19장 세상에 없는 얼굴 GAN, 오토인코더¶
3. 적대적 신경망 실행하기¶
실습: GAN 모델 만들기¶
In [2]:
Copied!
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Input, Dense, Reshape, Flatten, Dropout
from tensorflow.keras.layers import BatchNormalization, Activation, LeakyReLU, UpSampling2D, Conv2D
from tensorflow.keras.models import Sequential, Model
import numpy as np
import matplotlib.pyplot as plt
# 예제 파일에서 data 폴더 아래에 이미지가 저장될 gan_images 폴더가 함께 제공됩니다.
# 만약 이미지가 저장될 폴더가 없다면 아래 코드의 주석을 해제해 gan_images 폴더를 만듭니다.
# import os
# if not os.path.exists("./data/gan_images"):
# os.makedirs("./data/gan_images")
# 생성자 모델을 만듭니다.
generator = Sequential()
generator.add(Dense(128*7*7, input_dim=100, activation=LeakyReLU(0.2)))
generator.add(BatchNormalization())
generator.add(Reshape((7, 7, 128)))
generator.add(UpSampling2D())
generator.add(Conv2D(64, kernel_size=5, padding='same'))
generator.add(BatchNormalization())
generator.add(Activation(LeakyReLU(0.2)))
generator.add(UpSampling2D())
generator.add(Conv2D(1, kernel_size=5, padding='same', activation='tanh'))
# 판별자 모델을 만듭니다.
discriminator = Sequential()
discriminator.add(Conv2D(64, kernel_size=5, strides=2, input_shape=(28,28,1), padding="same"))
discriminator.add(Activation(LeakyReLU(0.2)))
discriminator.add(Dropout(0.3))
discriminator.add(Conv2D(128, kernel_size=5, strides=2, padding="same"))
discriminator.add(Activation(LeakyReLU(0.2)))
discriminator.add(Dropout(0.3))
discriminator.add(Flatten())
discriminator.add(Dense(1, activation='sigmoid'))
discriminator.compile(loss='binary_crossentropy', optimizer='adam')
discriminator.trainable = False
# 생성자와 판별자 모델을 연결시키는 gan 모델을 만듭니다.
ginput = Input(shape=(100,))
dis_output = discriminator(generator(ginput))
gan = Model(ginput, dis_output)
gan.compile(loss='binary_crossentropy', optimizer='adam')
gan.summary()
# 신경망을 실행시키는 함수를 만듭니다.
def gan_train(epoch, batch_size, saving_interval):
# MNIST 데이터를 불러옵니다.
(X_train, _), (_, _) = mnist.load_data() # 앞서 불러온 적 있는 MNIST를 다시 이용합니다. 단, 테스트 과정은 필요 없고 이미지만 사용할 것이기 때문에 X_train만 불러왔습니다.
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32')
X_train = (X_train - 127.5) / 127.5 # 픽셀 값은 0에서 255 사이의 값입니다. 이전에 255로 나누어 줄때는 이를 0~1 사이의 값으로 바꾸었던 것인데, 여기서는 127.5를 빼준 뒤 127.5로 나누어 줌으로 인해 -1에서 1사이의 값으로 바뀌게 됩니다.
# X_train.shape, Y_train.shape, X_test.shape, Y_test.shape
true = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for i in range(epoch):
# 실제 데이터를 판별자에 입력하는 부분입니다.
idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs = X_train[idx]
d_loss_real = discriminator.train_on_batch(imgs, true)
# 가상 이미지를 판별자에 입력하는 부분입니다.
noise = np.random.normal(0, 1, (batch_size, 100))
gen_imgs = generator.predict(noise)
d_loss_fake = discriminator.train_on_batch(gen_imgs, fake)
# 판별자와 생성자의 오차를 계산합니다.
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
g_loss = gan.train_on_batch(noise, true)
print('epoch:%d' % i, ' d_loss:%.4f' % d_loss, ' g_loss:%.4f' % g_loss)
# 이 부분은 중간 과정을 이미지로 저장해 주는 부분입니다. 본 장의 주요 내용과 관련이 없어
# 소스 코드만 첨부합니다. 만들어진 이미지들은 gan_images 폴더에 저장됩니다.
if i % saving_interval == 0:
#r, c = 5, 5
noise = np.random.normal(0, 1, (25, 100))
gen_imgs = generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(5, 5)
count = 0
for j in range(5):
for k in range(5):
axs[j, k].imshow(gen_imgs[count, :, :, 0], cmap='gray')
axs[j, k].axis('off')
count += 1
fig.savefig("./data/gan_images/gan_mnist_%d.png" % i)
gan_train(2001, 32, 200) # 2000번 반복되고, 배치 사이즈는 32, 200번마다 결과가 저장되게 하였습니다.
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Input, Dense, Reshape, Flatten, Dropout
from tensorflow.keras.layers import BatchNormalization, Activation, LeakyReLU, UpSampling2D, Conv2D
from tensorflow.keras.models import Sequential, Model
import numpy as np
import matplotlib.pyplot as plt
# 예제 파일에서 data 폴더 아래에 이미지가 저장될 gan_images 폴더가 함께 제공됩니다.
# 만약 이미지가 저장될 폴더가 없다면 아래 코드의 주석을 해제해 gan_images 폴더를 만듭니다.
# import os
# if not os.path.exists("./data/gan_images"):
# os.makedirs("./data/gan_images")
# 생성자 모델을 만듭니다.
generator = Sequential()
generator.add(Dense(128*7*7, input_dim=100, activation=LeakyReLU(0.2)))
generator.add(BatchNormalization())
generator.add(Reshape((7, 7, 128)))
generator.add(UpSampling2D())
generator.add(Conv2D(64, kernel_size=5, padding='same'))
generator.add(BatchNormalization())
generator.add(Activation(LeakyReLU(0.2)))
generator.add(UpSampling2D())
generator.add(Conv2D(1, kernel_size=5, padding='same', activation='tanh'))
# 판별자 모델을 만듭니다.
discriminator = Sequential()
discriminator.add(Conv2D(64, kernel_size=5, strides=2, input_shape=(28,28,1), padding="same"))
discriminator.add(Activation(LeakyReLU(0.2)))
discriminator.add(Dropout(0.3))
discriminator.add(Conv2D(128, kernel_size=5, strides=2, padding="same"))
discriminator.add(Activation(LeakyReLU(0.2)))
discriminator.add(Dropout(0.3))
discriminator.add(Flatten())
discriminator.add(Dense(1, activation='sigmoid'))
discriminator.compile(loss='binary_crossentropy', optimizer='adam')
discriminator.trainable = False
# 생성자와 판별자 모델을 연결시키는 gan 모델을 만듭니다.
ginput = Input(shape=(100,))
dis_output = discriminator(generator(ginput))
gan = Model(ginput, dis_output)
gan.compile(loss='binary_crossentropy', optimizer='adam')
gan.summary()
# 신경망을 실행시키는 함수를 만듭니다.
def gan_train(epoch, batch_size, saving_interval):
# MNIST 데이터를 불러옵니다.
(X_train, _), (_, _) = mnist.load_data() # 앞서 불러온 적 있는 MNIST를 다시 이용합니다. 단, 테스트 과정은 필요 없고 이미지만 사용할 것이기 때문에 X_train만 불러왔습니다.
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32')
X_train = (X_train - 127.5) / 127.5 # 픽셀 값은 0에서 255 사이의 값입니다. 이전에 255로 나누어 줄때는 이를 0~1 사이의 값으로 바꾸었던 것인데, 여기서는 127.5를 빼준 뒤 127.5로 나누어 줌으로 인해 -1에서 1사이의 값으로 바뀌게 됩니다.
# X_train.shape, Y_train.shape, X_test.shape, Y_test.shape
true = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for i in range(epoch):
# 실제 데이터를 판별자에 입력하는 부분입니다.
idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs = X_train[idx]
d_loss_real = discriminator.train_on_batch(imgs, true)
# 가상 이미지를 판별자에 입력하는 부분입니다.
noise = np.random.normal(0, 1, (batch_size, 100))
gen_imgs = generator.predict(noise)
d_loss_fake = discriminator.train_on_batch(gen_imgs, fake)
# 판별자와 생성자의 오차를 계산합니다.
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
g_loss = gan.train_on_batch(noise, true)
print('epoch:%d' % i, ' d_loss:%.4f' % d_loss, ' g_loss:%.4f' % g_loss)
# 이 부분은 중간 과정을 이미지로 저장해 주는 부분입니다. 본 장의 주요 내용과 관련이 없어
# 소스 코드만 첨부합니다. 만들어진 이미지들은 gan_images 폴더에 저장됩니다.
if i % saving_interval == 0:
#r, c = 5, 5
noise = np.random.normal(0, 1, (25, 100))
gen_imgs = generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(5, 5)
count = 0
for j in range(5):
for k in range(5):
axs[j, k].imshow(gen_imgs[count, :, :, 0], cmap='gray')
axs[j, k].axis('off')
count += 1
fig.savefig("./data/gan_images/gan_mnist_%d.png" % i)
gan_train(2001, 32, 200) # 2000번 반복되고, 배치 사이즈는 32, 200번마다 결과가 저장되게 하였습니다.
Model: "model_1" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_2 (InputLayer) [(None, 100)] 0 _________________________________________________________________ sequential_2 (Sequential) (None, 28, 28, 1) 865281 _________________________________________________________________ sequential_3 (Sequential) (None, 1) 212865 ================================================================= Total params: 1,078,146 Trainable params: 852,609 Non-trainable params: 225,537 _________________________________________________________________ epoch:0 d_loss:0.7238 g_loss:0.5319 epoch:1 d_loss:0.5213 g_loss:0.2201 epoch:2 d_loss:0.5245 g_loss:0.1033 epoch:3 d_loss:0.5226 g_loss:0.1019 epoch:4 d_loss:0.4939 g_loss:0.1923 epoch:5 d_loss:0.4677 g_loss:0.3840 epoch:6 d_loss:0.4334 g_loss:0.6663 epoch:7 d_loss:0.4546 g_loss:0.8910 epoch:8 d_loss:0.4369 g_loss:0.9794 epoch:9 d_loss:0.4771 g_loss:0.9490 epoch:10 d_loss:0.7274 g_loss:0.8980 epoch:11 d_loss:0.7928 g_loss:0.7521 epoch:12 d_loss:0.6813 g_loss:0.5383 epoch:13 d_loss:0.6899 g_loss:0.4752 epoch:14 d_loss:0.5241 g_loss:0.5128 epoch:15 d_loss:0.4708 g_loss:0.5832 epoch:16 d_loss:0.5005 g_loss:0.6172 epoch:17 d_loss:0.4690 g_loss:0.5709 epoch:18 d_loss:0.4311 g_loss:0.5919 epoch:19 d_loss:0.4473 g_loss:0.5782 epoch:20 d_loss:0.4592 g_loss:0.6169 epoch:21 d_loss:0.4170 g_loss:0.7523 epoch:22 d_loss:0.4254 g_loss:0.7337 epoch:23 d_loss:0.3708 g_loss:0.8320 epoch:24 d_loss:0.4364 g_loss:0.8373 epoch:25 d_loss:0.4068 g_loss:0.8528 epoch:26 d_loss:0.3658 g_loss:1.0229 epoch:27 d_loss:0.3861 g_loss:1.1883 epoch:28 d_loss:0.3337 g_loss:1.3169 epoch:29 d_loss:0.3352 g_loss:1.5259 epoch:30 d_loss:0.2818 g_loss:1.4910 epoch:31 d_loss:0.3074 g_loss:1.5922 epoch:32 d_loss:0.2164 g_loss:1.5288 epoch:33 d_loss:0.2642 g_loss:1.6789 epoch:34 d_loss:0.4409 g_loss:1.5284 epoch:35 d_loss:0.3314 g_loss:1.4386 epoch:36 d_loss:0.4896 g_loss:1.6659 epoch:37 d_loss:0.2828 g_loss:1.9569 epoch:38 d_loss:0.2551 g_loss:1.8495 epoch:39 d_loss:0.1184 g_loss:1.5115 epoch:40 d_loss:0.1285 g_loss:1.2799 epoch:41 d_loss:0.0905 g_loss:2.0185 epoch:42 d_loss:0.0988 g_loss:1.7263 epoch:43 d_loss:0.2424 g_loss:1.2644 epoch:44 d_loss:0.1105 g_loss:1.5158 epoch:45 d_loss:0.1301 g_loss:2.5900 epoch:46 d_loss:0.3572 g_loss:1.2607 epoch:47 d_loss:0.5631 g_loss:1.3923 epoch:48 d_loss:0.3418 g_loss:2.2626 epoch:49 d_loss:0.7786 g_loss:1.7267 epoch:50 d_loss:0.7344 g_loss:1.7198 epoch:51 d_loss:0.5621 g_loss:1.9998 epoch:52 d_loss:0.5235 g_loss:2.8257 epoch:53 d_loss:0.3995 g_loss:3.5907 epoch:54 d_loss:0.3579 g_loss:4.1705 epoch:55 d_loss:0.3354 g_loss:4.1453 epoch:56 d_loss:0.3304 g_loss:4.3154 epoch:57 d_loss:0.4644 g_loss:3.9084 epoch:58 d_loss:0.3020 g_loss:4.3417 epoch:59 d_loss:0.6173 g_loss:4.1584 epoch:60 d_loss:0.6237 g_loss:3.0282 epoch:61 d_loss:0.5893 g_loss:2.7448 epoch:62 d_loss:0.4209 g_loss:3.0565 epoch:63 d_loss:0.5586 g_loss:2.7083 