问题描述
在准备数据集以馈入一维CNN时遇到问题。
我的CSV具有3025个列，代表单个字节+最后一个列作为字符串标签。
也许不是预处理问题，而是我的网络模型。
这是我的模特
def cnn_1d(num_classes):
model = models.Sequential()
model.add(Conv1D(16,kernel_size=3,strides=1,activation="relu",input_shape=(3025,1)))
model.add(Conv1D(16,activation="relu"))
model.add(MaxPooling1D(pool_size=2))
model.add(Dropout(0.2))
model.add(Conv1D(32,activation="relu"))
model.add(Conv1D(32,activation="relu"))
model.add(MaxPooling1D(pool_size=2))
model.add(Dropout(0.2))
model.add(Dense(500,activation="relu"))
model.add(Dense(300,activation="relu"))
model.add(Dense(num_classes,activation="softmax"))
model.compile(
optimizer=keras.optimizers.Adam(1e-3),loss="categorical_crossentropy",metrics=["accuracy"],)
model.summary()
return model
这是我尝试预处理的数据：
num_classes = 4
df = pd.read_csv("test.csv",header=0)
df["label"] = pd.Categorical(df["label"])
df["label"] = df.label.cat.codes
Y = df.pop("label")
X = df.copy()
x_train,x_test,y_train,y_test = train_test_split(np.asarray(X),np.asarray(Y),test_size=0.33,shuffle=True)
x_train = np.reshape(x_train,(x_train.shape[0],x_train.shape[1],1))
x_test = np.reshape(x_test,(x_test.shape[0],x_test.shape[1],1))
model = cnn_1d(num_classes)
model.fit(x_train,epochs=100,batch_size=64,validation_data=(x_test,y_test))
我认为由于未正确处理标签，我在最后一个密集层上收到了一个错误。这个我
ValueError: Shapes (None,1) and (None,753,4) are incompatible
我缺少什么？我所知道的是，最后一个Dense层应具有num类作为单位计数（在我的示例中为4）。
解决方法
这是您上面显示的代码的模型摘要：
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d (Conv1D) (None,3023,16) 64
_________________________________________________________________
conv1d_1 (Conv1D) (None,3021,16) 784
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None,1510,16) 0
_________________________________________________________________
dropout (Dropout) (None,16) 0
_________________________________________________________________
conv1d_2 (Conv1D) (None,1508,32) 1568
_________________________________________________________________
conv1d_3 (Conv1D) (None,1506,32) 3104
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None,753,32) 0
_________________________________________________________________
dropout_1 (Dropout) (None,32) 0
_________________________________________________________________
dense (Dense) (None,500) 16500
_________________________________________________________________
dense_1 (Dense) (None,300) 150300
_________________________________________________________________
dense_2 (Dense) (None,4) 1204
=================================================================
Total params: 173,524
Trainable params: 173,524
Non-trainable params: 0
输出层的尺寸为（批，序列长度，4个类）。您可能打算在第二个max_pooling层之后展平矩阵。
如果这样做，我会得到一个参数较少的模型，并将输出4个类之一...
def cnn_1d(num_classes):
model = models.Sequential()
model.add(Conv1D(16,kernel_size=3,strides=1,activation="relu",input_shape=(3025,1)))
model.add(Conv1D(16,activation="relu"))
model.add(MaxPooling1D(pool_size=2))
model.add(Dropout(0.2))
model.add(Conv1D(32,activation="relu"))
model.add(Conv1D(32,activation="relu"))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dropout(0.2))
model.add(Dense(500,activation="relu"))
model.add(Dense(300,activation="relu"))
model.add(Dense(num_classes,activation="softmax"))
model.compile(
optimizer=keras.optimizers.Adam(1e-3),loss="categorical_crossentropy",metrics=["accuracy"],)
model.summary()
return model
cnn_1d(4)
Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d_4 (Conv1D) (None,16) 64
_________________________________________________________________
conv1d_5 (Conv1D) (None,16) 784
_________________________________________________________________
max_pooling1d_2 (MaxPooling1 (None,16) 0
_________________________________________________________________
dropout_2 (Dropout) (None,16) 0
_________________________________________________________________
conv1d_6 (Conv1D) (None,32) 1568
_________________________________________________________________
conv1d_7 (Conv1D) (None,32) 3104
_________________________________________________________________
max_pooling1d_3 (MaxPooling1 (None,32) 0
_________________________________________________________________
flatten (Flatten) (None,24096) 0
_________________________________________________________________
dropout_3 (Dropout) (None,24096) 0
_________________________________________________________________
dense_3 (Dense) (None,500) 12048500
_________________________________________________________________
dense_4 (Dense) (None,300) 150300
_________________________________________________________________
dense_5 (Dense) (None,4) 1204
=================================================================
Total params: 12,205,524
Trainable params: 12,524
Non-trainable params: 0
作为奖励，此模型的可训练参数大大减少。
,我弄清楚了我所缺少的：
- 我错过了在y_ *变量上使用to_categorical。我认为这与
df["label"] = pd.Categorical(df["label"])是绝对的。所以在添加模型之前：y_train = to_categorical(y_train,4) y_test = to_categorical(y_test,4) - 我忘了在MaxPool1D最后一层之后对输出进行展平。
现在它可以正常工作了。