解决keras使用cov1D函数的输入问题
解决了以下错误：
1.ValueError:Input0isincompatiblewithlayerconv1d_1:expectedndim=3,foundndim=4
2.ValueError:Errorwhencheckingtarget:expecteddense_3tohave3dimensions,butgotarraywith…
1.ValueError:Input0isincompatiblewithlayerconv1d_1:expectedndim=3,foundndim=4
错误代码：
model.add(Conv1D(8,kernel_size=3,strides=1,padding='same',input_shape=(x_train.shape))
或者
model.add(Conv1D(8,kernel_size=3,strides=1,padding='same',input_shape=(x_train.shape[1:])))
这是因为模型输入的维数有误，在使用基于tensorflow的keras中，cov1d的input_shape是二维的，应该：
1、reshapex_train的形状
x_train=x_train.reshape((x_train.shape[0],x_train.shape[1],1))
x_test=x_test.reshape((x_test.shape[0],x_test.shape[1],1))
2、改变input_shape
model=Sequential()
model.add(Conv1D(8,kernel_size=3,strides=1,padding='same',input_shape=(x_train.shape[1],1)))
大神原文：
Theinputshapeiswrong,itshouldbeinput_shape=(1,3253)forTheanoor(3253,1)forTensorFlow.Theinputshapedoesn'tincludethenumberofsamples.
Thenyouneedtoreshapeyourdatatoincludethechannelsaxis:
x_train=x_train.reshape((500000,1,3253))
OrmovethechannelsdimensiontotheendifyouuseTensorFlow.Afterthesechangesitshouldwork.
2.ValueError:Errorwhencheckingtarget:expecteddense_3tohave3dimensions,butgotarraywith…
出现此问题是因为ylabel的维数与x_trainx_test不符，既然将x_trainx_test都reshape了，那么也需要对y进行reshape。
解决办法：
同时对照x_train改变ylabel的形状
t_train=t_train.reshape((t_train.shape[0],1))
t_test=t_test.reshape((t_test.shape[0],1))
附：
修改完的代码：
importwarnings
warnings.filterwarnings("ignore")
importos
os.environ["CUDA_VISIBLE_DEVICES"]="0"
importpandasaspd
importnumpyasnp
importmatplotlib
#matplotlib.use('Agg')
importmatplotlib.pyplotasplt
fromsklearn.model_selectionimporttrain_test_split
fromsklearnimportpreprocessing
fromkeras.modelsimportSequential
fromkeras.layersimportDense,Dropout,BatchNormalization,Activation,Flatten,Conv1D
fromkeras.callbacksimportLearningRateScheduler,EarlyStopping,ModelCheckpoint,ReduceLROnPlateau
fromkerasimportoptimizers
fromkeras.regularizersimportl2
fromkeras.modelsimportload_model
df_train=pd.read_csv('./input/train_V2.csv')
df_test=pd.read_csv('./input/test_V2.csv')
df_train.drop(df_train.index[[2744604]],inplace=True)#去掉nan值
df_train["distance"]=df_train["rideDistance"]+df_train["walkDistance"]+df_train["swimDistance"]
#df_train["healthpack"]=df_train["boosts"]+df_train["heals"]
df_train["skill"]=df_train["headshotKills"]+df_train["roadKills"]
df_test["distance"]=df_test["rideDistance"]+df_test["walkDistance"]+df_test["swimDistance"]
#df_test["healthpack"]=df_test["boosts"]+df_test["heals"]
df_test["skill"]=df_test["headshotKills"]+df_test["roadKills"]
df_train_size=df_train.groupby(['matchId','groupId']).size().reset_index(name='group_size')
df_test_size=df_test.groupby(['matchId','groupId']).size().reset_index(name='group_size')
df_train_mean=df_train.groupby(['matchId','groupId']).mean().reset_index()
df_test_mean=df_test.groupby(['matchId','groupId']).mean().reset_index()
df_train=pd.merge(df_train,df_train_mean,suffixes=["","_mean"],how='left',on=['matchId','groupId'])
df_test=pd.merge(df_test,df_test_mean,suffixes=["","_mean"],how='left',on=['matchId','groupId'])
deldf_train_mean
deldf_test_mean
df_train=pd.merge(df_train,df_train_size,how='left',on=['matchId','groupId'])
df_test=pd.merge(df_test,df_test_size,how='left',on=['matchId','groupId'])
deldf_train_size
deldf_test_size
target='winPlacePerc'
train_columns=list(df_test.columns)
"""removesomecolumns"""
train_columns.remove("Id")
