我在训练一个深度学习模型时得到了非常低的准确率。我使用了L2正则化来防止过拟合并提高准确率，但这并没有解决问题。这种非常低的准确率的原因是什么？我该如何解决这个问题？
模型的训练准确率几乎完美（>90%），而验证准确率却非常低（<51%）（如下所示）
Epoch 1/152601/2601 - 38s - loss: 1.6510 - accuracy: 0.5125 - val_loss: 1.6108 - val_accuracy: 0.4706Epoch 2/152601/2601 - 38s - loss: 1.1733 - accuracy: 0.7009 - val_loss: 1.5660 - val_accuracy: 0.4971Epoch 3/152601/2601 - 38s - loss: 0.9169 - accuracy: 0.8147 - val_loss: 1.6223 - val_accuracy: 0.4948Epoch 4/152601/2601 - 38s - loss: 0.7820 - accuracy: 0.8551 - val_loss: 1.7773 - val_accuracy: 0.4683Epoch 5/152601/2601 - 38s - loss: 0.6539 - accuracy: 0.8989 - val_loss: 1.7968 - val_accuracy: 0.4937Epoch 6/152601/2601 - 38s - loss: 0.5691 - accuracy: 0.9204 - val_loss: 1.8743 - val_accuracy: 0.4844Epoch 7/152601/2601 - 38s - loss: 0.5090 - accuracy: 0.9327 - val_loss: 1.9348 - val_accuracy: 0.5029Epoch 8/152601/2601 - 40s - loss: 0.4465 - accuracy: 0.9500 - val_loss: 1.9566 - val_accuracy: 0.4787Epoch 9/152601/2601 - 38s - loss: 0.3931 - accuracy: 0.9596 - val_loss: 2.0824 - val_accuracy: 0.4764Epoch 10/152601/2601 - 41s - loss: 0.3786 - accuracy: 0.9596 - val_loss: 2.1185 - val_accuracy: 0.4925Epoch 11/152601/2601 - 38s - loss: 0.3471 - accuracy: 0.9604 - val_loss: 2.1972 - val_accuracy: 0.4879Epoch 12/152601/2601 - 38s - loss: 0.3169 - accuracy: 0.9669 - val_loss: 2.1091 - val_accuracy: 0.4948Epoch 13/152601/2601 - 38s - loss: 0.3018 - accuracy: 0.9685 - val_loss: 2.2073 - val_accuracy: 0.5006Epoch 14/152601/2601 - 38s - loss: 0.2629 - accuracy: 0.9746 - val_loss: 2.2086 - val_accuracy: 0.4971Epoch 15/152601/2601 - 38s - loss: 0.2700 - accuracy: 0.9650 - val_loss: 2.2178 - val_accuracy: 0.4879我尝试增加了训练轮数，这只会提高模型的训练准确率并降低验证准确率。
关于如何克服这个问题的建议有哪些？
我的代码：
def createModel(): input_shape=(11, 3840,1) model = Sequential() #C1 model.add(Conv2D(16, (5, 5), strides=( 2, 2), padding='same',activation='relu', input_shape=input_shape)) model.add(keras.layers.MaxPooling2D(pool_size=( 2, 2), padding='same')) model.add(BatchNormalization()) #C2 model.add(Conv2D(32, ( 3, 3), strides=(1,1), padding='same', activation='relu')) model.add(keras.layers.MaxPooling2D(pool_size=(2, 2), padding='same')) model.add(BatchNormalization()) #C3 model.add(Conv2D(64, (3, 3), strides=( 1,1), padding='same', activation='relu')) model.add(keras.layers.MaxPooling2D(pool_size=(2, 2), padding='same')) model.add(BatchNormalization()) model.add(Dense(64, input_dim=64,kernel_regularizer=regularizers.l2(0.01))) model.add(Flatten()) model.add(Dropout(0.5)) model.add(Dense(256, activation='sigmoid')) model.add(Dropout(0.5)) model.add(Dense(2, activation='softmax')) opt_adam = keras.optimizers.Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0) model.compile(loss='categorical_crossentropy', optimizer=opt_adam, metrics=['accuracy']) return modeldef getFilesPathWithoutSeizure(indexSeizure, indexPat): filesPath=[] print(indexSeizure) print(indexPat) for i in range(0, nSeizure): if(i==indexSeizure): filesPath.extend(interictalSpectograms[i]) filesPath.extend(preictalSpectograms[i]) shuffle(filesPath) return filesPathdef generate_arrays_for_training(indexPat, paths, start=0, end=100): while True: from_=int(len(paths)/100*start) to_=int(len(paths)/100*end) for i in range(from_, int(to_)): f=paths[i] x = np.load(PathSpectogramFolder+f) x = np.expand_dims(np.expand_dims(x, axis=0), axis = 0) x = x.transpose(0, 2, 3, 1) if('P' in f): y = np.repeat([[0,1]],x.shape[0], axis=0) else: y =np.repeat([[1,0]],x.shape[0], axis=0) yield(x,y)filesPath=getFilesPathWithoutSeizure(i, indexPat)history=model.fit_generator(generate_arrays_for_training(indexPat, filesPath, end=75),#It take the first 75% validation_data=generate_arrays_for_training(indexPat, filesPath, start=75), #It take the last 25% steps_per_epoch=int((len(filesPath)-int(len(filesPath)/100*25))), validation_steps=int((len(filesPath)-int(len(filesPath)/100*75))), verbose=2,class_weight = {0:1, 1:1}, epochs=15, max_queue_size=2, shuffle=True)回答：
您似乎在getFilesPathWithoutSeizure()函数中实现了洗牌功能，不过您可以通过多次打印文件名来验证洗牌是否真正起作用了。
filesPath=getFilesPathWithoutSeizure(i, indexPat) – i是否得到了更新？
根据您的代码if(i==indexSeizure):在getFilesPathWithoutSeizure方法中，当indexSeizure等于for循环的计数器（i）时，只会返回1个文件
如果您在调用函数时没有更改传递的i参数，这可能意味着只有1个文件被返回到filePath变量中，并且您的整个训练过程是在3467个文件的75%之外的1个输入数据上完成的。
—
在确认洗牌功能正常工作并且您的函数调用确实将所有数据插入到filePath变量中后，如果问题仍然没有解决，请尝试以下方法：
数据增强可以通过应用随机但现实的变换（如图像旋转、剪切、水平和垂直翻转、缩放、去中心化等）来增加数据集的多样性，从而帮助解决过拟合问题。
但更重要的是，您需要手动查看数据并了解训练数据中的相似性。
另一个选择是获取更多且更具多样性的数据进行训练。
