CODEWITHSUNDEEP
tensorflowmachine-learningtensorflow2.0
stoic-santiago
stoic-santiago

Reputation: 259

Tensorflow 2.3 - 'Keyword argument not understood:', 'input'

I'm trying to use the functional API of Keras to model skip connections in a neural net that I intend to use for a segmentation task, and I got the aforementioned error -

Here's my code:

def unet_model(input_size = (256,256,1)):
    input_ = keras.layers.Input(shape=input_size)
    conv1 = keras.layers.Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(input_)
    conv1 = keras.layers.Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    pool1 = keras.layers.MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = keras.layers.Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    conv2 = keras.layers.Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = keras.layers.MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = keras.layers.Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = keras.layers.Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = keras.layers.MaxPooling2D(pool_size=(2, 2))(conv3)
    conv4 = keras.layers.Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = keras.layers.Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = keras.layers.Dropout(0.5)(conv4)
    pool4 = keras.layers.MaxPooling2D(pool_size=(2, 2))(drop4)

    conv5 = keras.layers.Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = keras.layers.Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = keras.layers.Dropout(0.5)(conv5)

    up6 = keras.layers.Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(keras.layers.UpSampling2D(size = (2,2))(drop5))
    merge6 = keras.layers.Concatenate([drop4,up6], axis = 3)
    conv6 = keras.layers.Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = keras.layers.Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = keras.layers.Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(keras.layers.UpSampling2D(size = (2,2))(conv6))
    merge7 = keras.layers.Concatenate([conv3,up7], axis = 3)
    conv7 = keras.layers.Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = keras.layers.Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = keras.layers.Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(keras.layers.UpSampling2D(size = (2,2))(conv7))
    merge8 = keras.layers.Concatenate([conv2,up8], axis = 3)
    conv8 = keras.layers.Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = keras.layers.Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = keras.layers.Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(keras.layers.UpSampling2D(size = (2,2))(conv8))
    merge9 = keras.layers.Concatenate([conv1,up9], axis = 3)
    conv9 = keras.layers.Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = keras.layers.Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv9 = keras.layers.Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv10 = keras.layers.Conv2D(1, 1, activation = 'softmax')(conv9)

    model = keras.Model(inputs = [input_], outputs = [conv10])

    model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy'])

    return model

I get the error when I do:

from unet_model import unet_model
model = unet_model()

What's wrong? The construction seems to be in accordance with the documentation. Please help me out!

UPDATE: I replaced Concatenate with concatenate after reading this answer, and I have a different error now:

     24 
     25         up6 = keras.layers.Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(keras.layers.UpSampling2D(size = (2,2))(drop5))
---> 26         merge6 = keras.layers.concatenate([drop4,up6], axis = 3)
     27         conv6 = keras.layers.Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
     28         conv6 = keras.layers.Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

TypeError: __init__() got multiple values for argument 'axis'

Upvotes: 2

Views: 627

Answers (1)

jona
jona

Reputation: 712

** I am cloning this repository when I faced this similar issue. https://github.com/zhixuhao/unet

I followed these solution to fixed this issue. TypeError: ('Keyword argument not understood:', 'input')

Change:

input --> inputs 
output --> outputs

As for the concatenation, Keras Concatenate TypeError: init() got multiple values for argument 'axis'

Concatenation --> concatenation

Upvotes: 2

Related Questions