train_columns.remove("matchId")
train_columns.remove("groupId")
train_columns_new=[]
fornameintrain_columns:
if'_'inname:
train_columns_new.append(name)
train_columns=train_columns_new
#print(train_columns)
X=df_train[train_columns]
Y=df_test[train_columns]
T=df_train[target]
deldf_train
x_train,x_test,t_train,t_test=train_test_split(X,T,test_size=0.2,random_state=1234)
#scaler=preprocessing.MinMaxScaler(feature_range=(-1,1)).fit(x_train)
scaler=preprocessing.QuantileTransformer().fit(x_train)
x_train=scaler.transform(x_train)
x_test=scaler.transform(x_test)
Y=scaler.transform(Y)
x_train=x_train.reshape((x_train.shape[0],x_train.shape[1],1))
x_test=x_test.reshape((x_test.shape[0],x_test.shape[1],1))
t_train=t_train.reshape((t_train.shape[0],1))
t_test=t_test.reshape((t_test.shape[0],1))
model=Sequential()
model.add(Conv1D(8,kernel_size=3,strides=1,padding='same',input_shape=(x_train.shape[1],1)))
model.add(BatchNormalization())
model.add(Conv1D(8,kernel_size=3,strides=1,padding='same'))
model.add(Conv1D(16,kernel_size=3,strides=1,padding='valid'))
model.add(BatchNormalization())
model.add(Conv1D(16,kernel_size=3,strides=1,padding='same'))
model.add(Conv1D(32,kernel_size=3,strides=1,padding='valid'))
model.add(BatchNormalization())
model.add(Conv1D(32,kernel_size=3,strides=1,padding='same'))
model.add(Conv1D(32,kernel_size=3,strides=1,padding='same'))
model.add(Conv1D(64,kernel_size=3,strides=1,padding='same'))
model.add(Activation('tanh'))
model.add(Flatten())
model.add(Dropout(0.5))
#model.add(Dropout(0.25))
model.add(Dense(512,kernel_initializer='he_normal',activation='relu',W_regularizer=l2(0.01)))
model.add(Dense(128,kernel_initializer='he_normal',activation='relu',W_regularizer=l2(0.01)))
model.add(Dense(1,kernel_initializer='normal',activation='sigmoid'))
optimizers.Adam(lr=0.01,epsilon=1e-8,decay=1e-4)
model.compile(optimizer=optimizer,loss='mse',metrics=['mae'])
model.summary()
ng=EarlyStopping(monitor='val_mean_absolute_error',mode='min',patience=4,verbose=1)
#model_checkpoint=ModelCheckpoint(filepath='best_model.h5',monitor='val_mean_absolute_error',mode='min',save_best_only=True,verbose=1)
#reduce_lr=ReduceLROnPlateau(monitor='val_mean_absolute_error',mode='min',factor=0.5,patience=3,min_lr=0.0001,verbose=1)
history=model.fit(x_train,t_train,
validation_data=(x_test,t_test),
epochs=30,
batch_size=32768,
callbacks=[early_stopping],
verbose=1)predict(Y)
pred=pred.ravel()
补充知识：KerasConv1d参数及输入输出详解
Conv1d(in_channels，out_channels，kernel_size，stride=1，padding=0，dilation=1，groups=1，bias=True)
filters:卷积核的数目(即输出的维度)
kernel_size:整数或由单个整数构成的list/tuple，卷积核的空域或时域窗长度
strides:整数或由单个整数构成的list/tuple，为卷积的步长。任何不为1的strides均为任何不为1的dilation_rata均不兼容
padding:补0策略，为”valid”，”same”或”casual”，”casual”将产生因果(膨胀的)卷积，即output[t]不依赖于input[t+1:]。当对不能违反事件顺序的时序信号建模时有用。“valid”代表只进行有效的卷积，即对边界数据不处理。“same”代表保留边界处的卷积结果，通常会导致输出shape与输入shape相同。
activation:激活函数，为预定义的激活函数名,或逐元素的Theano函数。如果不指定该函数，将不会使用任何激活函数(即使用线性激活函数:a(x)=x)
model.add(Conv1D(filters=nn_params["input_filters"], kernel_size=nn_params["filter_length"], strides=1, padding='valid', activation=nn_params["activation"], kernel_regularizer=l2(nn_params["reg"])))
例：输入维度为（None，1000，4）
第一维度：None
第二维度：
output_length=int((input_length-nn_params["filter_length"]+1))
在此情况下为：
output_length=（1000+2*padding-filters+1）/strides=（1000+2*0-32+1）/1=969
第三维度：filters
以上这篇解决keras使用cov1D函数的输入问题就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持毛票票。