[英]How to implement a custom loss function including GAN generator in Keras?
I'd like to find a similar image using PGGAN generator for a real input image based on Encoder-Generator training.我想使用 PGGAN 生成器为基于编码器-生成器训练的真实输入图像找到类似的图像。 Below is my implementation:
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
After compiling the model, I encountered error messages as follows:编译模型后,遇到错误信息如下:
encoder.compile(optimizer='rmsprop', loss=loss_enc)
InvalidArgumentError: You must feed a value for placeholder tensor 'encoder_input_19' with dtype float and shape [?,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"]]
InvalidArgumentError:您必须为占位符张量“encoder_input_19”提供一个值,其数据类型为浮点型和形状 [?,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"]]
How can I correctly implement the loss function for this purpose?为此,我如何正确实现损失函数?
Firstly: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
When you compile the model:编译模型时:
encoder.compile(optimizer='rmsprop', loss=loss_enc(x, z_sim))
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.