"loss : nan" 正在为表格数据训练 "convolution 1D" 神经网络

Question

我需要为表格数据集上的多 class class 化实现 CNN。我的数据有 X_train.shape = (1534185, 81, 1) 和 Y_train = (1534185, 11)

这是我的数据集中的样本

DataSetImage

我试图规范化数据，但值太大而无法添加并存储在 float64 中。

我实现的CNN模型如下

batchSize =  X_train.shape[0]
length =  X_train.shape[1]
channel = X_train.shape[2]
n_outputs = y_train.shape[1]


#Initialising the CNN
model = Sequential()

#1.Multiple convolution and max pooling

model.add(Convolution1D(filters=64, kernel_size=3, activation="relu", input_shape=(length, channel)))
model.add(MaxPooling1D(strides=4))
model.add(Dropout(0.1))
model.add(BatchNormalization())


model.add(Convolution1D(filters= 32, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(strides=4))
model.add(Dropout(0.1))
model.add(BatchNormalization())


model.add(Convolution1D(filters= 16, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(strides=4))
model.add(Dropout(0.1))
model.add(BatchNormalization())

#2.Flattening
model.add(Dropout(0.2))
model.add(Flatten())

#3.Full Connection

model.add(Dense(30, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

如果我尝试更改内核大小，则会出现以下错误

ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling1d_103/MaxPool' (op: 'MaxPool') with input shapes: [?,1,1,16].

当我尝试使用下面的代码训练我的模型时，在损失 = Nan 的情况下我的准确性没有提高

history = model.fit(
    X_train,
    y_train,
    batch_size=1000,
    epochs=2,
    validation_data=(X_test, y_test),
)

损失：nan

Error:
Train on 1534185 samples, validate on 657509 samples
Epoch 1/2
 956000/1534185 [=================>............] - ETA: 1:44 - loss: nan - accuracy: 0.0101

需要你的帮助

Answer 1

尝试检查 inf 值并将其替换为 nan 并重试

X_train.replace([np.inf, -np.inf], np.nan,inplace=True)
X_train = X_train.fillna(0)

"loss : nan" 正在为表格数据训练 "convolution 1D" 神经网络

"loss : nan" in training of "convolution 1D" neural Network for tabular data

neural-network

conv-neural-network

keras

multiclass-classification

loss-function