epoch:64 d_loss:0.7224 g_loss:1.9284 epoch:65 d_loss:0.7055 g_loss:1.5615 epoch:66 d_loss:0.6960 g_loss:1.5033 epoch:67 d_loss:0.4219 g_loss:2.5921 epoch:68 d_loss:0.5122 g_loss:2.8553 epoch:69 d_loss:0.3467 g_loss:3.0689 epoch:70 d_loss:0.3663 g_loss:2.4682 epoch:71 d_loss:0.3678 g_loss:2.9167 epoch:72 d_loss:0.3784 g_loss:4.2239 epoch:73 d_loss:0.4957 g_loss:4.4359 epoch:74 d_loss:0.7101 g_loss:3.7071 epoch:75 d_loss:0.6890 g_loss:3.2894 epoch:76 d_loss:1.1161 g_loss:3.1617 epoch:77 d_loss:1.0422 g_loss:2.3360 epoch:78 d_loss:0.6570 g_loss:2.2917 epoch:79 d_loss:0.8125 g_loss:2.1783 epoch:80 d_loss:0.7752 g_loss:1.5621 epoch:81 d_loss:0.7027 g_loss:1.0666 epoch:82 d_loss:0.5535 g_loss:1.0320 epoch:83 d_loss:0.4716 g_loss:1.3315 epoch:84 d_loss:0.5371 g_loss:1.3644 epoch:85 d_loss:0.4153 g_loss:1.4105 epoch:86 d_loss:0.3791 g_loss:1.2880 epoch:87 d_loss:0.5779 g_loss:1.2143 epoch:88 d_loss:0.6173 g_loss:1.1684 epoch:89 d_loss:0.5416 g_loss:1.3788 epoch:90 d_loss:0.3049 g_loss:1.0736 epoch:91 d_loss:0.4979 g_loss:1.3525 epoch:92 d_loss:0.6275 g_loss:0.9999 epoch:93 d_loss:0.6015 g_loss:0.8695 epoch:94 d_loss:0.3780 g_loss:1.0551 epoch:95 d_loss:0.5470 g_loss:0.8799 epoch:96 d_loss:0.5545 g_loss:1.2309 epoch:97 d_loss:0.5651 g_loss:1.2471 epoch:98 d_loss:0.5540 g_loss:1.2145 epoch:99 d_loss:0.4486 g_loss:1.0622 epoch:100 d_loss:0.7139 g_loss:0.8051 epoch:101 d_loss:0.7235 g_loss:0.7825 epoch:102 d_loss:0.6027 g_loss:0.7954 epoch:103 d_loss:0.4666 g_loss:0.9490 epoch:104 d_loss:0.5393 g_loss:1.1609 epoch:105 d_loss:0.5681 g_loss:1.2926 epoch:106 d_loss:0.6066 g_loss:1.1721 epoch:107 d_loss:0.5634 g_loss:0.9979 epoch:108 d_loss:0.5840 g_loss:0.7713 epoch:109 d_loss:0.5024 g_loss:0.9952 epoch:110 d_loss:0.5234 g_loss:1.0693 epoch:111 d_loss:0.5705 g_loss:1.1779 epoch:112 d_loss:0.5005 g_loss:1.3133 epoch:113 d_loss:0.5310 g_loss:1.5447 epoch:114 d_loss:0.6249 g_loss:1.1589 epoch:115 d_loss:0.5276 g_loss:1.0873 epoch:116 d_loss:0.5236 g_loss:1.2229 epoch:117 d_loss:0.4730 g_loss:1.1398 epoch:118 d_loss:0.4347 g_loss:1.2972 epoch:119 d_loss:0.4625 g_loss:1.4939 epoch:120 d_loss:0.4952 g_loss:1.2859 epoch:121 d_loss:0.4788 g_loss:1.5777 epoch:122 d_loss:0.4851 g_loss:1.3921 epoch:123 d_loss:0.4154 g_loss:1.6607 epoch:124 d_loss:0.6136 g_loss:1.1694 epoch:125 d_loss:0.6184 g_loss:1.0555 epoch:126 d_loss:0.4546 g_loss:1.3080 epoch:127 d_loss:0.4763 g_loss:1.5461 epoch:128 d_loss:0.4648 g_loss:1.6658 epoch:129 d_loss:0.5094 g_loss:1.2648 epoch:130 d_loss:0.4835 g_loss:1.1654 epoch:131 d_loss:0.4364 g_loss:1.5718 epoch:132 d_loss:0.5162 g_loss:1.6179 epoch:133 d_loss:0.4911 g_loss:1.4768 epoch:134 d_loss:0.5528 g_loss:1.4488 epoch:135 d_loss:0.5088 g_loss:1.4083 epoch:136 d_loss:0.5419 g_loss:1.3428 epoch:137 d_loss:0.5701 g_loss:1.4053 epoch:138 d_loss:0.4727 g_loss:1.4022 epoch:139 d_loss:0.5189 g_loss:1.5426 epoch:140 d_loss:0.5487 g_loss:1.5208 epoch:141 d_loss:0.5486 g_loss:1.7270 epoch:142 d_loss:0.4688 g_loss:1.4353 epoch:143 d_loss:0.4548 g_loss:1.6635 epoch:144 d_loss:0.4369 g_loss:1.6255 epoch:145 d_loss:0.3996 g_loss:1.6210 epoch:146 d_loss:0.4900 g_loss:1.5430 epoch:147 d_loss:0.4986 g_loss:1.6948 epoch:148 d_loss:0.4528 g_loss:1.7427 epoch:149 d_loss:0.4789 g_loss:1.7763 epoch:150 d_loss:0.4959 g_loss:1.6453 epoch:151 d_loss:0.4498 g_loss:1.6557 epoch:152 d_loss:0.4271 g_loss:1.3941 epoch:153 d_loss:0.5023 g_loss:1.3294 epoch:154 d_loss:0.4269 g_loss:1.5049 epoch:155 d_loss:0.5563 g_loss:1.4867 epoch:156 d_loss:0.3519 g_loss:1.9441 epoch:157 d_loss:0.5775 g_loss:1.2957 epoch:158 d_loss:0.5695 g_loss:1.2110 epoch:159 d_loss:0.5083 g_loss:1.2414 epoch:160 d_loss:0.6109 g_loss:1.2178 epoch:161 d_loss:0.4724 g_loss:1.3710 epoch:162 d_loss:0.4872 g_loss:1.4114 epoch:163 d_loss:0.6461 g_loss:1.3517 epoch:164 d_loss:0.4818 g_loss:1.0744 epoch:165 d_loss:0.5900 g_loss:1.2044 epoch:166 d_loss:0.5480 g_loss:1.2769 epoch:167 d_loss:0.5198 g_loss:1.3024 epoch:168 d_loss:0.5431 g_loss:1.4263 epoch:169 d_loss:0.4144 g_loss:1.2689 epoch:170 d_loss:0.6978 g_loss:1.2433 epoch:171 d_loss:0.5773 g_loss:1.1627 epoch:172 d_loss:0.5207 g_loss:1.3264 epoch:173 d_loss:0.5423 g_loss:1.4330 epoch:174 d_loss:0.5806 g_loss:1.2217 epoch:175 d_loss:0.4911 g_loss:1.9365 epoch:176 d_loss:0.6138 g_loss:1.8384 epoch:177 d_loss:0.5881 g_loss:1.5433 epoch:178 d_loss:0.5817 g_loss:1.6670 epoch:179 d_loss:0.5169 g_loss:1.6294 epoch:180 d_loss:0.3904 g_loss:1.9606 epoch:181 d_loss:0.3672 g_loss:2.1544 epoch:182 d_loss:0.4502 g_loss:2.3461 epoch:183 d_loss:0.4448 g_loss:2.4092 epoch:184 d_loss:0.4525 g_loss:2.1993 epoch:185 d_loss:0.3859 g_loss:2.0161 epoch:186 d_loss:0.4362 g_loss:1.6228 epoch:187 d_loss:0.4667 g_loss:2.0848 epoch:188 d_loss:0.3837 g_loss:2.6583 epoch:189 d_loss:0.4553 g_loss:2.4417
epoch:190 d_loss:0.4755 g_loss:1.8939 epoch:191 d_loss:0.5863 g_loss:1.7595 epoch:192 d_loss:0.6580 g_loss:1.8571 epoch:193 d_loss:0.3263 g_loss:2.3702 epoch:194 d_loss:0.5184 g_loss:2.0908 epoch:195 d_loss:0.5411 g_loss:2.0358 epoch:196 d_loss:0.5440 g_loss:1.6567 epoch:197 d_loss:0.5204 g_loss:1.8065 epoch:198 d_loss:0.5380 g_loss:2.4020 epoch:199 d_loss:0.6539 g_loss:2.1931 epoch:200 d_loss:0.5229 g_loss:1.6866 epoch:201 d_loss:0.4783 g_loss:1.7460 epoch:202 d_loss:0.6188 g_loss:1.5498 epoch:203 d_loss:0.5924 g_loss:1.3935 epoch:204 d_loss:0.6566 g_loss:1.6698 epoch:205 d_loss:0.6255 g_loss:1.8457 epoch:206 d_loss:0.7002 g_loss:2.2371 epoch:207 d_loss:0.5491 g_loss:2.2091 epoch:208 d_loss:0.6547 g_loss:1.6779 epoch:209 d_loss:0.5097 g_loss:1.8389 epoch:210 d_loss:0.5317 g_loss:1.5865 epoch:211 d_loss:0.6993 g_loss:1.3851 epoch:212 d_loss:0.5264 g_loss:1.3001 epoch:213 d_loss:0.4477 g_loss:1.5817 epoch:214 d_loss:0.4436 g_loss:1.9428 epoch:215 d_loss:0.5283 g_loss:1.8842 epoch:216 d_loss:0.3952 g_loss:1.6859 epoch:217 d_loss:0.5869 g_loss:1.8270 epoch:218 d_loss:0.5421 g_loss:1.4653 epoch:219 d_loss:0.4703 g_loss:1.5900 epoch:220 d_loss:0.4894 g_loss:1.8371 epoch:221 d_loss:0.4854 g_loss:1.9652 epoch:222 d_loss:0.3308 g_loss:2.3949 epoch:223 d_loss:0.4530 g_loss:2.5148 epoch:224 d_loss:0.4517 g_loss:2.1696 epoch:225 d_loss:0.4579 g_loss:1.9608 epoch:226 d_loss:0.4878 g_loss:1.6373 epoch:227 d_loss:0.3712 g_loss:1.5628 epoch:228 d_loss:0.4952 g_loss:1.8775 epoch:229 d_loss:0.5281 g_loss:1.8209 epoch:230 d_loss:0.3235 g_loss:1.9706 epoch:231 d_loss:0.4033 g_loss:2.5809 epoch:232 d_loss:0.6234 g_loss:2.2873 epoch:233 d_loss:0.5521 g_loss:2.0197 epoch:234 d_loss:0.6646 g_loss:1.7059 epoch:235 d_loss:0.5247 g_loss:1.4994 epoch:236 d_loss:0.5348 g_loss:1.4808 epoch:237 d_loss:0.5151 g_loss:1.7020 epoch:238 d_loss:0.4671 g_loss:2.0755 epoch:239 d_loss:0.5800 g_loss:1.6904 epoch:240 d_loss:0.4993 g_loss:2.1935 epoch:241 d_loss:0.5824 g_loss:2.0455 epoch:242 d_loss:0.4325 g_loss:1.9722 epoch:243 d_loss:0.4013 g_loss:1.9890 epoch:244 d_loss:0.5411 g_loss:2.0361 epoch:245 d_loss:0.3939 g_loss:1.9907 epoch:246 d_loss:0.3309 g_loss:2.1235 epoch:247 d_loss:0.3991 g_loss:2.3764 epoch:248 d_loss:0.3243 g_loss:2.7761 epoch:249 d_loss:0.4449 g_loss:2.4104 epoch:250 d_loss:0.3918 g_loss:2.1955 epoch:251 d_loss:0.2863 g_loss:2.2064 epoch:252 d_loss:0.3713 g_loss:2.0908 epoch:253 d_loss:0.3683 g_loss:2.2257 epoch:254 d_loss:0.3022 g_loss:2.6383 epoch:255 d_loss:0.3322 g_loss:2.5920 epoch:256 d_loss:0.2895 g_loss:2.2423 epoch:257 d_loss:0.2238 g_loss:2.7859 epoch:258 d_loss:0.2424 g_loss:2.6703 epoch:259 d_loss:0.3668 g_loss:2.8724 epoch:260 d_loss:0.4524 g_loss:2.3284 epoch:261 d_loss:0.5089 g_loss:2.2247 epoch:262 d_loss:0.3784 g_loss:2.3639 epoch:263 d_loss:0.5729 g_loss:2.6212 epoch:264 d_loss:0.4004 g_loss:2.2309 epoch:265 d_loss:0.4183 g_loss:2.0617 epoch:266 d_loss:0.4620 g_loss:2.2143 epoch:267 d_loss:0.4135 g_loss:2.0758 epoch:268 d_loss:0.6278 g_loss:2.9521 epoch:269 d_loss:0.5985 g_loss:3.8830 epoch:270 d_loss:0.5416 g_loss:3.6628 epoch:271 d_loss:1.0072 g_loss:2.6283 epoch:272 d_loss:0.4385 g_loss:2.6934 epoch:273 d_loss:0.4314 g_loss:3.1929 epoch:274 d_loss:0.3787 g_loss:3.0646 epoch:275 d_loss:0.6312 g_loss:2.9060 epoch:276 d_loss:0.6127 g_loss:2.4264 epoch:277 d_loss:0.6159 g_loss:1.8168 epoch:278 d_loss:0.5345 g_loss:1.6628 epoch:279 d_loss:0.3446 g_loss:2.4334 epoch:280 d_loss:0.6869 g_loss:1.6908 epoch:281 d_loss:0.4296 g_loss:2.5250 epoch:282 d_loss:0.5609 g_loss:2.6885 epoch:283 d_loss:0.6962 g_loss:2.2746 epoch:284 d_loss:0.6073 g_loss:1.7872 epoch:285 d_loss:0.5505 g_loss:1.8145 epoch:286 d_loss:0.4173 g_loss:1.9593 epoch:287 d_loss:0.5868 g_loss:1.4290 epoch:288 d_loss:0.3300 g_loss:1.8337 epoch:289 d_loss:0.4740 g_loss:2.1410 epoch:290 d_loss:0.4204 g_loss:2.1118 epoch:291 d_loss:0.3898 g_loss:2.0246 epoch:292 d_loss:0.4738 g_loss:2.3935 epoch:293 d_loss:0.6355 g_loss:1.5795 epoch:294 d_loss:0.5431 g_loss:1.7604 epoch:295 d_loss:0.4319 g_loss:1.9608 epoch:296 d_loss:0.4781 g_loss:1.7725 epoch:297 d_loss:0.3929 g_loss:2.1947 epoch:298 d_loss:0.4697 g_loss:2.0036 epoch:299 d_loss:0.4318 g_loss:1.8737 epoch:300 d_loss:0.5157 g_loss:2.1700 epoch:301 d_loss:0.4284 g_loss:1.6597 epoch:302 d_loss:0.3954 g_loss:1.7459 epoch:303 d_loss:0.4184 g_loss:1.8350 epoch:304 d_loss:0.3509 g_loss:2.1024 epoch:305 d_loss:0.4392 g_loss:2.1478 epoch:306 d_loss:0.3918 g_loss:2.2264 epoch:307 d_loss:0.4287 g_loss:2.1986 epoch:308 d_loss:0.3880 g_loss:1.9754 epoch:309 d_loss:0.4182 g_loss:1.7470 epoch:310 d_loss:0.4117 g_loss:1.6482 epoch:311 d_loss:0.4434 g_loss:1.9316 epoch:312 d_loss:0.4670 g_loss:1.8455 epoch:313 d_loss:0.3944 g_loss:1.9639 epoch:314 d_loss:0.4409 g_loss:1.7926 epoch:315 d_loss:0.4574 g_loss:1.6657 epoch:316 d_loss:0.4932 g_loss:1.9224 epoch:317 d_loss:0.4156 g_loss:1.8931 epoch:318 d_loss:0.3534 g_loss:2.0243 epoch:319 