Question

我正在使用Python 3.7.7，Tensorflow 2.1.0和Functional Api通过以下摘要定义编码器：

Model: "encoder"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 200, 200, 1)]     0         
_________________________________________________________________
conv1_1 (Conv2D)             (None, 200, 200, 64)      1664      
_________________________________________________________________
conv1_2 (Conv2D)             (None, 200, 200, 64)      102464    
_________________________________________________________________
pool1 (MaxPooling2D)         (None, 100, 100, 64)      0         
_________________________________________________________________
conv2_1 (Conv2D)             (None, 100, 100, 96)      55392     
_________________________________________________________________
conv2_2 (Conv2D)             (None, 100, 100, 96)      83040     
_________________________________________________________________
pool2 (MaxPooling2D)         (None, 50, 50, 96)        0         
_________________________________________________________________
conv3_1 (Conv2D)             (None, 50, 50, 128)       110720    
_________________________________________________________________
conv3_2 (Conv2D)             (None, 50, 50, 128)       147584    
_________________________________________________________________
pool3 (MaxPooling2D)         (None, 25, 25, 128)       0         
_________________________________________________________________
conv4_1 (Conv2D)             (None, 25, 25, 256)       295168    
_________________________________________________________________
conv4_2 (Conv2D)             (None, 25, 25, 256)       1048832   
_________________________________________________________________
pool4 (MaxPooling2D)         (None, 12, 12, 256)       0         
_________________________________________________________________
conv5_1 (Conv2D)             (None, 12, 12, 512)       1180160   
_________________________________________________________________
conv5_2 (Conv2D)             (None, 12, 12, 512)       2359808   
_________________________________________________________________
global_average_pooling2d (Gl (None, 512)               0         
=================================================================
Total params: 5,384,832
Trainable params: 5,384,832
Non-trainable params: 0
_________________________________________________________________
None

我从U-Net网络使用以下代码获取编码器：

u_net: Model = get_unet_uncompiled(img_shape = (200, 200, 1))

encoder_input = Model(inputs=u_net.layers[0].input, outputs=u_net.layers[14].output)
encoder_output = GlobalAveragePooling2D()(encoder_input.layers[-1].output)

encoder = Model(encoder_input.input, encoder_output, name='encoder')

print(encoder.summary())

我想将其输出合并为(None, 12, 12, 512)的形状。

我已经尝试过了：

u_net: Model = get_unet_uncompiled(img_shape = (200, 200, 1))

encoder_input = Model(inputs=u_net.layers[0].input, outputs=u_net.layers[14].output)
encoder_output = GlobalAveragePooling2D()(encoder_input.layers[-1].output)

up = UpSampling2D(size=(12, 12))(encoder_output)

encoder = Model(encoder_input.input, up, name='encoder')

但是我有这个错误：

ValueError: Input 0 of layer up_sampling2d is incompatible with the layer: expected ndim=4, found ndim=2. Full shape received: [None, 512]

我不知道自己在做什么。也许UpSampling2D在这里是错误的。

但是，如何将其转换为形状(None, 12, 12, 512)？

Answer 1

Deconvolution/ Upsamping操作形成与正常卷积相同的连通性，但方向相反。对于Upsampling in Keras输入形状是

具有以下形状的4D张量：-如果data_format为“ channels_last” ：（批量大小，行，列，通道）

但是，您给输出的global_average_pooling2d层是2D张量（[None，512]），因此会引发错误。 如果您想在此处使用Upsamping，则应删除Global Average Pooling层，然后进行upsamping。 This是在Keras中从头实现的UNet的示例。

Answer 2

您可以使用Lambda层：

import tensorflow as tf

inputs = tf.random.uniform((100, 512),0, 1, dtype=tf.int32)

layer = tf.keras.layers.Lambda(lambda x: tf.tile(tf.reshape(x, (100, 1, 1, 512)), 
                                                 (1, 12, 12, 1)))

print(layer(inputs).shape)

TensorShape([100, 12, 12, 512])

如何将形状为（None，512）的张量转换为形状为（None，12，12，512）的张量

2 个答案: