使用keras进行分类问题时，验证集loss,accuracy 显示0.0000e+00，但是最后画图像时能显示出验证曲线

data_train, data_test, label_train, label_test = train_test_split(data_all, label_all, test_size= 0.2, random_state = 1)

data_train, data_val, label_train, label_val = train_test_split(data_train,label_train, test_size = 0.25)

data_train = np.asarray(data_train, np.float32)
data_test = np.asarray(data_test, np.float32)
data_val = np.asarray(data_val, np.float32)
label_train = np.asarray(label_train, np.int32)
label_test = np.asarray(label_test, np.int32)
label_val = np.asarray(label_val, np.int32)

training = model.fit_generator(datagen.flow(data_train, label_train_binary, batch_size=200,shuffle=True), validation_data=(data_val,label_val_binary), samples_per_epoch=len(data_train)*8, nb_epoch=30, verbose=1)

def plot_history(history):
plt.plot(training.history['acc'])
plt.plot(training.history['val_acc'])
plt.title('model accuracy')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.legend(['acc', 'val_acc'], loc='lower right')
plt.show()
plt.plot(training.history['loss'])
plt.plot(training.history['val_loss'])
plt.title('model loss')
plt.xlabel('epoch')
plt.ylabel('loss')
plt.legend(['loss', 'val_loss'], loc='lower right')
plt.show()

plot_history(training)

没看到你history输出的代码，感觉曲线图是可信的，而你输出val_loss的时候输出错了。

数据的类型不一致，有的是int，有的是float，需要转成一样的进行计算

你的目标函数有问题吧

你的batch_size 设置200，实际上只有29，你把它改为29试试