模型输入必须来自`tf.keras.Input` ...,它们不能是前一个非输入层的输出

Model inputs must come from `tf.keras.Input` ..., they cannot be the output of a previous non-Input layer

我正在使用 Python 3.7.7。和 Tensorflow 2.1.0.

我有一个预训练的 U-Net 网络,我想得到它的编码器它的解码器

如下图:

您可以看到一个卷积编码器-解码器架构。我想得到encoder部分,也就是图片左边出现的图层:

解码器部分:

我从这个函数得到 U-Net 模型:

def get_unet_uncompiled(img_shape = (200,200,1)):
    inputs = Input(shape=img_shape)

    conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', data_format="channels_last", name='conv1_1')(inputs)
    conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', data_format="channels_last", name='conv1_2')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool1')(conv1)
    conv2 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv2_1')(pool1)
    conv2 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv2_2')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool2')(conv2)

    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv3_1')(pool2)
    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv3_2')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool3')(conv3)

    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv4_1')(pool3)
    conv4 = Conv2D(256, (4, 4), activation='relu', padding='same', data_format="channels_last", name='conv4_2')(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool4')(conv4)

    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv5_1')(pool4)
    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv5_2')(conv5)

    up_conv5 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv5')(conv5)
    ch, cw = get_crop_shape(conv4, up_conv5)
    crop_conv4 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv4')(conv4)
    up6 = concatenate([up_conv5, crop_conv4])
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv6_1')(up6)
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv6_2')(conv6)

    up_conv6 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv6')(conv6)
    ch, cw = get_crop_shape(conv3, up_conv6)
    crop_conv3 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv3')(conv3)
    up7 = concatenate([up_conv6, crop_conv3])
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv7_1')(up7)
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv7_2')(conv7)

    up_conv7 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv7')(conv7)
    ch, cw = get_crop_shape(conv2, up_conv7)
    crop_conv2 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv2')(conv2)
    up8 = concatenate([up_conv7, crop_conv2])
    conv8 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv8_1')(up8)
    conv8 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv8_2')(conv8)

    up_conv8 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv8')(conv8)
    ch, cw = get_crop_shape(conv1, up_conv8)
    crop_conv1 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv1')(conv1)
    up9 = concatenate([up_conv8, crop_conv1])
    conv9 = Conv2D(64, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv9_1')(up9)
    conv9 = Conv2D(64, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv9_2')(conv9)

    ch, cw = get_crop_shape(inputs, conv9)
    conv9 = ZeroPadding2D(padding=(ch, cw), data_format="channels_last", name='conv9_3')(conv9)
    conv10 = Conv2D(1, (1, 1), activation='sigmoid', data_format="channels_last", name='conv10_1')(conv9)
    model = Model(inputs=inputs, outputs=conv10)

    return model

辅助功能为:

def get_crop_shape(target, refer):
    # width, the 3rd dimension
    cw = (target.get_shape()[2] - refer.get_shape()[2])
    assert (cw >= 0)
    if cw % 2 != 0:
        cw1, cw2 = cw // 2, cw // 2 + 1
    else:
        cw1, cw2 = cw // 2, cw // 2
    # height, the 2nd dimension
    ch = (target.get_shape()[1] - refer.get_shape()[1])
    assert (ch >= 0)
    if ch % 2 != 0:
        ch1, ch2 = ch // 2, ch // 2 + 1
    else:
        ch1, ch2 = ch // 2, ch // 2

    return (ch1, ch2), (cw1, cw2)

此模型的图表是:

我训练网络,训练后我让编码器这样做:

first_encoder_layer = 0
last_encoder_layer = 14
old_model = get_unet_uncompiled()

old_model.compile(tf.keras.optimizers.Adam(lr=(1e-4) * 2),
              loss='binary_crossentropy',
              metrics=['accuracy'])

encoder: Model = Model(inputs=old_model.layers[first_encoder_layer].input,
                     outputs=old_model.layers[last_encoder_layer].output,
                     name='encoder')

而且效果很好。

但是,当我尝试使用以下方法提取解码器时:

decoder: Model = Model(inputs=old_model.layers[last_encoder_layer + 1].input,
                     outputs=old_model.layers[-1].output,
                     name='decoder')

我收到这些我不理解的错误:

WARNING:tensorflow:Model inputs must come from `tf.keras.Input` (thus holding past layer metadata), they cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "decoder" was not an Input tensor, it was generated by layer up_conv5.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: up_conv5/Identity:0
WARNING:tensorflow:Model inputs must come from `tf.keras.Input` (thus holding past layer metadata), they cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "decoder" was not an Input tensor, it was generated by layer crop_conv4.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: crop_conv4/Identity:0

一个TraceBack,然后另一个错误:

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(None, 200, 200, 1), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []

我试过这段代码来获取解码器:

decoder_input = Input(shape=(12, 12, 512), name='dec_input')
z = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_dec_conv5')(decoder_input)
decoder: Model = Model(inputs=z,
                     outputs=old_model.layers[-1].output,
                     name='decoder')

但我得到的错误大多是相同的:

WARNING:tensorflow:Model inputs must come from `tf.keras.Input` (thus holding past layer metadata), they cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "decoder" was not an Input tensor, it was generated by layer up_dec_conv5.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: up_dec_conv5/Identity:0

如何从预训练的 U-Net 网络中获取解码器?