d_loss:0.3996 g_loss:2.0901 epoch:320 d_loss:0.4564 g_loss:2.0832 epoch:321 d_loss:0.3459 g_loss:2.5125 epoch:322 d_loss:0.3929 g_loss:2.3152 epoch:323 d_loss:0.3738 g_loss:2.1398 epoch:324 d_loss:0.3297 g_loss:2.2491 epoch:325 d_loss:0.3191 g_loss:2.2913 epoch:326 d_loss:0.3477 g_loss:2.8536 epoch:327 d_loss:0.4481 g_loss:2.5997 epoch:328 d_loss:0.3604 g_loss:2.5674 epoch:329 d_loss:0.3201 g_loss:2.2464 epoch:330 d_loss:0.4390 g_loss:2.1189 epoch:331 d_loss:0.4112 g_loss:2.2362 epoch:332 d_loss:0.4965 g_loss:2.3382 epoch:333 d_loss:0.7031 g_loss:1.9669 epoch:334 d_loss:0.6192 g_loss:1.7709 epoch:335 d_loss:0.4212 g_loss:1.8409 epoch:336 d_loss:0.4559 g_loss:1.8894 epoch:337 d_loss:0.4531 g_loss:1.7296 epoch:338 d_loss:0.5549 g_loss:1.7023 epoch:339 d_loss:0.5588 g_loss:1.4646 epoch:340 d_loss:0.4724 g_loss:1.3526 epoch:341 d_loss:0.4856 g_loss:1.6309 epoch:342 d_loss:0.4005 g_loss:1.5827 epoch:343 d_loss:0.3440 g_loss:2.1422 epoch:344 d_loss:0.2937 g_loss:2.1836 epoch:345 d_loss:0.4136 g_loss:2.5599 epoch:346 d_loss:0.2152 g_loss:2.5449 epoch:347 d_loss:0.3182 g_loss:2.2260 epoch:348 d_loss:0.4031 g_loss:1.9769 epoch:349 d_loss:0.2507 g_loss:2.0328 epoch:350 d_loss:0.2683 g_loss:2.1337 epoch:351 d_loss:0.2667 g_loss:2.2238 epoch:352 d_loss:0.3116 g_loss:2.1497 epoch:353 d_loss:0.2850 g_loss:2.5396 epoch:354 d_loss:0.1950 g_loss:2.6751 epoch:355 d_loss:0.2917 g_loss:2.6066 epoch:356 d_loss:0.2514 g_loss:3.1134 epoch:357 d_loss:0.3212 g_loss:2.8279 epoch:358 d_loss:0.4103 g_loss:2.1345 epoch:359 d_loss:0.2443 g_loss:2.5322 epoch:360 d_loss:0.2879 g_loss:2.3982 epoch:361 d_loss:0.1837 g_loss:2.5530 epoch:362 d_loss:0.4159 g_loss:2.3730 epoch:363 d_loss:0.4352 g_loss:2.5262 epoch:364 d_loss:0.2079 g_loss:3.5984 epoch:365 d_loss:0.3321 g_loss:3.7080 epoch:366 d_loss:0.4086 g_loss:2.6160 epoch:367 d_loss:0.3834 g_loss:2.1017 epoch:368 d_loss:0.5426 g_loss:1.9040 epoch:369 d_loss:0.5000 g_loss:2.5589 epoch:370 d_loss:0.5622 g_loss:2.5325 epoch:371 d_loss:0.4096 g_loss:2.5706 epoch:372 d_loss:0.5740 g_loss:2.1961 epoch:373 d_loss:0.4907 g_loss:1.7281 epoch:374 d_loss:0.5181 g_loss:1.7636 epoch:375 d_loss:0.4461 g_loss:1.5463 epoch:376 d_loss:0.4185 g_loss:2.3101 epoch:377 d_loss:0.5528 g_loss:2.2681 epoch:378 d_loss:0.4154 g_loss:2.1598 epoch:379 d_loss:0.4486 g_loss:2.1603 epoch:380 d_loss:0.4991 g_loss:1.8075 epoch:381 d_loss:0.3783 g_loss:1.7749 epoch:382 d_loss:0.3265 g_loss:2.1035 epoch:383 d_loss:0.2877 g_loss:2.4085 epoch:384 d_loss:0.4754 g_loss:2.2142 epoch:385 d_loss:0.5509 g_loss:1.7194 epoch:386 d_loss:0.4485 g_loss:1.9443 epoch:387 d_loss:0.4041 g_loss:2.0850 epoch:388 d_loss:0.3586 g_loss:2.2256 epoch:389 d_loss:0.3590 g_loss:2.0659 epoch:390 d_loss:0.3531 g_loss:2.1561 epoch:391 d_loss:0.3145 g_loss:2.1602 epoch:392 d_loss:0.2379 g_loss:2.2056 epoch:393 d_loss:0.2694 g_loss:2.3366 epoch:394 d_loss:0.3794 g_loss:2.1376
epoch:395 d_loss:0.3041 g_loss:2.5643 epoch:396 d_loss:0.3722 g_loss:2.1225 epoch:397 d_loss:0.2404 g_loss:2.0540 epoch:398 d_loss:0.2253 g_loss:2.3613 epoch:399 d_loss:0.2378 g_loss:2.5881 epoch:400 d_loss:0.1991 g_loss:2.7049 epoch:401 d_loss:0.3111 g_loss:2.2434 epoch:402 d_loss:0.2703 g_loss:1.9917 epoch:403 d_loss:0.2121 g_loss:2.1297 epoch:404 d_loss:0.2713 g_loss:2.1420 epoch:405 d_loss:0.2453 g_loss:2.1746 epoch:406 d_loss:0.2360 g_loss:2.5312 epoch:407 d_loss:0.2538 g_loss:2.8531 epoch:408 d_loss:0.2152 g_loss:2.6131 epoch:409 d_loss:0.1923 g_loss:2.8917 epoch:410 d_loss:0.2122 g_loss:2.6323 epoch:411 d_loss:0.2669 g_loss:2.4929 epoch:412 d_loss:0.2821 g_loss:2.3937 epoch:413 d_loss:0.3037 g_loss:2.1643 epoch:414 d_loss:0.3360 g_loss:2.2630 epoch:415 d_loss:0.2535 g_loss:2.4100 epoch:416 d_loss:0.2547 g_loss:2.7976 epoch:417 d_loss:0.3122 g_loss:2.2651 epoch:418 d_loss:0.3588 g_loss:2.2672 epoch:419 d_loss:0.2003 g_loss:2.1223 epoch:420 d_loss:0.2972 g_loss:2.2343 epoch:421 d_loss:0.2365 g_loss:2.3959 epoch:422 d_loss:0.2529 g_loss:2.7842 epoch:423 d_loss:0.4903 g_loss:2.1944 epoch:424 d_loss:0.3824 g_loss:2.2184 epoch:425 d_loss:0.3462 g_loss:2.2935 epoch:426 d_loss:0.2734 g_loss:2.4180 epoch:427 d_loss:0.3459 g_loss:1.8659 epoch:428 d_loss:0.3004 g_loss:2.2018 epoch:429 d_loss:0.4085 g_loss:2.2210 epoch:430 d_loss:0.3889 g_loss:2.1025 epoch:431 d_loss:0.4367 g_loss:2.0986 epoch:432 d_loss:0.4386 g_loss:2.4101 epoch:433 d_loss:0.6096 g_loss:2.1628 epoch:434 d_loss:0.4491 g_loss:2.0616 epoch:435 d_loss:0.5701 g_loss:1.8241 epoch:436 d_loss:0.4220 g_loss:2.1054 epoch:437 d_loss:0.3506 g_loss:2.1862 epoch:438 d_loss:0.3039 g_loss:2.3663 epoch:439 d_loss:0.3397 g_loss:2.6988 epoch:440 d_loss:0.4448 g_loss:2.3961 epoch:441 d_loss:0.3822 g_loss:1.7556 epoch:442 d_loss:0.3594 g_loss:2.4469 epoch:443 d_loss:0.4648 g_loss:1.8753 epoch:444 d_loss:0.3325 g_loss:2.6876 epoch:445 d_loss:0.4792 g_loss:2.2556 epoch:446 d_loss:0.4157 g_loss:2.2613 epoch:447 d_loss:0.4913 g_loss:1.9880 epoch:448 d_loss:0.2860 g_loss:1.7999 epoch:449 d_loss:0.2949 g_loss:2.1346 epoch:450 d_loss:0.4165 g_loss:2.1922 epoch:451 d_loss:0.3668 g_loss:2.4789 epoch:452 d_loss:0.2721 g_loss:2.2475 epoch:453 d_loss:0.3020 g_loss:2.4721 epoch:454 d_loss:0.2556 g_loss:2.3865 epoch:455 d_loss:0.2154 g_loss:2.3817 epoch:456 d_loss:0.2992 g_loss:2.1046 epoch:457 d_loss:0.2755 g_loss:2.3317 epoch:458 d_loss:0.2924 g_loss:2.5772 epoch:459 d_loss:0.2304 g_loss:2.3271 epoch:460 d_loss:0.1902 g_loss:2.6025 epoch:461 d_loss:0.3143 g_loss:3.0145 epoch:462 d_loss:0.2593 g_loss:3.1742 epoch:463 d_loss:0.2734 g_loss:3.1569 epoch:464 d_loss:0.1511 g_loss:2.8377 epoch:465 d_loss:0.1614 g_loss:3.4045 epoch:466 d_loss:0.1955 g_loss:2.8533 epoch:467 d_loss:0.1806 g_loss:2.9643 epoch:468 d_loss:0.1547 g_loss:2.9232 epoch:469 d_loss:0.2123 g_loss:2.5597 epoch:470 d_loss:0.1306 g_loss:2.6573 epoch:471 d_loss:0.1785 g_loss:2.8241 epoch:472 d_loss:0.1562 g_loss:2.8296 epoch:473 d_loss:0.2224 g_loss:2.5884 epoch:474 d_loss:0.1364 g_loss:3.0324 epoch:475 d_loss:0.2212 g_loss:2.8251 epoch:476 d_loss:0.2556 g_loss:3.1362 epoch:477 d_loss:0.2433 g_loss:2.5431 epoch:478 d_loss:0.1367 g_loss:2.9443 epoch:479 d_loss:0.1481 g_loss:2.6376 epoch:480 d_loss:0.2036 g_loss:2.5774 epoch:481 d_loss:0.2842 g_loss:2.3042 epoch:482 d_loss:0.2560 g_loss:2.3012 epoch:483 d_loss:0.2054 g_loss:3.6647 epoch:484 d_loss:0.1352 g_loss:3.8614 epoch:485 d_loss:0.2477 g_loss:3.5652 epoch:486 d_loss:0.2082 g_loss:2.6968 epoch:487 d_loss:0.2237 g_loss:2.1758 epoch:488 d_loss:0.2241 g_loss:2.4422 epoch:489 d_loss:0.1838 g_loss:2.8395 epoch:490 d_loss:0.1526 g_loss:3.2497 epoch:491 d_loss:0.1945 g_loss:2.6813 epoch:492 d_loss:0.2429 g_loss:2.8310 epoch:493 d_loss:0.2946 g_loss:3.1930 epoch:494 d_loss:0.2496 g_loss:2.6722 epoch:495 d_loss:0.1906 g_loss:2.5774 epoch:496 d_loss:0.2457 g_loss:3.3255 epoch:497 d_loss:0.2171 g_loss:3.3777 epoch:498 d_loss:0.1994 g_loss:3.0608 epoch:499 d_loss:0.2195 g_loss:3.0508 epoch:500 d_loss:0.1112 g_loss:3.5598 epoch:501 d_loss:0.2425 g_loss:2.6227 epoch:502 d_loss:0.2764 g_loss:2.8653 epoch:503 d_loss:0.2849 g_loss:2.3545 epoch:504 d_loss:0.1596 g_loss:2.6260 epoch:505 d_loss:0.1696 g_loss:3.2492 epoch:506 d_loss:0.2124 g_loss:2.8774 epoch:507 d_loss:0.1619 g_loss:2.3791 epoch:508 d_loss:0.1943 g_loss:2.9778 epoch:509 d_loss:0.2355 g_loss:2.4657 epoch:510 d_loss:0.2227 g_loss:2.9652 epoch:511 d_loss:0.1364 g_loss:3.6510 epoch:512 d_loss:0.3449 g_loss:2.4509 epoch:513 d_loss:0.2555 g_loss:2.3095 epoch:514 d_loss:0.3403 g_loss:2.1884 epoch:515 d_loss:0.2549 g_loss:2.7003 epoch:516 d_loss:0.2519 g_loss:3.6486 epoch:517 d_loss:0.2705 g_loss:3.2120 epoch:518 d_loss:0.2775 g_loss:3.1739 epoch:519 d_loss:0.3626 g_loss:2.6975 epoch:520 d_loss:0.2589 g_loss:2.3120 epoch:521 d_loss:0.2301 g_loss:2.7981 epoch:522 d_loss:0.1247 g_loss:3.4918 epoch:523 d_loss:0.1447 g_loss:3.8286 epoch:524 d_loss:0.2209 g_loss:3.5086 epoch:525 d_loss:0.2268 g_loss:2.9137 epoch:526 d_loss:0.1963 g_loss:2.3770 epoch:527 d_loss:0.2074 g_loss:2.7450 epoch:528 d_loss:0.1257 g_loss:3.1478 epoch:529 d_loss:0.1161 g_loss:3.5029 epoch:530 d_loss:0.2560 g_loss:2.7309 epoch:531 d_loss:0.2072 g_loss:2.3318 epoch:532 d_loss:0.2161 g_loss:3.0531 epoch:533 d_loss:0.0824 g_loss:3.8669 epoch:534 d_loss:0.1340 g_loss:3.9390 epoch:535 d_loss:0.1892 g_loss:2.3426 epoch:536 d_loss:0.1856 g_loss:2.3817 epoch:537 d_loss:0.1390 g_loss:3.3419 epoch:538 d_loss:0.1455 g_loss:3.3591 epoch:539 d_loss:0.1543 g_loss:2.9693 epoch:540 d_loss:0.1381 g_loss:3.8321 epoch:541 d_loss:0.1709 g_loss:3.3430 epoch:542 d_loss:0.1304 g_loss:2.8287 epoch:543 d_loss:0.1951 g_loss:2.7096 epoch:544 d_loss:0.2267 g_loss:2.4958 epoch:545 d_loss:0.2523 g_loss:2.4727 epoch:546 d_loss:0.1717 g_loss:3.0786 epoch:547 d_loss:0.1963 g_loss:3.2581 epoch:548 d_loss:0.1993 g_loss:2.9668 epoch:549 d_loss:0.1503 g_loss:2.8748 epoch:550 d_loss:0.1761 g_loss:3.0918 epoch:551 d_loss:0.2461 g_loss:3.4572 epoch:552 d_loss:0.1598 g_loss:3.0489 epoch:553 d_loss:0.1734 g_loss:3.7373 epoch:554 d_loss:0.2480 g_loss:2.4497 epoch:555 d_loss:0.1908 g_loss:2.7203 epoch:556 d_loss:0.1877 g_loss:3.2414 epoch:557 d_loss:0.0978 g_loss:3.9296 epoch:558 d_loss:0.2758 g_loss:3.7313 epoch:559 d_loss:0.1699 g_loss:3.0135 epoch:560 d_loss:0.2354 g_loss:2.8858 epoch:561 d_loss:0.1910 g_loss:3.2168 epoch:562 d_loss:0.2664 g_loss:2.8316 epoch:563 d_loss:0.0918 g_loss:4.1163 epoch:564 d_loss:0.0794 g_loss:3.8262 epoch:565 d_loss:0.1687 g_loss:2.9755 epoch:566 d_loss:0.1476 g_loss:2.3057 epoch:567 d_loss:0.1377 g_loss:2.6718 epoch:568 d_loss:0.1458 g_loss:2.9313 epoch:569 d_loss:0.1125 g_loss:3.2424 epoch:570 d_loss:0.1897 g_loss:2.8969 epoch:571 d_loss:0.1706 g_loss:2.8766 epoch:572 d_loss:0.0849 g_loss:3.6923 epoch:573 d_loss:0.1448 g_loss:3.7100 epoch:574 d_loss:0.1910 g_loss:3.3090 epoch:575 d_loss:0.1575 g_loss:3.3373 epoch:576 d_loss:0.1004 g_loss:3.2510 epoch:577 d_loss:0.0979 g_loss:3.0951 epoch:578 d_loss:0.1396 g_loss:3.6251 epoch:579 d_loss:0.1134 g_loss:4.1262 epoch:580 d_loss:0.1400 g_loss:3.3847 epoch:581 d_loss:0.1955 g_loss:2.4633 epoch:582 d_loss:0.2066 g_loss:3.0308 epoch:583 d_loss:0.1362 g_loss:3.3639 epoch:584 d_loss:0.0880 g_loss:3.5769 epoch:585 d_loss:0.2449 g_loss:2.8647 epoch:586 d_loss:0.1993 g_loss:1.9783 epoch:587 d_loss:0.2714 g_loss:2.4461 epoch:588 d_loss:0.1459 g_loss:3.7101 epoch:589 d_loss:0.4409 g_loss:2.2241 epoch:590 d_loss:0.1829 g_loss:1.9939 epoch:591 d_loss:0.3257 g_loss:2.8104 epoch:592 d_loss:0.2008 g_loss:4.0815 epoch:593 d_loss:0.2653 g_loss:4.2834 epoch:594 d_loss:0.2521 g_loss:2.5580 epoch:595 d_loss:0.2914 g_loss:1.8689 epoch:596 d_loss:0.2753 g_loss:2.3237 epoch:597 d_loss:0.1804 g_loss:2.8007 epoch:598 d_loss:0.1580 g_loss:3.5362 epoch:599 d_loss:0.1858 g_loss:3.2749 epoch:600 d_loss:0.2423 g_loss:3.0069
