compile().

上提供它

因为它只是 returns 损失，你应该像这样改变这一行：

train_loss = model.evaluate(trainX, trainY, verbose=2)
test_loss = model.evaluate(testX, testY, verbose=2)

如果你想获得准确性，你应该将它添加到你的模型编译中：

model.compile(loss='...',metrics=['accuracy'],optimizer='adam')
.
.
train_loss, train_acc = model.evaluate(trainX, trainY, verbose=2)
test_loss, test_acc = model.evaluate(testX, testY, verbose=2)

Getting an error TypeError: cannot unpack non-iterable float object

Getting an error TypeError: cannot unpack non-iterable float object

python

typeerror

keras

tensorflow