Below is my unet model ,i loaded images with kerasImageDataGenerator with 360X480 dim,but when compile the model. but model is complied if dim are 128X128 , 256X256, to load this dim what are parameters should be change and why the concatenate error is thrown i have filters and corresponding are same .
IMG_HEIGHT=360
IMG_WIDTH=480
IMG_CHANNELS=3
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))
c1 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (inputs)
c1 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c1)
c1 = Dropout(0.1) (c1)
p1 = MaxPooling2D((2, 2)) (c1)
c2 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p1)
c2 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c2)
c2 = Dropout(0.1) (c2)
p2 = MaxPooling2D((2, 2)) (c2)
c3 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p2)
c3 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c3)
c3 = Dropout(0.2) (c3)
p3 = MaxPooling2D((2, 2)) (c3)
c4 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p3)
c4 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c4)
c4 = Dropout(0.2) (c4)
p4 = MaxPooling2D(pool_size=(2, 2)) (c4)
c5 = Conv2D(256, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p4)
c5 = Conv2D(256, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c5)
c5 = Dropout(0.3) (c5)
u6 = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same') (c5)
u6 = concatenate([u6, c4])
c6 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u6)
c6 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c6)
c6 = Dropout(0.2) (c6)
u7 = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same') (c6)
u7 = concatenate([u7, c3])
c7 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u7)
c7 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c7)
c7 = Dropout(0.2) (c7)
u8 = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same') (c7)
u8 = concatenate([u8, c2])
c8 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u8)
c8 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c8)
c8 = Dropout(0.1) (c8)
u9 = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same') (c8)
u9 = concatenate([u9, c1], axis=3)
c9 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u9)
c9 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c9)
c9 = Dropout(0.1) (c9)
outputs = Conv2D(3, (1, 1), activation='sigmoid') (c9)
model = Model(inputs=[inputs], outputs=[outputs])
model.compile(optimizer='adam', loss='binary_crossentropy',metrics = ['accuracy'])
model.summary()
Following error is thrown:
'inputs with matching shapes '
361 'except for the concat axis. '
--> 362 'Got inputs shapes: %s' % (input_shape))
363
364 def _merge_function(self, inputs):
ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 44, 60, 128), (None, 45, 60, 128)]
As your input size is not a square image you have to take special care about shapes when upsampling the features resulting from the feature extracting step. I recommend you to reshape your inputs to square images.
This will force to reshape your labeled mask, you can look here to know how to do it.
Finally, this is a working implementation of uNet with square images:
# Credits to https://github.com/zhixuhao/unet/blob/master/model.py
def unet(pretrained_weights = None,input_size = (256,256,1)):
inputs = Input(input_size)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
drop4 = Dropout(0.5)(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)
conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
drop5 = Dropout(0.5)(conv5)
up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop5))
merge6 = concatenate([drop4,up6], axis = 3)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)
up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
merge7 = concatenate([conv3,up7], axis = 3)
conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)
up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
merge8 = concatenate([conv2,up8], axis = 3)
conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)
up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
merge9 = concatenate([conv1,up9], axis = 3)
conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)
model = Model(input = inputs, output = conv10)
model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy'])
I read the UNet paper and the authors state:
To allow a seamless tiling of the output segmentation map (see Figure 2), it is important to select the input tile size such that all 2x2 max-pooling operations are applied to a layer with an even x- and y-size.
So resize your image according to these restrictions.