epoch:601 d_loss:0.2450 g_loss:1.8899 epoch:602 d_loss:0.1092 g_loss:3.1321 epoch:603 d_loss:0.1022 g_loss:2.7092 epoch:604 d_loss:0.1910 g_loss:3.1953 epoch:605 d_loss:0.1093 g_loss:3.9540 epoch:606 d_loss:0.2260 g_loss:3.6573 epoch:607 d_loss:0.2149 g_loss:2.8724 epoch:608 d_loss:0.1623 g_loss:2.3658 epoch:609 d_loss:0.3624 g_loss:2.7089 epoch:610 d_loss:0.1602 g_loss:3.3111 epoch:611 d_loss:0.3035 g_loss:3.1079 epoch:612 d_loss:0.2677 g_loss:2.2577 epoch:613 d_loss:0.3471 g_loss:1.9304 epoch:614 d_loss:0.2865 g_loss:2.2070 epoch:615 d_loss:0.1911 g_loss:3.1183 epoch:616 d_loss:0.1898 g_loss:3.3193 epoch:617 d_loss:0.3425 g_loss:2.4482 epoch:618 d_loss:0.2360 g_loss:1.6738 epoch:619 d_loss:0.3215 g_loss:1.7912 epoch:620 d_loss:0.4157 g_loss:2.3420 epoch:621 d_loss:0.3665 g_loss:2.1640 epoch:622 d_loss:0.2123 g_loss:3.3544 epoch:623 d_loss:0.5264 g_loss:1.9491 epoch:624 d_loss:0.4946 g_loss:2.1125 epoch:625 d_loss:0.6614 g_loss:2.0009 epoch:626 d_loss:0.4614 g_loss:2.4568 epoch:627 d_loss:0.2993 g_loss:2.7000 epoch:628 d_loss:0.4852 g_loss:2.2567 epoch:629 d_loss:0.5600 g_loss:1.7791 epoch:630 d_loss:0.3738 g_loss:1.9042 epoch:631 d_loss:0.3698 g_loss:2.4472 epoch:632 d_loss:0.1983 g_loss:3.0591 epoch:633 d_loss:0.3113 g_loss:2.4404 epoch:634 d_loss:0.7414 g_loss:2.1235 epoch:635 d_loss:0.1703 g_loss:3.8490 epoch:636 d_loss:0.3350 g_loss:3.4859 epoch:637 d_loss:0.2645 g_loss:3.1603 epoch:638 d_loss:0.2564 g_loss:1.9487 epoch:639 d_loss:0.2976 g_loss:2.0621 epoch:640 d_loss:0.4567 g_loss:2.0163 epoch:641 d_loss:1.5982 g_loss:1.3368 epoch:642 d_loss:2.0960 g_loss:1.2371 epoch:643 d_loss:1.0775 g_loss:2.0282 epoch:644 d_loss:0.3722 g_loss:4.8606 epoch:645 d_loss:0.8230 g_loss:6.2481 epoch:646 d_loss:0.9445 g_loss:5.6482 epoch:647 d_loss:0.8927 g_loss:4.1412 epoch:648 d_loss:0.8569 g_loss:1.9774 epoch:649 d_loss:0.7442 g_loss:1.4366 epoch:650 d_loss:0.6527 g_loss:1.4873 epoch:651 d_loss:0.1938 g_loss:3.1778 epoch:652 d_loss:0.3528 g_loss:3.8323 epoch:653 d_loss:0.3801 g_loss:3.4698 epoch:654 d_loss:0.6765 g_loss:2.3081 epoch:655 d_loss:0.3937 g_loss:1.4571 epoch:656 d_loss:0.3239 g_loss:1.3567 epoch:657 d_loss:0.3279 g_loss:1.7112 epoch:658 d_loss:0.1402 g_loss:2.2648 epoch:659 d_loss:0.2062 g_loss:2.9566 epoch:660 d_loss:0.1754 g_loss:2.7750 epoch:661 d_loss:0.1340 g_loss:3.4817 epoch:662 d_loss:0.1517 g_loss:3.0713 epoch:663 d_loss:0.2540 g_loss:2.7071 epoch:664 d_loss:0.2529 g_loss:2.7081 epoch:665 d_loss:0.1421 g_loss:2.8366 epoch:666 d_loss:0.1465 g_loss:2.3383 epoch:667 d_loss:0.2685 g_loss:2.4581 epoch:668 d_loss:0.2967 g_loss:2.8704 epoch:669 d_loss:0.2441 g_loss:2.7856 epoch:670 d_loss:0.4127 g_loss:2.4491 epoch:671 d_loss:0.5313 g_loss:3.6557 epoch:672 d_loss:0.5232 g_loss:2.9219 epoch:673 d_loss:0.6458 g_loss:2.8528 epoch:674 d_loss:0.5721 g_loss:1.9473 epoch:675 d_loss:0.5004 g_loss:1.8096 epoch:676 d_loss:0.4001 g_loss:2.2292 epoch:677 d_loss:0.3647 g_loss:2.3065 epoch:678 d_loss:0.4603 g_loss:2.5712 epoch:679 d_loss:0.4700 g_loss:3.2374 epoch:680 d_loss:0.3950 g_loss:2.7293 epoch:681 d_loss:0.5362 g_loss:1.7290 epoch:682 d_loss:0.3323 g_loss:1.7324 epoch:683 d_loss:0.2928 g_loss:1.9080 epoch:684 d_loss:0.4553 g_loss:2.2184 epoch:685 d_loss:0.2022 g_loss:2.6381 epoch:686 d_loss:0.1991 g_loss:3.4090 epoch:687 d_loss:0.2578 g_loss:2.9352 epoch:688 d_loss:0.2742 g_loss:2.3444 epoch:689 d_loss:0.2573 g_loss:2.3758 epoch:690 d_loss:0.3607 g_loss:2.4027 epoch:691 d_loss:0.4310 g_loss:2.3036 epoch:692 d_loss:0.3428 g_loss:2.0505 epoch:693 d_loss:0.4305 g_loss:2.3186 epoch:694 d_loss:0.4506 g_loss:1.7466 epoch:695 d_loss:0.4885 g_loss:1.9236 epoch:696 d_loss:0.3830 g_loss:1.8852 epoch:697 d_loss:0.4079 g_loss:2.0420 epoch:698 d_loss:0.7060 g_loss:1.7475 epoch:699 d_loss:0.8444 g_loss:1.6632 epoch:700 d_loss:0.5428 g_loss:2.0463 epoch:701 d_loss:0.5330 g_loss:2.2102 epoch:702 d_loss:0.8334 g_loss:2.1019 epoch:703 d_loss:0.4787 g_loss:2.1723 epoch:704 d_loss:0.4949 g_loss:1.6274 epoch:705 d_loss:0.2645 g_loss:2.0028 epoch:706 d_loss:0.3601 g_loss:2.1292 epoch:707 d_loss:0.1853 g_loss:2.5920 epoch:708 d_loss:0.1759 g_loss:2.4883 epoch:709 d_loss:0.2235 g_loss:2.3169 epoch:710 d_loss:0.3314 g_loss:2.0627 epoch:711 d_loss:0.2525 g_loss:2.0897 epoch:712 d_loss:0.3276 g_loss:1.9914 epoch:713 d_loss:0.4898 g_loss:2.3520 epoch:714 d_loss:0.3365 g_loss:2.4257 epoch:715 d_loss:0.3806 g_loss:1.6120 epoch:716 d_loss:0.4710 g_loss:1.2471 epoch:717 d_loss:0.5230 g_loss:1.2230 epoch:718 d_loss:0.6410 g_loss:1.0572 epoch:719 d_loss:0.9903 g_loss:0.9406 epoch:720 d_loss:0.7262 g_loss:1.1020 epoch:721 d_loss:0.7483 g_loss:1.5384 epoch:722 d_loss:0.6432 g_loss:1.7927 epoch:723 d_loss:0.9518 g_loss:1.1742 epoch:724 d_loss:0.6532 g_loss:0.6789 epoch:725 d_loss:0.8192 g_loss:0.6901 epoch:726 d_loss:0.6831 g_loss:0.9857 epoch:727 d_loss:0.8870 g_loss:1.0291 epoch:728 d_loss:0.6229 g_loss:1.4026 epoch:729 d_loss:0.5007 g_loss:1.4598 epoch:730 d_loss:0.6735 g_loss:1.1337 epoch:731 d_loss:0.5281 g_loss:1.0524 epoch:732 d_loss:0.4511 g_loss:1.1936 epoch:733 d_loss:0.4868 g_loss:1.3164 epoch:734 d_loss:0.2497 g_loss:1.7786 epoch:735 d_loss:0.3579 g_loss:2.1353 epoch:736 d_loss:0.3150 g_loss:2.1792 epoch:737 d_loss:0.4777 g_loss:2.2660 epoch:738 d_loss:0.3507 g_loss:2.0973 epoch:739 d_loss:0.4225 g_loss:1.6237 epoch:740 d_loss:0.3916 g_loss:1.2928 epoch:741 d_loss:0.4422 g_loss:1.2289 epoch:742 d_loss:0.4291 g_loss:1.7272 epoch:743 d_loss:0.4957 g_loss:2.0641 epoch:744 d_loss:0.3821 g_loss:1.9801 epoch:745 d_loss:0.3668 g_loss:2.0876 epoch:746 d_loss:0.4770 g_loss:1.7462 epoch:747 d_loss:0.3291 g_loss:1.6883 epoch:748 d_loss:0.3758 g_loss:1.4352 epoch:749 d_loss:0.3563 g_loss:1.5702 epoch:750 d_loss:0.3903 g_loss:1.7124 epoch:751 d_loss:0.2509 g_loss:2.3582 epoch:752 d_loss:0.5997 g_loss:1.6970 epoch:753 d_loss:0.3832 g_loss:1.6067 epoch:754 d_loss:0.4188 g_loss:1.7069 epoch:755 d_loss:0.3731 g_loss:1.6993 epoch:756 d_loss:0.6390 g_loss:1.6434 epoch:757 d_loss:0.5048 g_loss:1.3866 epoch:758 d_loss:0.6247 g_loss:1.3774 epoch:759 d_loss:0.5491 g_loss:1.4309 epoch:760 d_loss:0.6706 g_loss:1.3187 epoch:761 d_loss:0.8181 g_loss:1.1714 epoch:762 d_loss:0.7186 g_loss:1.3696 epoch:763 d_loss:0.5064 g_loss:1.3219 epoch:764 d_loss:0.4677 g_loss:1.8221 epoch:765 d_loss:0.6166 g_loss:1.7861 epoch:766 d_loss:0.3428 g_loss:2.2382 epoch:767 d_loss:0.4003 g_loss:1.9622 epoch:768 d_loss:0.4411 g_loss:1.7929 epoch:769 d_loss:0.3148 g_loss:1.6937 epoch:770 d_loss:0.5299 g_loss:1.3924 epoch:771 d_loss:0.6170 g_loss:1.3419 epoch:772 d_loss:0.5501 g_loss:1.2063 epoch:773 d_loss:0.6396 g_loss:1.5668 epoch:774 d_loss:0.6618 g_loss:1.6994 epoch:775 d_loss:0.7108 g_loss:1.7145 epoch:776 d_loss:1.0121 g_loss:1.4047 epoch:777 d_loss:0.5592 g_loss:1.1383 epoch:778 d_loss:0.5784 g_loss:1.1838 epoch:779 d_loss:0.7028 g_loss:1.1144 epoch:780 d_loss:0.5887 g_loss:1.5339 epoch:781 d_loss:0.4857 g_loss:1.6281 epoch:782 d_loss:0.6252 g_loss:1.7293 epoch:783 d_loss:0.6922 g_loss:1.7365 epoch:784 d_loss:0.7041 g_loss:1.6951 epoch:785 d_loss:0.8234 g_loss:1.4720 epoch:786 d_loss:0.5670 g_loss:1.4387 epoch:787 d_loss:0.9369 g_loss:1.3995 epoch:788 d_loss:0.8965 g_loss:1.2355 epoch:789 d_loss:0.6333 g_loss:1.5119 epoch:790 d_loss:0.4158 g_loss:1.9922 epoch:791 d_loss:0.5209 g_loss:2.1219 epoch:792 d_loss:0.3373 g_loss:2.6689 epoch:793 d_loss:0.4365 g_loss:2.9772 epoch:794 d_loss:0.4336 g_loss:3.1374 epoch:795 d_loss:0.2327 g_loss:3.6933 epoch:796 d_loss:0.2858 g_loss:3.2481 epoch:797 d_loss:0.2528 g_loss:3.5207 epoch:798 d_loss:0.2414 g_loss:3.5727 epoch:799 d_loss:0.2185 g_loss:3.0674 epoch:800 d_loss:0.2320 g_loss:3.5969 epoch:801 d_loss:0.1994 g_loss:3.7841 epoch:802 d_loss:0.2323 g_loss:3.7433 epoch:803 d_loss:0.2530 g_loss:2.8669 epoch:804 d_loss:0.2894 g_loss:2.7780 epoch:805 d_loss:0.3104 g_loss:2.6822 epoch:806 d_loss:0.3366 g_loss:1.9857 epoch:807 d_loss:0.4990 g_loss:1.8808 epoch:808 d_loss:0.2922 g_loss:1.9336