我的建议是为编码器和解码器定义一个结构(get_encoderget_decoder)。在整个模型的训练之后,我们的想法是创建一个新的解码器架构(通过get_decoder),我们可以用解码器训练的权重

填充它

pythonic 你可以用这种方式做到这一点...

def get_crop_shape(target, refer):
    
    # width, the 3rd dimension
    cw = (target.get_shape()[2] - refer.get_shape()[2])
    assert (cw >= 0)
    if cw % 2 != 0:
        cw1, cw2 = cw // 2, cw // 2 + 1
    else:
        cw1, cw2 = cw // 2, cw // 2
    # height, the 2nd dimension
    ch = (target.get_shape()[1] - refer.get_shape()[1])
    assert (ch >= 0)
    if ch % 2 != 0:
        ch1, ch2 = ch // 2, ch // 2 + 1
    else:
        ch1, ch2 = ch // 2, ch // 2

    return (ch1, ch2), (cw1, cw2)

def get_encoder(img_shape):
    
    inp = Input(shape=img_shape)
    conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', data_format="channels_last", name='conv1_1')(inp)
    conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', data_format="channels_last", name='conv1_2')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool1')(conv1)
    conv2 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv2_1')(pool1)
    conv2 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv2_2')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool2')(conv2)

    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv3_1')(pool2)
    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv3_2')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool3')(conv3)

    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv4_1')(pool3)
    conv4 = Conv2D(256, (4, 4), activation='relu', padding='same', data_format="channels_last", name='conv4_2')(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool4')(conv4)

    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv5_1')(pool4)
    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv5_2')(conv5)
    
    return conv5,conv4,conv3,conv2,conv1,inp

def get_decoder(convs):
    
    conv5,conv4,conv3,conv2,conv1,inputs = convs
    
    up_conv5 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv5')(conv5)
    ch, cw = get_crop_shape(conv4, up_conv5)
    crop_conv4 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv4')(conv4)
    up6 = concatenate([up_conv5, crop_conv4])
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv6_1')(up6)
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv6_2')(conv6)

    up_conv6 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv6')(conv6)
    ch, cw = get_crop_shape(conv3, up_conv6)
    crop_conv3 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv3')(conv3)
    up7 = concatenate([up_conv6, crop_conv3])
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv7_1')(up7)
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv7_2')(conv7)

    up_conv7 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv7')(conv7)
    ch, cw = get_crop_shape(conv2, up_conv7)
    crop_conv2 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv2')(conv2)
    up8 = concatenate([up_conv7, crop_conv2])
    conv8 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv8_1')(up8)
    conv8 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv8_2')(conv8)

    up_conv8 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv8')(conv8)
    ch, cw = get_crop_shape(conv1, up_conv8)
    crop_conv1 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv1')(conv1)
    up9 = concatenate([up_conv8, crop_conv1])
    conv9 = Conv2D(64, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv9_1')(up9)
    conv9 = Conv2D(64, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv9_2')(conv9)

    ch, cw = get_crop_shape(inputs, conv9)
    conv9 = ZeroPadding2D(padding=(ch, cw), data_format="channels_last", name='conv9_3')(conv9)
    conv10 = Conv2D(1, (1, 1), activation='sigmoid', data_format="channels_last", name='conv10_1')(conv9)
    
    return conv10
    

def get_unet(img_shape = (200,200,1)):

    enc = get_encoder(img_shape)
    
    dec = get_decoder(enc)
    
    model = Model(inputs=enc[-1], outputs=dec)

    return model

创建整个模型并拟合

img_shape = (200,200,1)

old_model = get_unet(img_shape)

# old_model.compile(...)
# old_model.fit(...)

像往常一样提取编码器

# extract encoder
first_encoder_layer = 0
last_encoder_layer = 14
encoder_output_layer = [14, 11, 8, 5, 2, 0]

encoder = Model(inputs=old_model.layers[first_encoder_layer].input,
                outputs=[old_model.layers[l].output for l in encoder_output_layer],
                name='encoder')

encoder.summary()

创建解码器结构并分配经过训练的权重

# extract decoder fitted weights
restored_w = []
for w in old_model.layers[last_encoder_layer + 1:]:
    restored_w.extend(w.get_weights())
  
# reconstruct decoder architecture setting the fitted weights
new_inp = [Input(l.shape[1:]) for l in get_encoder(img_shape)]
new_dec = get_decoder(new_inp)
decoder = Model(new_inp, new_dec)
decoder.set_weights(restored_w)

decoder.summary()

return 预测

# generate random images
n_images = 20
X = np.random.uniform(0,1, (n_images,200,200,1)).astype('float32')

# get encoder predictions 
pred_encoder = encoder.predict(X)
print([p.shape for p in pred_encoder])

# get decoder predictions
pred_decoder = decoder.predict(pred_encoder)
print(pred_decoder.shape)

here 运行 笔记本