在keras中修复3D Conv的input_shape（后端的Tensorflow）

Question

I have around 8k+ images. After preprocessing I have numpy arrays of images of size 224*224*3 and I am using inception_V3 as a base model. I have label(y) of binary classification.

Here are some quick insights:

X_train.shape = (5058, 224, 224, 3, 1)   #after reshaping

Conv_3d input_shape = (5058,224,224, 3) 

Now when I try to fit my model then I am getting this error:

ValueError: Error when checking input: expected conv3d_42_input to have shape (5058, 224, 224, 3) but got array with shape (224, 224, 3, 1)

base_model = InceptionV3(weights='imagenet', include_top=False, input_shape=(224, 224, 3))

def conv_3d():

    model = Sequential()
    model.add(Conv3D(32, (3, 3, 3), activation='relu',input_shape= (5058,224,224, 3) ,padding='same'))                      #(time_sequence, width, height, channels)
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))
    model.add(Conv3D(64, (3, 3, 3), activation='relu'))
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))
    model.add(Conv3D(128, (3, 3, 3), activation='relu'))
    model.add(Conv3D(128, (3, 3, 3), activation='relu'))
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))
    model.add(Conv3D(256, (2, 2, 2), activation='relu'))
    model.add(Conv3D(256, (2, 2, 2), activation='relu'))
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))

    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Dropout(0.5))
    model.add(Dense(1024))
    model.add(Dropout(0.5))
    model.add(Dense(2, activation='softmax'))

    return model


X_train_temp = X_train.reshape(X_train.shape[0], 224, 224, 3, 1)
X_valid_temp = X_valid.reshape(X_valid.shape[0], 224, 224, 3, 1)

model.fit(X_train_temp, y_train, epochs=50, validation_data=(X_valid_temp, y_valid))

Literally, I am screwed up with the above error. I also saw some similar answers but can't find the solution

Answer 1

def conv_3d():

    model = Sequential()
    model.add(Conv3D(32, (3, 3, 3), activation='relu',input_shape= (224,224,3) ,padding='same'))                      #(time_sequence, width, height, channels)
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))
    model.add(Conv3D(64, (3, 3, 3), activation='relu'))
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))
    model.add(Conv3D(128, (3, 3, 3), activation='relu'))
    model.add(Conv3D(128, (3, 3, 3), activation='relu'))
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))
    model.add(Conv3D(256, (2, 2, 2), activation='relu'))
    model.add(Conv3D(256, (2, 2, 2), activation='relu'))
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2)))

    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Dropout(0.5))
    model.add(Dense(1024))
    model.add(Dropout(0.5))
    model.add(Dense(2, activation='softmax'))

    return model


X_train_temp = X_train.reshape(X_train.shape[0], 224, 224, 3, 1)
X_valid_temp = X_valid.reshape(X_valid.shape[0], 224, 224, 3, 1)

model.fit(X_train_temp, y_train, epochs=50, validation_data=(X_valid_temp, y_valid))