epoch:809 d_loss:0.4226 g_loss:2.1354 epoch:810 d_loss:0.5206 g_loss:2.4379 epoch:811 d_loss:0.4834 g_loss:2.2545 epoch:812 d_loss:0.5826 g_loss:1.8927 epoch:813 d_loss:0.7925 g_loss:1.2489 epoch:814 d_loss:0.6779 g_loss:1.1929 epoch:815 d_loss:0.5816 g_loss:1.4125 epoch:816 d_loss:0.6281 g_loss:1.7564 epoch:817 d_loss:0.6710 g_loss:1.7552 epoch:818 d_loss:0.7221 g_loss:1.6691 epoch:819 d_loss:0.6176 g_loss:1.8068 epoch:820 d_loss:0.5497 g_loss:1.7236 epoch:821 d_loss:0.5003 g_loss:1.6883 epoch:822 d_loss:0.4240 g_loss:2.0882 epoch:823 d_loss:0.2852 g_loss:2.0985 epoch:824 d_loss:0.3378 g_loss:2.4807 epoch:825 d_loss:0.2389 g_loss:2.5155 epoch:826 d_loss:0.2029 g_loss:2.4997 epoch:827 d_loss:0.1642 g_loss:2.3629 epoch:828 d_loss:0.2565 g_loss:2.9331 epoch:829 d_loss:0.1568 g_loss:2.4701 epoch:830 d_loss:0.1755 g_loss:2.5536 epoch:831 d_loss:0.1985 g_loss:2.2756 epoch:832 d_loss:0.1947 g_loss:2.6668 epoch:833 d_loss:0.1473 g_loss:3.0148 epoch:834 d_loss:0.2154 g_loss:2.8087 epoch:835 d_loss:0.2495 g_loss:3.1325 epoch:836 d_loss:0.2371 g_loss:2.7208 epoch:837 d_loss:0.1994 g_loss:2.7600 epoch:838 d_loss:0.2799 g_loss:2.4383 epoch:839 d_loss:0.2938 g_loss:2.3909 epoch:840 d_loss:0.2729 g_loss:2.3543 epoch:841 d_loss:0.3579 g_loss:2.5044 epoch:842 d_loss:0.2772 g_loss:2.4016 epoch:843 d_loss:0.4057 g_loss:2.4222 epoch:844 d_loss:0.3229 g_loss:2.4588 epoch:845 d_loss:0.3580 g_loss:2.1193 epoch:846 d_loss:0.4569 g_loss:2.0426 epoch:847 d_loss:0.2738 g_loss:2.4689 epoch:848 d_loss:0.3010 g_loss:2.3066 epoch:849 d_loss:0.4646 g_loss:1.8957 epoch:850 d_loss:0.3811 g_loss:1.8738 epoch:851 d_loss:0.3728 g_loss:1.6222 epoch:852 d_loss:0.4793 g_loss:1.4637 epoch:853 d_loss:0.4396 g_loss:1.7835 epoch:854 d_loss:0.4033 g_loss:2.0936 epoch:855 d_loss:0.5875 g_loss:1.9612 epoch:856 d_loss:0.4475 g_loss:2.3491 epoch:857 d_loss:0.4717 g_loss:1.9297 epoch:858 d_loss:0.5059 g_loss:1.6191 epoch:859 d_loss:0.4798 g_loss:1.4069 epoch:860 d_loss:0.4598 g_loss:1.6106 epoch:861 d_loss:0.3779 g_loss:2.1442 epoch:862 d_loss:0.5319 g_loss:2.1117 epoch:863 d_loss:0.4101 g_loss:1.6910 epoch:864 d_loss:0.4116 g_loss:2.1582 epoch:865 d_loss:0.5594 g_loss:2.5344 epoch:866 d_loss:0.4590 g_loss:2.2058 epoch:867 d_loss:0.7257 g_loss:1.8845 epoch:868 d_loss:0.4737 g_loss:1.8834 epoch:869 d_loss:0.4497 g_loss:1.4471 epoch:870 d_loss:0.3884 g_loss:1.7526 epoch:871 d_loss:0.5337 g_loss:1.6304 epoch:872 d_loss:0.4465 g_loss:1.7298 epoch:873 d_loss:0.4386 g_loss:2.0406 epoch:874 d_loss:0.5311 g_loss:1.7606 epoch:875 d_loss:0.6255 g_loss:1.8602 epoch:876 d_loss:0.5058 g_loss:1.9182 epoch:877 d_loss:0.5759 g_loss:1.6493 epoch:878 d_loss:0.3344 g_loss:1.8608 epoch:879 d_loss:0.3747 g_loss:1.9786 epoch:880 d_loss:0.5607 g_loss:1.8130 epoch:881 d_loss:0.4578 g_loss:1.6704 epoch:882 d_loss:0.4537 g_loss:1.5001 epoch:883 d_loss:0.5451 g_loss:1.4527 epoch:884 d_loss:0.5684 g_loss:1.4435 epoch:885 d_loss:0.4317 g_loss:1.7713 epoch:886 d_loss:0.5074 g_loss:1.7625 epoch:887 d_loss:0.5143 g_loss:2.0578 epoch:888 d_loss:0.3832 g_loss:1.8969 epoch:889 d_loss:0.4544 g_loss:1.6999 epoch:890 d_loss:0.3918 g_loss:1.9535 epoch:891 d_loss:0.4979 g_loss:1.8612 epoch:892 d_loss:0.4717 g_loss:1.4765 epoch:893 d_loss:0.4301 g_loss:1.5848 epoch:894 d_loss:0.3706 g_loss:1.8818 epoch:895 d_loss:0.2439 g_loss:1.9928 epoch:896 d_loss:0.4070 g_loss:1.9860 epoch:897 d_loss:0.2836 g_loss:2.1361 epoch:898 d_loss:0.2622 g_loss:2.5905 epoch:899 d_loss:0.3219 g_loss:2.3001 epoch:900 d_loss:0.3202 g_loss:2.1935 epoch:901 d_loss:0.2299 g_loss:2.2972 epoch:902 d_loss:0.1829 g_loss:2.2679 epoch:903 d_loss:0.2836 g_loss:2.2819 epoch:904 d_loss:0.2834 g_loss:2.1876 epoch:905 d_loss:0.2735 g_loss:2.3619 epoch:906 d_loss:0.1970 g_loss:2.4353 epoch:907 d_loss:0.3461 g_loss:2.3028 epoch:908 d_loss:0.2906 g_loss:2.7593 epoch:909 d_loss:0.2922 g_loss:2.8627 epoch:910 d_loss:0.3398 g_loss:2.6749 epoch:911 d_loss:0.3835 g_loss:1.9207 epoch:912 d_loss:0.2220 g_loss:2.6610 epoch:913 d_loss:0.2353 g_loss:2.8279 epoch:914 d_loss:0.2353 g_loss:2.5831 epoch:915 d_loss:0.4552 g_loss:2.5484 epoch:916 d_loss:0.3174 g_loss:2.5450 epoch:917 d_loss:0.3337 g_loss:2.6426 epoch:918 d_loss:0.3099 g_loss:2.8840 epoch:919 d_loss:0.4497 g_loss:2.3157 epoch:920 d_loss:0.3232 g_loss:1.5822 epoch:921 d_loss:0.3153 g_loss:1.9065 epoch:922 d_loss:0.3110 g_loss:1.9154 epoch:923 d_loss:0.4028 g_loss:2.4824 epoch:924 d_loss:0.3114 g_loss:2.3454 epoch:925 d_loss:0.3004 g_loss:2.3952 epoch:926 d_loss:0.3191 g_loss:2.0474 epoch:927 d_loss:0.4579 g_loss:1.7556 epoch:928 d_loss:0.3625 g_loss:2.2360 epoch:929 d_loss:0.4876 g_loss:2.1892 epoch:930 d_loss:0.5021 g_loss:2.1128 epoch:931 d_loss:0.5158 g_loss:1.7947 epoch:932 d_loss:0.2815 g_loss:2.0605 epoch:933 d_loss:0.2685 g_loss:2.2472 epoch:934 d_loss:0.3846 g_loss:2.1505 epoch:935 d_loss:0.2481 g_loss:2.1772 epoch:936 d_loss:0.3827 g_loss:2.5183 epoch:937 d_loss:0.2990 g_loss:2.4687 epoch:938 d_loss:0.3425 g_loss:2.2880 epoch:939 d_loss:0.3686 g_loss:2.3862 epoch:940 d_loss:0.3766 g_loss:2.2088 epoch:941 d_loss:0.4881 g_loss:2.0448 epoch:942 d_loss:0.3080 g_loss:1.9373 epoch:943 d_loss:0.3463 g_loss:1.9397 epoch:944 d_loss:0.4698 g_loss:2.0679 epoch:945 d_loss:0.2995 g_loss:2.6141 epoch:946 d_loss:0.3273 g_loss:2.5473 epoch:947 d_loss:0.4762 g_loss:2.3139 epoch:948 d_loss:0.3996 g_loss:2.1311 epoch:949 d_loss:0.4969 g_loss:1.7610 epoch:950 d_loss:0.4070 g_loss:2.0679 epoch:951 d_loss:0.3783 g_loss:2.2526 epoch:952 d_loss:0.4607 g_loss:1.8977 epoch:953 d_loss:0.4096 g_loss:2.2517 epoch:954 d_loss:0.4078 g_loss:2.7241 epoch:955 d_loss:0.5272 g_loss:2.2163 epoch:956 d_loss:0.6185 g_loss:1.9074 epoch:957 d_loss:0.3380 g_loss:1.6198 epoch:958 d_loss:0.5686 g_loss:1.4587 epoch:959 d_loss:0.4181 g_loss:1.6329 epoch:960 d_loss:0.4936 g_loss:1.9673 epoch:961 d_loss:0.2921 g_loss:1.9945 epoch:962 d_loss:0.3183 g_loss:2.0484 epoch:963 d_loss:0.2497 g_loss:2.3979 epoch:964 d_loss:0.3897 g_loss:2.0434 epoch:965 d_loss:0.4042 g_loss:2.4057 epoch:966 d_loss:0.3614 g_loss:2.0852 epoch:967 d_loss:0.4304 g_loss:1.7460 epoch:968 d_loss:0.3486 g_loss:2.1834 epoch:969 d_loss:0.3244 g_loss:2.2478 epoch:970 d_loss:0.2564 g_loss:2.3703 epoch:971 d_loss:0.2823 g_loss:2.3682 epoch:972 d_loss:0.4070 g_loss:2.2533 epoch:973 d_loss:0.4307 g_loss:2.5244 epoch:974 d_loss:0.2143 g_loss:2.5349 epoch:975 d_loss:0.3057 g_loss:2.6686 epoch:976 d_loss:0.2769 g_loss:2.5592 epoch:977 d_loss:0.2894 g_loss:1.9915 epoch:978 d_loss:0.3987 g_loss:1.9295 epoch:979 d_loss:0.2053 g_loss:2.4244 epoch:980 d_loss:0.1931 g_loss:2.5022 epoch:981 d_loss:0.2538 g_loss:3.0988 epoch:982 d_loss:0.3407 g_loss:2.4743 epoch:983 d_loss:0.1763 g_loss:2.7463 epoch:984 d_loss:0.2521 g_loss:2.6693 epoch:985 d_loss:0.3538 g_loss:2.1527 epoch:986 d_loss:0.2926 g_loss:2.3468 epoch:987 d_loss:0.4065 g_loss:2.3612 epoch:988 d_loss:0.3292 g_loss:2.9806 epoch:989 d_loss:0.2670 g_loss:3.0118 epoch:990 d_loss:0.4376 g_loss:2.8118 epoch:991 d_loss:0.3514 g_loss:3.0801 epoch:992 d_loss:0.4146 g_loss:2.1040 epoch:993 d_loss:0.4156 g_loss:1.5243 epoch:994 d_loss:0.3997 g_loss:1.7930 epoch:995 d_loss:0.3484 g_loss:1.8473 epoch:996 d_loss:0.4480 g_loss:2.2277 epoch:997 d_loss:0.2813 g_loss:2.6553 epoch:998 d_loss:0.4462 g_loss:2.6685 epoch:999 d_loss:0.3683 g_loss:2.2337 epoch:1000 d_loss:0.3741 g_loss:1.9827 epoch:1001 d_loss:0.4937 g_loss:1.5701 epoch:1002 d_loss:0.4399 g_loss:1.8992 epoch:1003 d_loss:0.3227 g_loss:2.0247 epoch:1004 d_loss:0.4462 g_loss:1.9310 epoch:1005 d_loss:0.3080 g_loss:2.5803 epoch:1006 d_loss:0.3912 g_loss:2.2145 epoch:1007 d_loss:0.4611 g_loss:2.3394 epoch:1008 d_loss:0.5185 g_loss:2.0168 epoch:1009 d_loss:0.3749 g_loss:1.6893 epoch:1010 d_loss:0.4745 g_loss:1.6927 epoch:1011 d_loss:0.3489 g_loss:2.2789 epoch:1012 d_loss:0.2352 g_loss:2.6603 epoch:1013 d_loss:0.3341 g_loss:2.0114 epoch:1014 d_loss:0.3786 g_loss:2.1545 epoch:1015 d_loss:0.2575 g_loss:2.0238 epoch:1016 d_loss:0.3229 g_loss:1.7055
epoch:1017 d_loss:0.3217 g_loss:1.6948 epoch:1018 d_loss:0.2786 g_loss:2.5536 epoch:1019 d_loss:0.4589 g_loss:2.3590 epoch:1020 d_loss:0.3450 g_loss:2.4763 epoch:1021 d_loss:0.3475 g_loss:2.5556 epoch:1022 d_loss:0.4816 g_loss:1.9917 epoch:1023 d_loss:0.3118 g_loss:1.9476 epoch:1024 d_loss:0.3692 g_loss:1.9715 epoch:1025 d_loss:0.3245 g_loss:2.0057 epoch:1026 d_loss:0.3583 g_loss:2.0152 epoch:1027 d_loss:0.3837 g_loss:2.3934 epoch:1028 d_loss:0.4675 g_loss:2.5253 epoch:1029 d_loss:0.2866 g_loss:2.4826 epoch:1030 d_loss:0.4257 g_loss:1.7747 epoch:1031 d_loss:0.3458 g_loss:2.3538 epoch:1032 d_loss:0.6136 g_loss:1.6671 epoch:1033 d_loss:0.5520 g_loss:2.0421 epoch:1034 d_loss:0.3093 g_loss:2.2760 epoch:1035 d_loss:0.5574 g_loss:2.7880 epoch:1036 d_loss:0.3964 g_loss:2.3058 epoch:1037 d_loss:0.6023 g_loss:1.7663 epoch:1038 d_loss:0.7906 g_loss:1.2262 epoch:1039 d_loss:0.5660 g_loss:1.6487 epoch:1040 d_loss:0.6175 g_loss:1.5713 epoch:1041 d_loss:0.4714 g_loss:1.8877 epoch:1042 d_loss:0.5050 g_loss:1.8871 epoch:1043 d_loss:0.4236 g_loss:1.9011 epoch:1044 d_loss:0.3533 g_loss:2.2733 epoch:1045 d_loss:0.3965 g_loss:2.1256 epoch:1046 d_loss:0.4174 g_loss:2.0301 epoch:1047 d_loss:0.4248 g_loss:2.0042 epoch:1048 d_loss:0.4967 g_loss:1.7894 epoch:1049 d_loss:0.3612 g_loss:1.9851 epoch:1050 d_loss:0.3383 g_loss:2.1129 epoch:1051 d_loss:0.3758 g_loss:1.9853 epoch:1052 d_loss:0.3285 g_loss:1.8015 epoch:1053 d_loss:0.2307 g_loss:2.3350 epoch:1054 d_loss:0.3369 g_loss:2.4637 epoch:1055 d_loss:0.2877 g_loss:2.4845 epoch:1056 d_loss:0.2656 g_loss:2.7895 epoch:1057 d_loss:0.2503 g_loss:2.5625 epoch:1058 d_loss:0.3399 g_loss:2.3157 epoch:1059 d_loss:0.2829 g_loss:2.5478 epoch:1060 d_loss:0.2274 g_loss:2.5865 epoch:1061 d_loss:0.2820 g_loss:2.7989 epoch:1062 d_loss:0.2127 g_loss:3.2704 epoch:1063 d_loss:0.2607 g_loss:2.6063 epoch:1064 d_loss:0.2117 g_loss:2.6158 epoch:1065 d_loss:0.3581 g_loss:2.4999 epoch:1066 d_loss:0.2510 g_loss:2.7603 epoch:1067 d_loss:0.4292 g_loss:2.3626 epoch:1068 d_loss:0.4070 g_loss:2.1940 epoch:1069 d_loss:0.4485 g_loss:2.4287 epoch:1070 d_loss:0.2416 g_loss:2.0586 epoch:1071 d_loss:0.2931 g_loss:2.0902 epoch:1072 d_loss:0.3207 g_loss:2.1702 epoch:1073 d_loss:0.2719 g_loss:2.6065 epoch:1074 d_loss:0.3380 g_loss:2.1512 epoch:1075 d_loss:0.2523 g_loss:2.1752 epoch:1076 d_loss:0.4082 g_loss:1.8758 epoch:1077 d_loss:0.4203 g_loss:1.8007 epoch:1078 d_loss:0.4048 g_loss:2.4256 epoch:1079 d_loss:0.3860 g_loss:2.4864 