时间戳

首页 > 解决方案 > 如何在 Keras 中实现包括 GAN 生成器的自定义损失函数？

python - 如何在 Keras 中实现包括 GAN 生成器的自定义损失函数？

问题描述

我想为基于 Encoder-Generator 训练的真实输入图像使用 PGGAN 生成器找到类似的图像。下面是我的实现：

# load pre-trained generator
sess = tf.InteractiveSession()
with open('network-snapshot-final.pkl', 'rb') as file:
    G, D, Gs = pickle.load(file)

# network parameters
image_size = 1024
input_shape = (image_size, image_size, 1)
batch_size = 8
kernel_size = 3
filters = 16
latent_dim = 512
epochs = 100

# build an encoder
inputs = Input(shape=input_shape, name='encoder_input')
x = inputs
for i in range(10):
    filters *= 2
    x = Conv2D(filters=filters,
               kernel_size=kernel_size,
               activation='relu',
               strides=2,
               padding='same')(x)

# generate latent vector
x = Flatten()(x)
x = Dense(2048, activation='relu')(x)
z_sim = Dense(latent_dim, name='z_sim')(x)

encoder = Model(inputs, z_sim, name='encoder')

# define a custom loss function
def loss_enc(x, z_sim):
    im_g = tf.convert_to_tensor(Gs.run(z_sim.eval(), labels))
    im_g2 = tf.reshape(im_g, [-1, 1024, 1024, 1])
    los = mse(K.flatten(x), K.flatten(im_g2))
    return los

编译模型后，遇到如下错误信息：

encoder.compile(optimizer='rmsprop', loss=loss_enc)

InvalidArgumentError：您必须为占位符张量“encoder_input_19”提供一个值，其 dtype 浮点数和形状 [?,1024,1024,1] [[{{node encoder_input_19}} = Placeholderdtype=DT_FLOAT, shape= [?,1024,1024,1 ], _device="/job:localhost/replica:0/task:0/device:GPU:0"]] [[{{node z_sim_12/BiasAdd/_713}} = _Recvclient_terminated=false, recv_device="/job:localhost /replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_127_z_sim_12/BiasAdd" , tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

为此，我该如何正确实现损失函数？

标签： pythontensorflowkerasloss

解决方案

首先：

def loss_enc(x, z_sim):
   def loss(y_pred, y_true):
     # Things you would do with x, z_sim and store in 'result' (for example)
   return result
return loss

编译模型时：

encoder.compile(optimizer='rmsprop', loss=loss_enc(x, z_sim))

推荐阅读