I’ve tried to implement a U-Net model to classify audio, and after preprocessing, I’ve converted the data into a dataset of float values. These are the shapes of my X and Y

X_train shape: (3806, 2809)
X_test shape: (952, 2809)
y_train shape: (3806, 1)
y_test shape: (952, 1)

I have tried padding and cropping, yet I still end up with the same issue, just with different dimensions. I have attached the code to my U-net architecture, any advice would be appreciated, Thank you in advance.

import tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, Concatenate, Dropout, ZeroPadding2D

def unet(input_size=(53, 53, 1), num_classes=2):
    inputs = Input(input_size)
    
    # Encoder
    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)

    # Decoder
    up6 = UpSampling2D(size=(2, 2))(drop5)
    conv6 = Conv2D(512, 2, activation='relu', padding='same', kernel_initializer='he_normal')(up6)
    
    # Padding
    pad_top = (conv4.shape[1] - conv6.shape[1]) // 2
    pad_bottom = conv4.shape[1] - conv6.shape[1] - pad_top
    pad_left = (conv4.shape[2] - conv6.shape[2]) // 2
    pad_right = conv4.shape[2] - conv6.shape[2] - pad_left
    padded_conv4 = ZeroPadding2D(padding=((pad_top, pad_bottom), (pad_left, pad_right)))(conv4)
    
    merge6 = Concatenate(axis=3)([padded_conv4, conv6])
    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 = UpSampling2D(size=(2, 2))(conv6)
    conv7 = Conv2D(256, 2, activation='relu', padding='same', kernel_initializer='he_normal')(up7)
    
    # Padding
    pad_top = (conv3.shape[1] - conv7.shape[1]) // 2
    pad_bottom = conv3.shape[1] - conv7.shape[1] - pad_top
    pad_left = (conv3.shape[2] - conv7.shape[2]) // 2
    pad_right = conv3.shape[2] - conv7.shape[2] - pad_left
    padded_conv3 = ZeroPadding2D(padding=((pad_top, pad_bottom), (pad_left, pad_right)))(conv3)
    
    merge7 = Concatenate(axis=3)([padded_conv3, conv7])
    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 = UpSampling2D(size=(2, 2))(conv7)
    conv8 = Conv2D(128, 2, activation='relu', padding='same', kernel_initializer='he_normal')(up8)
    
    # Padding
    pad_top = (conv2.shape[1] - conv8.shape[1]) // 2
    pad_bottom = conv2.shape[1] - conv8.shape[1] - pad_top
    pad_left = (conv2.shape[2] - conv8.shape[2]) // 2
    pad_right = conv2.shape[2] - conv8.shape[2] - pad_left
    padded_conv2 = ZeroPadding2D(padding=((pad_top, pad_bottom), (pad_left, pad_right)))(conv2)
    
    merge8 = Concatenate(axis=3)([padded_conv2, conv8])
    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 = UpSampling2D(size=(2, 2))(conv8)
    conv9 = Conv2D(64, 2, activation='relu', padding='same', kernel_initializer='he_normal')(up9)
    
    # Padding
    pad_top = (conv1.shape[1] - conv9.shape[1]) // 2
    pad_bottom = conv1.shape[1] - conv9.shape[1] - pad_top
    pad_left = (conv1.shape[2] - conv9.shape[2]) // 2
    pad_right = conv1.shape[2] - conv9.shape[2] - pad_left
    padded_conv1 = ZeroPadding2D(padding=((pad_top, pad_bottom), (pad_left, pad_right)))(conv1)
    
    merge9 = Concatenate(axis=3)([padded_conv1, conv9])
    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)
    
    conv10 = Conv2D(num_classes, 1, activation='sigmoid')(conv9)  # Use 'sigmoid' for binary classification

    model = Model(inputs=inputs, outputs=conv10)
    
    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    
    return model

Error:

ValueError                                Traceback (most recent call last)
Cell In[73], line 1
----> 1 model = unet(input_size=(53, 53, 1))

Cell In[72], line 55, in unet(input_size, num_classes)
     52 pad_right = conv3.shape[2] - conv7.shape[2] - pad_left
     53 padded_conv3 = ZeroPadding2D(padding=((pad_top, pad_bottom), (pad_left, pad_right)))(conv3)
---> 55 merge7 = Concatenate(axis=3)([padded_conv3, conv7])
     56 conv7 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(merge7)
     57 conv7 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv7)

File ~anaconda3libsite-packageskerassrcutilstraceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     67     filtered_tb = _process_traceback_frames(e.__traceback__)
     68     # To get the full stack trace, call:
     69     # `tf.debugging.disable_traceback_filtering()`
---> 70     raise e.with_traceback(filtered_tb) from None
     71 finally:
     72     del filtered_tb

File ~anaconda3libsite-packageskerassrclayersmergingconcatenate.py:131, in Concatenate.build(self, input_shape)
    125 unique_dims = set(
    126     shape[axis]
    127     for shape in shape_set
    128     if shape[axis] is not None
    129 )
    130 if len(unique_dims) > 1:
--> 131     raise ValueError(err_msg)

ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concatenation axis. Received: input_shape=[(None, 14, 14, 256), (None, 12, 12, 256)]