epoch:1080 d_loss:0.7999 g_loss:1.6100 epoch:1081 d_loss:0.5847 g_loss:1.7160 epoch:1082 d_loss:0.5125 g_loss:1.8218 epoch:1083 d_loss:0.5248 g_loss:1.9219 epoch:1084 d_loss:0.4662 g_loss:1.9048 epoch:1085 d_loss:0.6190 g_loss:1.5933 epoch:1086 d_loss:0.4630 g_loss:1.7383 epoch:1087 d_loss:0.6410 g_loss:1.7000 epoch:1088 d_loss:0.6572 g_loss:1.6529 epoch:1089 d_loss:0.3835 g_loss:2.1602 epoch:1090 d_loss:0.5671 g_loss:1.6587 epoch:1091 d_loss:0.3885 g_loss:1.9038 epoch:1092 d_loss:0.4370 g_loss:1.7631 epoch:1093 d_loss:0.6732 g_loss:1.3777 epoch:1094 d_loss:0.4785 g_loss:1.4060 epoch:1095 d_loss:0.3048 g_loss:1.7466 epoch:1096 d_loss:0.4492 g_loss:1.7601 epoch:1097 d_loss:0.3518 g_loss:2.4893 epoch:1098 d_loss:0.5223 g_loss:2.2847 epoch:1099 d_loss:0.3972 g_loss:2.1094 epoch:1100 d_loss:0.5004 g_loss:2.1147 epoch:1101 d_loss:0.3678 g_loss:1.6047 epoch:1102 d_loss:0.3785 g_loss:1.5891 epoch:1103 d_loss:0.3998 g_loss:2.5280 epoch:1104 d_loss:0.2862 g_loss:2.4743 epoch:1105 d_loss:0.4443 g_loss:2.3670 epoch:1106 d_loss:0.4216 g_loss:2.2465 epoch:1107 d_loss:0.3898 g_loss:1.8265 epoch:1108 d_loss:0.6702 g_loss:1.5486 epoch:1109 d_loss:0.2748 g_loss:2.3758 epoch:1110 d_loss:0.2831 g_loss:2.0101 epoch:1111 d_loss:0.2743 g_loss:2.0674 epoch:1112 d_loss:0.3310 g_loss:2.0105 epoch:1113 d_loss:0.4345 g_loss:2.2085 epoch:1114 d_loss:0.4322 g_loss:2.4885 epoch:1115 d_loss:0.3898 g_loss:2.7174 epoch:1116 d_loss:0.3919 g_loss:2.6764 epoch:1117 d_loss:0.2060 g_loss:2.9771 epoch:1118 d_loss:0.3207 g_loss:3.1330 epoch:1119 d_loss:0.2716 g_loss:2.6103 epoch:1120 d_loss:0.3811 g_loss:2.5298 epoch:1121 d_loss:0.4779 g_loss:1.7221 epoch:1122 d_loss:0.3304 g_loss:1.8740 epoch:1123 d_loss:0.3790 g_loss:1.8268 epoch:1124 d_loss:0.4946 g_loss:2.0163 epoch:1125 d_loss:0.3846 g_loss:2.2419 epoch:1126 d_loss:0.3676 g_loss:2.5056 epoch:1127 d_loss:0.3329 g_loss:2.2837 epoch:1128 d_loss:0.3297 g_loss:2.1088 epoch:1129 d_loss:0.3200 g_loss:1.9530 epoch:1130 d_loss:0.2735 g_loss:2.1074 epoch:1131 d_loss:0.3553 g_loss:2.1481 epoch:1132 d_loss:0.2632 g_loss:2.2343 epoch:1133 d_loss:0.3424 g_loss:1.9047 epoch:1134 d_loss:0.3192 g_loss:1.9443 epoch:1135 d_loss:0.1819 g_loss:2.4884 epoch:1136 d_loss:0.3568 g_loss:2.4950 epoch:1137 d_loss:0.3093 g_loss:2.3902 epoch:1138 d_loss:0.1825 g_loss:2.8450 epoch:1139 d_loss:0.2392 g_loss:2.4525 epoch:1140 d_loss:0.4568 g_loss:2.0318 epoch:1141 d_loss:0.3781 g_loss:1.7518 epoch:1142 d_loss:0.3621 g_loss:2.1548 epoch:1143 d_loss:0.2026 g_loss:2.7350 epoch:1144 d_loss:0.3211 g_loss:2.5541 epoch:1145 d_loss:0.3094 g_loss:2.6776 epoch:1146 d_loss:0.5268 g_loss:2.1261 epoch:1147 d_loss:0.3554 g_loss:1.9750 epoch:1148 d_loss:0.3591 g_loss:2.3762 epoch:1149 d_loss:0.3368 g_loss:2.4231 epoch:1150 d_loss:0.3391 g_loss:2.4048 epoch:1151 d_loss:0.3789 g_loss:2.8403 epoch:1152 d_loss:0.5429 g_loss:2.5089 epoch:1153 d_loss:0.3804 g_loss:2.4557 epoch:1154 d_loss:0.4577 g_loss:2.5668 epoch:1155 d_loss:0.3979 g_loss:1.9888 epoch:1156 d_loss:0.3722 g_loss:2.5662 epoch:1157 d_loss:0.2864 g_loss:2.3589 epoch:1158 d_loss:0.3981 g_loss:2.4637 epoch:1159 d_loss:0.3511 g_loss:3.0451 epoch:1160 d_loss:0.3888 g_loss:2.6523 epoch:1161 d_loss:0.3410 g_loss:2.5231 epoch:1162 d_loss:0.3706 g_loss:2.2913 epoch:1163 d_loss:0.3749 g_loss:2.4738 epoch:1164 d_loss:0.5131 g_loss:1.8605 epoch:1165 d_loss:0.6434 g_loss:2.1646 epoch:1166 d_loss:0.3108 g_loss:2.3278 epoch:1167 d_loss:0.4283 g_loss:2.5780 epoch:1168 d_loss:0.7307 g_loss:2.5353 epoch:1169 d_loss:0.4861 g_loss:2.0263 epoch:1170 d_loss:0.6015 g_loss:1.5174 epoch:1171 d_loss:0.3847 g_loss:1.9865 epoch:1172 d_loss:0.2315 g_loss:2.9206 epoch:1173 d_loss:0.4635 g_loss:2.5324 epoch:1174 d_loss:0.3246 g_loss:2.2400 epoch:1175 d_loss:0.3170 g_loss:1.9758 epoch:1176 d_loss:0.3286 g_loss:2.2038 epoch:1177 d_loss:0.4521 g_loss:1.9567 epoch:1178 d_loss:0.4042 g_loss:2.4212 epoch:1179 d_loss:0.3770 g_loss:2.5849 epoch:1180 d_loss:0.4825 g_loss:2.5805 epoch:1181 d_loss:0.4425 g_loss:2.4526 epoch:1182 d_loss:0.3385 g_loss:2.6915 epoch:1183 d_loss:0.2504 g_loss:2.0077 epoch:1184 d_loss:0.4366 g_loss:2.2552 epoch:1185 d_loss:0.4399 g_loss:1.9906 epoch:1186 d_loss:0.3447 g_loss:2.1364 epoch:1187 d_loss:0.3383 g_loss:2.4086 epoch:1188 d_loss:0.4568 g_loss:2.7899 epoch:1189 d_loss:0.4937 g_loss:2.3350 epoch:1190 d_loss:0.3236 g_loss:2.4550 epoch:1191 d_loss:0.3841 g_loss:2.3123 epoch:1192 d_loss:0.4059 g_loss:2.4432 epoch:1193 d_loss:0.3540 g_loss:2.7756 epoch:1194 d_loss:0.4620 g_loss:2.5128 epoch:1195 d_loss:0.4334 g_loss:2.2109 epoch:1196 d_loss:0.3646 g_loss:2.2979 epoch:1197 d_loss:0.2718 g_loss:2.9524 epoch:1198 d_loss:0.2551 g_loss:3.2339 epoch:1199 d_loss:0.2660 g_loss:2.7090 epoch:1200 d_loss:0.2905 g_loss:2.9921 epoch:1201 d_loss:0.3286 g_loss:2.6585 epoch:1202 d_loss:0.4072 g_loss:2.2256 epoch:1203 d_loss:0.3664 g_loss:2.3715 epoch:1204 d_loss:0.3806 g_loss:2.1102 epoch:1205 d_loss:0.2805 g_loss:3.1036 epoch:1206 d_loss:0.3543 g_loss:3.2053 epoch:1207 d_loss:0.4010 g_loss:2.7925 epoch:1208 d_loss:0.4133 g_loss:2.2291 epoch:1209 d_loss:0.3422 g_loss:1.8350 epoch:1210 d_loss:0.3791 g_loss:2.1747 epoch:1211 d_loss:0.3998 g_loss:2.1368 epoch:1212 d_loss:0.3656 g_loss:2.6588 epoch:1213 d_loss:0.3093 g_loss:2.4901 epoch:1214 d_loss:0.5632 g_loss:2.1280 epoch:1215 d_loss:0.4341 g_loss:2.1132 epoch:1216 d_loss:0.3839 g_loss:2.1252
epoch:1217 d_loss:0.4443 g_loss:2.1359 epoch:1218 d_loss:0.4319 g_loss:1.7964 epoch:1219 d_loss:0.5506 g_loss:1.2644 epoch:1220 d_loss:0.4359 g_loss:1.9806 epoch:1221 d_loss:0.4296 g_loss:2.0041 epoch:1222 d_loss:0.5076 g_loss:2.0323 epoch:1223 d_loss:0.4529 g_loss:2.1018 epoch:1224 d_loss:0.5150 g_loss:1.6099 epoch:1225 d_loss:0.6835 g_loss:1.0122 epoch:1226 d_loss:0.5485 g_loss:1.5002 epoch:1227 d_loss:0.5567 g_loss:1.6855 epoch:1228 d_loss:0.5013 g_loss:1.6523 epoch:1229 d_loss:0.6182 g_loss:2.0510 epoch:1230 d_loss:0.4786 g_loss:1.7808 epoch:1231 d_loss:0.5544 g_loss:1.4700 epoch:1232 d_loss:0.6435 g_loss:1.3269 epoch:1233 d_loss:0.4470 g_loss:1.5023 epoch:1234 d_loss:0.5694 g_loss:1.4705 epoch:1235 d_loss:0.4555 g_loss:1.7968 epoch:1236 d_loss:0.4237 g_loss:1.7187 epoch:1237 d_loss:0.5367 g_loss:1.2455 epoch:1238 d_loss:0.4592 g_loss:1.4601 epoch:1239 d_loss:0.5132 g_loss:1.4868 epoch:1240 d_loss:0.4924 g_loss:1.5816 epoch:1241 d_loss:0.3918 g_loss:1.6775 epoch:1242 d_loss:0.5219 g_loss:1.7819 epoch:1243 d_loss:0.3858 g_loss:1.7005 epoch:1244 d_loss:0.3001 g_loss:1.8683 epoch:1245 d_loss:0.3202 g_loss:1.6578 epoch:1246 d_loss:0.3213 g_loss:1.8932 epoch:1247 d_loss:0.3483 g_loss:2.2328 epoch:1248 d_loss:0.3381 g_loss:2.0853 epoch:1249 d_loss:0.3576 g_loss:1.9400 epoch:1250 d_loss:0.3610 g_loss:1.5812 epoch:1251 d_loss:0.4230 g_loss:1.7474 epoch:1252 d_loss:0.2309 g_loss:2.4402 epoch:1253 d_loss:0.2694 g_loss:2.0625 epoch:1254 d_loss:0.3662 g_loss:2.1153 epoch:1255 d_loss:0.3350 g_loss:1.9178 epoch:1256 d_loss:0.3946 g_loss:1.7490 epoch:1257 d_loss:0.4730 g_loss:1.7954 epoch:1258 d_loss:0.4251 g_loss:2.0650 epoch:1259 d_loss:0.3896 g_loss:2.1259 epoch:1260 d_loss:0.2754 g_loss:2.1375 epoch:1261 d_loss:0.3975 g_loss:2.1251 epoch:1262 d_loss:0.5361 g_loss:1.7161 epoch:1263 d_loss:0.3826 g_loss:1.6082 epoch:1264 d_loss:0.3711 g_loss:1.6875 epoch:1265 d_loss:0.3642 g_loss:1.4771 epoch:1266 d_loss:0.4839 g_loss:1.6014 epoch:1267 d_loss:0.3862 g_loss:1.7703 epoch:1268 d_loss:0.3376 g_loss:1.7543 epoch:1269 d_loss:0.4793 g_loss:1.6811 epoch:1270 d_loss:0.4844 g_loss:1.8115 epoch:1271 d_loss:0.3553 g_loss:2.0014 epoch:1272 d_loss:0.5891 g_loss:2.0935 epoch:1273 d_loss:0.5592 g_loss:1.6131 epoch:1274 d_loss:0.5586 g_loss:1.2277 epoch:1275 d_loss:0.6063 g_loss:1.2458 epoch:1276 d_loss:0.4418 g_loss:1.8934 epoch:1277 d_loss:0.5310 g_loss:1.7220 epoch:1278 d_loss:0.4215 g_loss:2.1832 epoch:1279 d_loss:0.3626 g_loss:2.2082 epoch:1280 d_loss:0.3984 g_loss:1.6781 epoch:1281 d_loss:0.3809 g_loss:1.5563 epoch:1282 d_loss:0.4766 g_loss:1.5710 epoch:1283 d_loss:0.4079 g_loss:1.8032 epoch:1284 d_loss:0.4591 g_loss:2.0764 epoch:1285 d_loss:0.4242 g_loss:1.9045 epoch:1286 d_loss:0.4498 g_loss:2.0715 epoch:1287 d_loss:0.4555 g_loss:2.0753 epoch:1288 d_loss:0.4507 g_loss:1.5417 epoch:1289 d_loss:0.5204 g_loss:2.0013 epoch:1290 d_loss:0.4895 g_loss:1.8945 epoch:1291 d_loss:0.3759 g_loss:2.3502 epoch:1292 d_loss:0.3930 g_loss:2.3412 epoch:1293 d_loss:0.4701 g_loss:2.3232 epoch:1294 d_loss:0.4884 g_loss:1.8428 epoch:1295 d_loss:0.5482 g_loss:1.1354 epoch:1296 d_loss:0.3340 g_loss:1.8820 epoch:1297 d_loss:0.5198 g_loss:1.6536 epoch:1298 d_loss:0.5075 g_loss:1.7234 epoch:1299 d_loss:0.4747 g_loss:1.8577 epoch:1300 d_loss:0.4455 g_loss:1.7780 epoch:1301 d_loss:0.4324 g_loss:2.0527 epoch:1302 d_loss:0.4784 g_loss:1.5430 epoch:1303 d_loss:0.6726 g_loss:2.0199 epoch:1304 d_loss:0.4865 g_loss:1.8346 epoch:1305 d_loss:0.4875 g_loss:1.7603 epoch:1306 d_loss:0.6139 g_loss:1.2370 epoch:1307 d_loss:0.6590 g_loss:1.4903 epoch:1308 d_loss:0.3953 g_loss:1.5140 epoch:1309 d_loss:0.4053 g_loss:2.3156 epoch:1310 d_loss:0.6165 g_loss:2.1400 epoch:1311 d_loss:0.5064 g_loss:2.3369 epoch:1312 d_loss:0.5965 g_loss:1.5675 epoch:1313 d_loss:0.4995 g_loss:1.5678 epoch:1314 d_loss:0.5778 g_loss:1.6056 epoch:1315 d_loss:0.5362 g_loss:1.8797 epoch:1316 d_loss:0.4131 g_loss:2.1087 epoch:1317 d_loss:0.5405 g_loss:1.8258 epoch:1318 d_loss:0.4871 g_loss:1.5918 epoch:1319 d_loss:0.5627 g_loss:1.5413 epoch:1320 d_loss:0.4336 g_loss:1.6513 epoch:1321 d_loss:0.3585 g_loss:2.0269 epoch:1322 d_loss:0.3442 g_loss:1.6011 epoch:1323 d_loss:0.3744 g_loss:2.1504 epoch:1324 d_loss:0.2579 g_loss:2.1474 epoch:1325 d_loss:0.4741 g_loss:2.1803 epoch:1326 d_loss:0.3180 g_loss:2.2252 epoch:1327 d_loss:0.4148 