图像分割 U-Net 模型分配

Question

我的 U-Net 模型

def unet_model(input_size=(96, 128, 3), n_filters=32, n_classes=23):

"""
Unet model

Arguments:
    input_size -- Input shape 
    n_filters -- Number of filters for the convolutional layers
    n_classes -- Number of output classes
Returns: 
    model -- tf.keras.Model
"""
inputs = Input(input_size)
# Contracting Path (encoding)
# Add a conv_block with the inputs of the unet_ model and n_filters
### START CODE HERE
cblock1 = conv_block(inputs, n_filters)
# Chain the first element of the output of each block to be the input of the next conv_block. 
# Double the number of filters at each new step
cblock2 = conv_block(cblock1[0], n_filters*2)
cblock3 = conv_block(cblock2[0], n_filters*4)
cblock4 = conv_block(cblock3[0], n_filters*8, dropout_prob=0.3) # Include a dropout_prob of 0.3 for this layer
# Include a dropout_prob of 0.3 for this layer, and avoid the max_pooling layer
cblock5 = conv_block(cblock4[0], n_filters*16, dropout_prob=0.3, max_pooling=False) 
### END CODE HERE

# Expanding Path (decoding)
# Add the first upsampling_block.
# Use the cblock5[0] as expansive_input and cblock4[1] as contractive_input and n_filters * 8
### START CODE HERE
ublock6 = upsampling_block(cblock5[0], cblock4[1],  n_filters*8)
# Chain the output of the previous block as expansive_input and the corresponding contractive block output.
# Note that you must use the second element of the contractive block i.e before the maxpooling layer. 
# At each step, use half the number of filters of the previous block 
ublock7 = upsampling_block(ublock6[0], cblock5[0],  n_filters*4)
ublock8 = upsampling_block(ublock7[0], ublock6[0],  n_filters*2)
ublock9 = upsampling_block(ublock8[0], ublock7[0],  n_filters)
### END CODE HERE

conv9 = Conv2D(n_filters,
             3,
             activation='relu',
             padding='same',
             kernel_initializer='he_normal')(ublock9)

# Add a Conv2D layer with n_classes filter, kernel size of 1 and a 'same' padding
### START CODE HERE
conv10 = Conv2D(n_filters, 1 , padding='same')(conv9)
### END CODE HERE

model = tf.keras.Model(inputs=inputs, outputs=conv10)

return model

... 在上述 Unet 模型中，模型的前半部分已完成，即直到 cblock5 但是从模型的后半部分，即从 cblock6 到 cblock9 我有点困惑 ...

# 将前一个块的输出链接为 expansive_input 和相应的收缩块输出。
# 请注意，您必须使用收缩块的第二个元素，即在 maxpooling 层之前。
# 在每一步，使用前一个块的一半过滤器数量

... 请帮我理解上述指令的含义。 ...

Answer 1

图中的unet有4个编码块（降序）和4个解码块。

在 unet 中，解码块的输入（张量在前一维返回的那些）它是“同一级别”块和前一个块的连接，作业要求您执行此连接（您可以在图片中看到 2 个不同的箭头如何进入解码级别，这是 2 个输入）

at each step use half the filters: 在每个解码层上只使用一半的过滤器（在图片中有 4 个解码层，所以假设你在第一个解码层（较低的一个）上使用 N 个过滤器，然后在第一个解码层上使用 N/2第二解码层等）

Note that you must use the second element of the contractive block i.e before the maxpooling layer. : 很难说，我想他是在说，当你在 3 级获取编码器的输出时，在某些时候，你会想要将此输入提供给 3 级的解码器（水平灰色图中的箭头，您需要连接的输入），您需要在 maxpooling 之前获取此输入，否则它不会具有相同的尺寸（基本上来自编码器有 2 个输出，红色（maxpool）一个和灰色（复制）一个）

Answer 2

问题是在下半场追踪 cblocks

# UNQ_C3
# GRADED FUNCTION: unet_model
def unet_model(input_size=(96, 128, 3), n_filters=32, n_classes=23):
    """
    Unet model
    
    Arguments:
        input_size -- Input shape 
        n_filters -- Number of filters for the convolutional layers
        n_classes -- Number of output classes
    Returns: 
        model -- tf.keras.Model
    """
    inputs = Input(input_size)
    # Contracting Path (encoding)
    # Add a conv_block with the inputs of the unet_ model and n_filters
    ### START CODE HERE
    cblock1 = conv_block(inputs, n_filters)
    # Chain the first element of the output of each block to be the input of the next conv_block. 
    # Double the number of filters at each new step
    cblock2 = conv_block(cblock1[0], 2*n_filters)
    cblock3 = conv_block(cblock2[0], 4*n_filters)
    cblock4 = conv_block(cblock3[0], 8*n_filters, dropout_prob=0.3) # Include a dropout_prob of 0.3 for this layer
    # Include a dropout_prob of 0.3 for this layer, and avoid the max_pooling layer
    cblock5 = conv_block(cblock4[0], 16*n_filters, dropout_prob=0.3, max_pooling=False) 
    ### END CODE HERE
    
    # Expanding Path (decoding)
    # Add the first upsampling_block.
    # Use the cblock5[0] as expansive_input and cblock4[1] as contractive_input and n_filters * 8
    ### START CODE HERE
    ublock6 = upsampling_block(cblock5[0], cblock4[1],  n_filters * 8)
    # Chain the output of the previous block as expansive_input and the corresponding contractive block output.
    # Note that you must use the second element of the contractive block i.e before the maxpooling layer. 
    # At each step, use half the number of filters of the previous block 
    ublock7 = upsampling_block(ublock6, cblock3[1],  n_filters * 4)
    ublock8 = upsampling_block(ublock7, cblock2[1],  n_filters * 2)
    ublock9 = upsampling_block(ublock8, cblock1[1],  n_filters*1)
    ### END CODE HERE

    conv9 = Conv2D(n_filters,
                 3,
                 activation='relu',
                 padding='same',
                 kernel_initializer='he_normal')(ublock9)

    # Add a Conv2D layer with n_classes filter, kernel size of 1 and a 'same' padding
    ### START CODE HERE
    conv10 = Conv2D(n_classes, 1, padding='same')(conv9)
    ### END CODE HERE
    
    model = tf.keras.Model(inputs=inputs, outputs=conv10)

    return model