g_loss:1.9146 epoch:1328 d_loss:0.3203 g_loss:2.3273 epoch:1329 d_loss:0.2850 g_loss:2.0066 epoch:1330 d_loss:0.3267 g_loss:1.7023 epoch:1331 d_loss:0.4471 g_loss:2.1862 epoch:1332 d_loss:0.3084 g_loss:2.2626 epoch:1333 d_loss:0.4020 g_loss:2.0271 epoch:1334 d_loss:0.3828 g_loss:2.3140 epoch:1335 d_loss:0.3328 g_loss:2.4350 epoch:1336 d_loss:0.3834 g_loss:1.9731 epoch:1337 d_loss:0.3746 g_loss:1.9264 epoch:1338 d_loss:0.3787 g_loss:1.9017 epoch:1339 d_loss:0.5094 g_loss:1.4878 epoch:1340 d_loss:0.4046 g_loss:1.9750 epoch:1341 d_loss:0.4276 g_loss:2.5483 epoch:1342 d_loss:0.4709 g_loss:2.4676 epoch:1343 d_loss:0.4178 g_loss:2.5272 epoch:1344 d_loss:0.2671 g_loss:2.1922 epoch:1345 d_loss:0.3617 g_loss:1.8946 epoch:1346 d_loss:0.4618 g_loss:1.7785 epoch:1347 d_loss:0.7536 g_loss:1.6313 epoch:1348 d_loss:0.3783 g_loss:2.1646 epoch:1349 d_loss:0.5206 g_loss:2.2563 epoch:1350 d_loss:0.8678 g_loss:2.0578 epoch:1351 d_loss:0.5487 g_loss:1.7138 epoch:1352 d_loss:0.5516 g_loss:1.5584 epoch:1353 d_loss:0.3751 g_loss:2.1359 epoch:1354 d_loss:0.3942 g_loss:2.0222 epoch:1355 d_loss:0.3561 g_loss:1.9716 epoch:1356 d_loss:0.5404 g_loss:1.9293 epoch:1357 d_loss:0.4400 g_loss:1.9434 epoch:1358 d_loss:0.3242 g_loss:2.1384 epoch:1359 d_loss:0.3081 g_loss:2.4068 epoch:1360 d_loss:0.3320 g_loss:2.6249 epoch:1361 d_loss:0.4245 g_loss:2.1281 epoch:1362 d_loss:0.4076 g_loss:1.6706 epoch:1363 d_loss:0.4210 g_loss:2.2334 epoch:1364 d_loss:0.2974 g_loss:2.7636 epoch:1365 d_loss:0.4226 g_loss:2.4327 epoch:1366 d_loss:0.3561 g_loss:2.1518 epoch:1367 d_loss:0.3954 g_loss:1.8363 epoch:1368 d_loss:0.4744 g_loss:1.9794 epoch:1369 d_loss:0.4179 g_loss:2.3397 epoch:1370 d_loss:0.4304 g_loss:2.1355 epoch:1371 d_loss:0.4560 g_loss:2.2831 epoch:1372 d_loss:0.5051 g_loss:1.8029 epoch:1373 d_loss:0.4136 g_loss:1.7931 epoch:1374 d_loss:0.4270 g_loss:1.4845 epoch:1375 d_loss:0.5824 g_loss:1.6515 epoch:1376 d_loss:0.6135 g_loss:1.8212 epoch:1377 d_loss:0.6349 g_loss:1.7939 epoch:1378 d_loss:0.6950 g_loss:1.5393 epoch:1379 d_loss:0.6714 g_loss:1.9945 epoch:1380 d_loss:0.6615 g_loss:1.4186 epoch:1381 d_loss:0.6906 g_loss:1.7138 epoch:1382 d_loss:0.6705 g_loss:1.5495 epoch:1383 d_loss:0.6234 g_loss:1.9816 epoch:1384 d_loss:0.7692 g_loss:2.2334 epoch:1385 d_loss:0.7539 g_loss:1.8347 epoch:1386 d_loss:0.5098 g_loss:1.8146 epoch:1387 d_loss:0.4853 g_loss:2.0501 epoch:1388 d_loss:0.6136 g_loss:1.8949 epoch:1389 d_loss:0.4789 g_loss:1.4178 epoch:1390 d_loss:0.5406 g_loss:1.4070 epoch:1391 d_loss:0.3694 g_loss:1.4146 epoch:1392 d_loss:0.4590 g_loss:1.7080 epoch:1393 d_loss:0.3872 g_loss:1.7583 epoch:1394 d_loss:0.4226 g_loss:2.0073 epoch:1395 d_loss:0.4958 g_loss:1.8233 epoch:1396 d_loss:0.3003 g_loss:1.9914 epoch:1397 d_loss:0.4073 g_loss:1.8232 epoch:1398 d_loss:0.3301 g_loss:1.9170 epoch:1399 d_loss:0.5190 g_loss:1.8817 epoch:1400 d_loss:0.3168 g_loss:1.7118 epoch:1401 d_loss:0.2604 g_loss:1.7851 epoch:1402 d_loss:0.4471 g_loss:1.5499 epoch:1403 d_loss:0.3247 g_loss:2.0300 epoch:1404 d_loss:0.2423 g_loss:2.1221 epoch:1405 d_loss:0.4085 g_loss:1.8259 epoch:1406 d_loss:0.2281 g_loss:2.4038 epoch:1407 d_loss:0.4057 g_loss:1.6432 epoch:1408 d_loss:0.3473 g_loss:2.1936 epoch:1409 d_loss:0.2506 g_loss:2.1777 epoch:1410 d_loss:0.3288 g_loss:1.9964 epoch:1411 d_loss:0.4165 g_loss:2.4673 epoch:1412 d_loss:0.2908 g_loss:1.9982 epoch:1413 d_loss:0.2654 g_loss:2.0025 epoch:1414 d_loss:0.4624 g_loss:1.9446 epoch:1415 d_loss:0.2985 g_loss:1.9218 epoch:1416 d_loss:0.2803 g_loss:2.2614
epoch:1417 d_loss:0.4108 g_loss:1.9409 epoch:1418 d_loss:0.3342 g_loss:2.5178 epoch:1419 d_loss:0.3187 g_loss:2.2087 epoch:1420 d_loss:0.3173 g_loss:2.1235 epoch:1421 d_loss:0.4401 g_loss:1.8288 epoch:1422 d_loss:0.4241 g_loss:2.0731 epoch:1423 d_loss:0.3804 g_loss:2.0167 epoch:1424 d_loss:0.5758 g_loss:1.3939 epoch:1425 d_loss:0.5001 g_loss:1.9849 epoch:1426 d_loss:0.4911 g_loss:1.8639 epoch:1427 d_loss:0.3982 g_loss:1.3731 epoch:1428 d_loss:0.4388 g_loss:1.6035 epoch:1429 d_loss:0.5090 g_loss:1.6664 epoch:1430 d_loss:0.4925 g_loss:1.7714 epoch:1431 d_loss:0.4239 g_loss:1.7273 epoch:1432 d_loss:0.4874 g_loss:1.2740 epoch:1433 d_loss:0.4828 g_loss:1.7382 epoch:1434 d_loss:0.4975 g_loss:1.7412 epoch:1435 d_loss:0.5025 g_loss:1.8929 epoch:1436 d_loss:0.4924 g_loss:1.5253 epoch:1437 d_loss:0.5823 g_loss:1.7245 epoch:1438 d_loss:0.6667 g_loss:1.3393 epoch:1439 d_loss:0.4944 g_loss:1.5964 epoch:1440 d_loss:0.3931 g_loss:1.5624 epoch:1441 d_loss:0.3706 g_loss:1.8308 epoch:1442 d_loss:0.5187 g_loss:1.8822 epoch:1443 d_loss:0.4707 g_loss:1.7792 epoch:1444 d_loss:0.5624 g_loss:1.6459 epoch:1445 d_loss:0.5014 g_loss:1.4700 epoch:1446 d_loss:0.4991 g_loss:1.2113 epoch:1447 d_loss:0.4691 g_loss:1.6203 epoch:1448 d_loss:0.4128 g_loss:1.8779 epoch:1449 d_loss:0.3830 g_loss:2.0713 epoch:1450 d_loss:0.5817 g_loss:1.9361 epoch:1451 d_loss:0.5503 g_loss:1.3838 epoch:1452 d_loss:0.4568 g_loss:1.7705 epoch:1453 d_loss:0.4415 g_loss:1.6949 epoch:1454 d_loss:0.4055 g_loss:1.6797 epoch:1455 d_loss:0.4717 g_loss:1.8582 epoch:1456 d_loss:0.6029 g_loss:1.6064 epoch:1457 d_loss:0.4215 g_loss:1.8312 epoch:1458 d_loss:0.5673 g_loss:1.6759 epoch:1459 d_loss:0.5841 g_loss:1.4553 epoch:1460 d_loss:0.5692 g_loss:1.7111 epoch:1461 d_loss:0.6203 g_loss:1.5484 epoch:1462 d_loss:0.4078 g_loss:1.5098 epoch:1463 d_loss:0.7052 g_loss:1.3425 epoch:1464 d_loss:0.4240 g_loss:1.6150 epoch:1465 d_loss:0.5831 g_loss:1.6190 epoch:1466 d_loss:0.5853 g_loss:1.8646 epoch:1467 d_loss:0.6677 g_loss:1.6134 epoch:1468 d_loss:0.4999 g_loss:1.5582 epoch:1469 d_loss:0.6143 g_loss:1.5896 epoch:1470 d_loss:0.5056 g_loss:1.4199 epoch:1471 d_loss:0.4635 g_loss:1.2848 epoch:1472 d_loss:0.5244 g_loss:1.6185 epoch:1473 d_loss:0.5949 g_loss:1.6267 epoch:1474 d_loss:0.4308 g_loss:1.7051 epoch:1475 d_loss:0.3851 g_loss:1.8028 epoch:1476 d_loss:0.4340 g_loss:1.8482 epoch:1477 d_loss:0.4813 g_loss:1.4547 epoch:1478 d_loss:0.4171 g_loss:1.8075 epoch:1479 d_loss:0.3777 g_loss:1.6471 epoch:1480 d_loss:0.3607 g_loss:1.6383 epoch:1481 d_loss:0.4289 g_loss:1.5288 epoch:1482 d_loss:0.3332 g_loss:1.9551 epoch:1483 d_loss:0.4058 g_loss:2.1408 epoch:1484 d_loss:0.4226 g_loss:2.1600 epoch:1485 d_loss:0.3639 g_loss:2.3550 epoch:1486 d_loss:0.3459 g_loss:2.1958 epoch:1487 d_loss:0.5330 g_loss:1.7317 epoch:1488 d_loss:0.4553 g_loss:1.4305 epoch:1489 d_loss:0.4565 g_loss:1.4748 epoch:1490 d_loss:0.4319 g_loss:1.6057 epoch:1491 d_loss:0.3625 g_loss:1.9520 epoch:1492 d_loss:0.3677 g_loss:2.5227 epoch:1493 d_loss:0.4095 g_loss:2.8571 epoch:1494 d_loss:0.4337 g_loss:2.2311 epoch:1495 d_loss:0.4330 g_loss:1.9291 epoch:1496 d_loss:0.5599 g_loss:1.6619 epoch:1497 d_loss:0.3405 g_loss:1.5154 epoch:1498 d_loss:0.6057 g_loss:1.6686 epoch:1499 d_loss:0.4127 g_loss:1.9655 epoch:1500 d_loss:0.4107 g_loss:2.0739 epoch:1501 d_loss:0.4034 g_loss:2.2595 epoch:1502 d_loss:0.4849 g_loss:1.9855 epoch:1503 d_loss:0.5745 g_loss:2.0123 epoch:1504 d_loss:0.5324 g_loss:1.5844 epoch:1505 d_loss:0.5285 g_loss:1.4022 epoch:1506 d_loss:0.5604 g_loss:1.6125 epoch:1507 d_loss:0.4488 g_loss:2.2056 epoch:1508 d_loss:0.5020 g_loss:2.4898 epoch:1509 d_loss:0.5192 g_loss:1.8438 epoch:1510 d_loss:0.3822 g_loss:1.4630 epoch:1511 d_loss:0.3989 g_loss:1.8848 epoch:1512 d_loss:0.4170 g_loss:1.1382 epoch:1513 d_loss:0.3849 g_loss:1.9349 epoch:1514 d_loss:0.4748 g_loss:1.8225 epoch:1515 d_loss:0.3523 g_loss:2.2142 epoch:1516 d_loss:0.4337 g_loss:1.6333 epoch:1517 d_loss:0.4076 g_loss:2.1080 epoch:1518 d_loss:0.3544 g_loss:1.9727 epoch:1519 d_loss:0.5008 g_loss:1.4942 epoch:1520 d_loss:0.4465 g_loss:1.7056 epoch:1521 d_loss:0.3661 g_loss:1.9838 epoch:1522 d_loss:0.4398 g_loss:1.7448 epoch:1523 d_loss:0.3873 g_loss:1.9571 epoch:1524 d_loss:0.3284 g_loss:1.5328 epoch:1525 d_loss:0.5200 g_loss:1.5994 epoch:1526 d_loss:0.4097 g_loss:1.8525 epoch:1527 d_loss:0.4016 g_loss:2.1326 epoch:1528 d_loss:0.4707 g_loss:1.8031 epoch:1529 d_loss:0.5343 g_loss:2.1779 epoch:1530 d_loss:0.5844 g_loss:1.7852 epoch:1531 d_loss:0.4537 g_loss:1.5149 epoch:1532 d_loss:0.5438 g_loss:1.4560 epoch:1533 d_loss:0.3821 g_loss:1.4388 epoch:1534 d_loss:0.3854 g_loss:2.1232 epoch:1535 d_loss:0.5454 g_loss:2.1328 epoch:1536 d_loss:0.4784 g_loss:2.1693 epoch:1537 d_loss:0.5320 g_loss:1.3732 epoch:1538 d_loss:0.4886 g_loss:1.3363 epoch:1539 d_loss:0.7276 g_loss:1.2091 epoch:1540 d_loss:0.5036 g_loss:1.4230 epoch:1541 d_loss:0.5771 g_loss:1.6381 epoch:1542 d_loss:0.5567 g_loss:2.0319 epoch:1543 d_loss:0.4622 g_loss:1.6917 epoch:1544 d_loss:0.6598 g_loss:1.4304 epoch:1545 d_loss:0.5321 g_loss:1.4422 epoch:1546 d_loss:0.5302 g_loss:1.3843 epoch:1547 d_loss:0.3607 g_loss:1.6035 epoch:1548 d_loss:0.3706 g_loss:2.2879 epoch:1549 d_loss:0.3643 g_loss:2.1548 epoch:1550 d_loss:0.4153 g_loss:2.1337 epoch:1551 d_loss:0.4624 g_loss:1.5846 epoch:1552 d_loss:0.4668 g_loss:1.4982 epoch:1553 d_loss:0.5116 g_loss:1.2216 epoch:1554 d_loss:0.5050 g_loss:1.6519 epoch:1555 d_loss:0.4922 g_loss:2.0212 epoch:1556 d_loss:0.4038 g_loss:2.2376 epoch:1557 d_loss:0.4217 g_loss:1.8117 epoch:1558 d_loss:0.3918 g_loss:1.9238 epoch:1559 d_loss:0.4862 g_loss:1.6244 epoch:1560 d_loss:0.3717 g_loss:1.8909 epoch:1561 d_loss:0.3107 g_loss:1.9816 epoch:1562 d_loss:0.3752 g_loss:2.3049 epoch:1563 d_loss:0.3757 g_loss:1.8635 epoch:1564 d_loss:0.4729 g_loss:1.6321 epoch:1565 d_loss:0.4163 g_loss:1.8752 epoch:1566 d_loss:0.3171 g_loss:1.8960 epoch:1567 d_loss:0.2991 g_loss:2.1421 epoch:1568 d_loss:0.4015 g_loss:2.4549 epoch:1569 d_loss:0.4102 g_loss:1.9152 epoch:1570 d_loss:0.4260 g_loss:1.8400 epoch:1571 d_loss:0.5096 g_loss:1.5119 epoch:1572 d_loss:0.4072 g_loss:1.7232 epoch:1573 d_loss:0.3751 g_loss:1.8264 epoch:1574 d_loss:0.4109 g_loss:2.0265 epoch:1575 d_loss:0.5259 g_loss:1.7998 epoch:1576 d_loss:0.5630 g_loss:1.5449 epoch:1577 d_loss:0.4615 g_loss:1.8072 epoch:1578 d_loss:0.6757 g_loss:1.6864 epoch:1579 d_loss:0.6680 g_loss:1.5377 epoch:1580 d_loss:0.4411 g_loss:1.7130 epoch:1581 d_loss:0.4297 g_loss:1.8382 epoch:1582 d_loss:0.5817 g_loss:1.8209 epoch:1583 d_loss:0.7094 g_loss:1.4418 epoch:1584 d_loss:0.5153 g_loss:1.8668 epoch:1585 d_loss:0.5714 g_loss:1.8551 epoch:1586 d_loss:0.5398 g_loss:1.8410 epoch:1587 d_loss:0.5551 g_loss:1.3899 epoch:1588 d_loss:0.6525 g_loss:1.4643 epoch:1589 d_loss:0.4816 g_loss:1.5154 epoch:1590 d_loss:0.4406 g_loss:1.6935 epoch:1591 d_loss:0.5820 g_loss:1.6606 epoch:1592 d_loss:0.4940 g_loss:1.8146 epoch:1593 d_loss:0.4335 g_loss:1.5062 epoch:1594 d_loss:0.4832 g_loss:1.3771 epoch:1595 d_loss:0.4991 g_loss:1.5136 epoch:1596 d_loss:0.3739 g_loss:1.9716 epoch:1597 d_loss:0.4019 g_loss:2.0882 epoch:1598 d_loss:0.4491 g_loss:2.5770 epoch:1599 d_loss:0.3640 g_loss:2.1418 epoch:1600 d_loss:0.4614 g_loss:2.0781 epoch:1601 d_loss:0.3382 g_loss:1.8050 epoch:1602 d_loss:0.3882 g_loss:1.6664 epoch:1603 d_loss:0.4055 g_loss:1.5560 epoch:1604 d_loss:0.2886 g_loss:1.7923 epoch:1605 d_loss:0.3643 g_loss:2.0284 epoch:1606 d_loss:0.4730 g_loss:2.3074 epoch:1607 d_loss:0.3847 g_loss:2.1216 epoch:1608 d_loss:0.5288 g_loss:1.6878 epoch:1609 d_loss:0.5866 g_loss:1.7856 epoch:1610 d_loss:0.5889 g_loss:1.1513 epoch:1611 d_loss:0.6003 g_loss:1.6610 epoch:1612 d_loss:0.5038 g_loss:1.4792 epoch:1613 d_loss:0.3768 g_loss:1.6794 epoch:1614 d_loss:0.3507 g_loss:1.9264 epoch:1615 d_loss:0.5588 g_loss:2.2716 epoch:1616 d_loss:0.6085 g_loss:1.4887 epoch:1617 d_loss:0.5719 g_loss:0.9352 epoch:1618 d_loss:0.7200 g_loss:1.3092
epoch:1619 d_loss:0.4023 g_loss:1.4314 epoch:1620 d_loss:0.4581 g_loss:1.6014 epoch:1621 d_loss:0.4678 g_loss:1.6887 epoch:1622 d_loss:0.6409 g_loss:1.5496 epoch:1623 d_loss:0.6374 g_loss:1.5375 epoch:1624 d_loss:0.5021 g_loss:1.2979 epoch:1625 d_loss:0.3874 g_loss:1.3782 epoch:1626 d_loss:0.4458 g_loss:1.8605 epoch:1627 d_loss:0.4349 g_loss:2.2042 epoch:1628 d_loss:0.4866 g_loss:1.7911 epoch:1629 d_loss:0.4537 g_loss:1.8591 epoch:1630 d_loss:0.3965 g_loss:1.8894 epoch:1631 d_loss:0.5348 g_loss:1.3385 epoch:1632 d_loss:0.4324 g_loss:1.3873 epoch:1633 d_loss:0.4590 g_loss:1.4649 epoch:1634 d_loss:0.5994 g_loss:1.6895 epoch:1635 d_loss:0.3669 g_loss:1.7457 epoch:1636 d_loss:0.4809 g_loss:1.4796 epoch:1637 d_loss:0.5708 g_loss:1.6643 epoch:1638 d_loss:0.4741 g_loss:1.9260 epoch:1639 d_loss:0.5074 g_loss:1.7071 epoch:1640 d_loss:0.5002 g_loss:1.5490 epoch:1641 d_loss:0.4973 g_loss:1.4810 epoch:1642 d_loss:0.4066 g_loss:1.6063 epoch:1643 d_loss:0.3408 g_loss:1.9260 epoch:1644 d_loss:0.4238 g_loss:2.1172 epoch:1645 d_loss:0.6199 g_loss:1.7107 epoch:1646 d_loss:0.5037 g_loss:1.5818 epoch:1647 d_loss:0.3682 g_loss:1.8589 epoch:1648 d_loss:0.4958 g_loss:1.6124 epoch:1649 d_loss:0.4542 g_loss:1.7411 epoch:1650 d_loss:0.5729 g_loss:1.5628 epoch:1651 d_loss:0.4498 g_loss:1.5752 epoch:1652 d_loss:0.4314 g_loss:1.8039 epoch:1653 d_loss:0.5523 g_loss:1.6984 epoch:1654 d_loss:0.4091 g_loss:1.6336 epoch:1655 d_loss:0.4955 g_loss:1.6752 epoch:1656 d_loss:0.4023 g_loss:1.9455 epoch:1657 d_loss:0.4788 g_loss:1.9465 epoch:1658 d_loss:0.4536 g_loss:1.9583 epoch:1659 d_loss:0.3902 g_loss:1.6354 epoch:1660 d_loss:0.4024 g_loss:1.8299 epoch:1661 d_loss:0.4173 g_loss:1.8037 epoch:1662 d_loss:0.3474 g_loss:1.8506 epoch:1663 d_loss:0.4917 g_loss:1.8320 epoch:1664 d_loss:0.4120 g_loss:1.8374 epoch:1665 d_loss:0.4571 g_loss:1.5766 epoch:1666 d_loss:0.3604 g_loss:1.7148 epoch:1667 d_loss:0.4013 g_loss:1.8126 epoch:1668 d_loss:0.4364 g_loss:1.8594 epoch:1669 d_loss:0.3112 g_loss:2.0303 epoch:1670 d_loss:0.4982 g_loss:1.9198 epoch:1671 d_loss:0.4116 g_loss:1.6560 epoch:1672 d_loss:0.4681 g_loss:1.8289 epoch:1673 d_loss:0.3545 g_loss:1.8334 epoch:1674 d_loss:0.3671 g_loss:1.8764 epoch:1675 d_loss:0.4941 g_loss:1.5040 epoch:1676 d_loss:0.3710 g_loss:1.7634 epoch:1677 d_loss:0.6393 g_loss:1.6196 epoch:1678 d_loss:0.3856 g_loss:1.7485 epoch:1679 d_loss:0.6073 g_loss:1.4737 epoch:1680 d_loss:0.5167 g_loss:1.4655 epoch:1681 d_loss:0.5286 g_loss:1.4656 epoch:1682 d_loss:0.4582 g_loss:1.5778 epoch:1683 d_loss:0.5483 g_loss:1.5002 epoch:1684 d_loss:0.6047 g_loss:1.5740 epoch:1685 d_loss:0.5272 g_loss:1.9897 epoch:1686 d_loss:0.5008 g_loss:1.4394 epoch:1687 d_loss:0.7079 g_loss:1.2912 epoch:1688 d_loss:0.5919 g_loss:1.0830 epoch:1689 d_loss:0.5395 g_loss:1.4094 epoch:1690 d_loss:0.5945 g_loss:1.3342 epoch:1691 d_loss:0.5787 g_loss:1.5707 epoch:1692 d_loss:0.5274 g_loss:1.7914 epoch:1693 d_loss:0.7228 g_loss:1.4084 epoch:1694 d_loss:0.8419 g_loss:0.8605 epoch:1695 d_loss:0.6010 g_loss:1.0397 epoch:1696 d_loss:0.6084 g_loss:1.3637 epoch:1697 d_loss:0.5137 g_loss:1.4689 epoch:1698 d_loss:0.5488 g_loss:1.7306 epoch:1699 d_loss:0.5915 g_loss:1.9493 epoch:1700 d_loss:0.4917 g_loss:1.5837 epoch:1701 d_loss:0.5207 g_loss:1.7529 epoch:1702 d_loss:0.4731 g_loss:1.3830 epoch:1703 d_loss:0.4394 g_loss:1.4024 epoch:1704 d_loss:0.4821 g_loss:1.2869 epoch:1705 d_loss:0.3878 g_loss:1.6898 epoch:1706 d_loss:0.3699 g_loss:2.1321 epoch:1707 d_loss:0.3490 g_loss:2.0928 epoch:1708 d_loss:0.5264 g_loss:2.0181 epoch:1709 d_loss:0.4480 g_loss:1.9803 epoch:1710 d_loss:0.3344 g_loss:1.7241 epoch:1711 d_loss:0.3561 g_loss:1.6138 epoch:1712 d_loss:0.3615 g_loss:1.8590 epoch:1713 d_loss:0.2787 g_loss:1.9494 epoch:1714 d_loss:0.3736 g_loss:1.9093 epoch:1715 d_loss:0.3270 g_loss:1.8911 epoch:1716 d_loss:0.4667 g_loss:2.0546 epoch:1717 d_loss:0.3901 g_loss:1.5369 epoch:1718 d_loss:0.3957 g_loss:1.6896 epoch:1719 d_loss:0.5133 g_loss:1.7382 epoch:1720 d_loss:0.3981 g_loss:1.7350 epoch:1721 d_loss:0.3746 g_loss:1.7604 epoch:1722 d_loss:0.3320 g_loss:1.8392 epoch:1723 d_loss:0.4288 g_loss:1.5795 epoch:1724 d_loss:0.3464 g_loss:1.9006 epoch:1725 d_loss:0.3922 g_loss:1.6511 epoch:1726 d_loss:0.3629 g_loss:1.6257 epoch:1727 d_loss:0.4788 g_loss:1.6976 epoch:1728 d_loss:0.4175 g_loss:1.9030 epoch:1729 d_loss:0.4476 g_loss:1.8841 epoch:1730 d_loss:0.6131 g_loss:1.5321 epoch:1731 d_loss:0.4904 g_loss:1.5195 epoch:1732 d_loss:0.5305 g_loss:1.6222 epoch:1733 d_loss:0.4392 g_loss:1.8161 epoch:1734 d_loss:0.5746 g_loss:1.4163 epoch:1735 d_loss:0.5461 g_loss:1.4442 epoch:1736 d_loss:0.5251 g_loss:1.1810 epoch:1737 d_loss:0.5704 g_loss:1.4347 epoch:1738 d_loss:0.4167 g_loss:1.7830 epoch:1739 d_loss:0.5629 g_loss:1.8535 epoch:1740 d_loss:0.5032 g_loss:1.8521 epoch:1741 d_loss:0.4573 g_loss:1.7102 epoch:1742 d_loss:0.5718 g_loss:1.4808 epoch:1743 d_loss:0.4981 g_loss:1.4769 epoch:1744 d_loss:0.5439 g_loss:1.7239 epoch:1745 d_loss:0.5352 g_loss:1.5015 epoch:1746 d_loss:0.5072 g_loss:1.8588 epoch:1747 d_loss:0.4215 g_loss:1.6356 epoch:1748 d_loss:0.4945 g_loss:1.6064 epoch:1749 d_loss:0.5411 g_loss:1.3043 epoch:1750 d_loss:0.4087 g_loss:1.4439 epoch:1751 d_loss:0.4002 g_loss:1.6587 epoch:1752 d_loss:0.4168 g_loss:1.4399 epoch:1753 d_loss:0.5205 g_loss:1.5846 epoch:1754 d_loss:0.5333 g_loss:1.9398 epoch:1755 d_loss:0.5646 g_loss:1.6225 epoch:1756 d_loss:0.6060 g_loss:1.4366 epoch:1757 d_loss:0.5872 g_loss:1.3864 epoch:1758 d_loss:0.5080 g_loss:1.2025 epoch:1759 d_loss:0.6337 g_loss:1.3442 epoch:1760 d_loss:0.3959 g_loss:1.4171 epoch:1761 d_loss:0.6080 g_loss:1.6721 epoch:1762 d_loss:0.5734 g_loss:2.0473 epoch:1763 d_loss:0.6349 g_loss:1.5868 epoch:1764 d_loss:0.4593 g_loss:1.4161 epoch:1765 d_loss:0.5429 g_loss:1.2241 epoch:1766 d_loss:0.5480 g_loss:1.5953 epoch:1767 d_loss:0.4616 g_loss:1.5600 epoch:1768 d_loss:0.4098 g_loss:1.4545 epoch:1769 d_loss:0.4255 g_loss:1.7716 epoch:1770 d_loss:0.4450 g_loss:1.9638 epoch:1771 d_loss:0.4527 g_loss:1.8752 epoch:1772 d_loss:0.3232 g_loss:1.7245 epoch:1773 d_loss:0.4433 g_loss:1.7042 epoch:1774 d_loss:0.4124 g_loss:1.7361 epoch:1775 d_loss:0.3847 g_loss:1.6921 epoch:1776 d_loss:0.3589 g_loss:1.7943 epoch:1777 d_loss:0.4452 g_loss:1.8723 epoch:1778 d_loss:0.4517 g_loss:1.7017 epoch:1779 d_loss:0.4192 g_loss:1.5836 epoch:1780 d_loss:0.3740 g_loss:1.7955 epoch:1781 d_loss:0.2794 g_loss:1.7492 epoch:1782 d_loss:0.3738 g_loss:1.7864 epoch:1783 d_loss:0.3932 g_loss:1.4752 epoch:1784 d_loss:0.4691 g_loss:1.3907 epoch:1785 d_loss:0.4456 g_loss:1.6840 epoch:1786 d_loss:0.3682 g_loss:1.9360 epoch:1787 d_loss:0.5800 g_loss:1.9521 epoch:1788 d_loss:0.4122 g_loss:1.6181 epoch:1789 d_loss:0.4973 g_loss:1.3786 epoch:1790 d_loss:0.4710 g_loss:1.7193 epoch:1791 d_loss:0.3996 g_loss:1.4808 epoch:1792 d_loss:0.5483 g_loss:1.8129 epoch:1793 d_loss:0.4091 g_loss:1.5662 epoch:1794 d_loss:0.3866 g_loss:1.7387 epoch:1795 d_loss:0.5556 g_loss:1.5479 epoch:1796 d_loss:0.5368 g_loss:1.5060 epoch:1797 d_loss:0.4694 g_loss:1.5754 epoch:1798 d_loss:0.5678 g_loss:1.5537 epoch:1799 d_loss:0.5537 g_loss:1.6145 epoch:1800 d_loss:0.4467 g_loss:2.1032 epoch:1801 d_loss:0.5091 g_loss:1.4691 epoch:1802 d_loss:0.6270 g_loss:1.3187 epoch:1803 d_loss:0.6466 g_loss:1.1927 epoch:1804 d_loss:0.4481 g_loss:1.4645 epoch:1805 d_loss:0.5032 g_loss:1.6206 epoch:1806 d_loss:0.4689 g_loss:2.2118 epoch:1807 d_loss:0.4383 g_loss:1.9974 epoch:1808 d_loss:0.5711 g_loss:1.5878 epoch:1809 d_loss:0.5205 g_loss:1.5436 epoch:1810 d_loss:0.4183 g_loss:1.5749 epoch:1811 d_loss:0.5406 g_loss:1.5922 epoch:1812 d_loss:0.5257 g_loss:1.5597 epoch:1813 d_loss:0.4105 g_loss:1.3632 epoch:1814 d_loss:0.4133 g_loss:1.5332 epoch:1815 d_loss:0.3828 g_loss:1.7764 epoch:1816 d_loss:0.3725 g_loss:1.6831 epoch:1817 d_loss:0.4360 g_loss:1.9221 epoch:1818 d_loss:0.4641 g_loss:1.4841 epoch:1819 d_loss:0.4820 g_loss:1.6876 epoch:1820 d_loss:0.4719 g_loss:1.6858
epoch:1821 d_loss:0.5424 g_loss:1.9578 epoch:1822 d_loss:0.5214 g_loss:1.5547 epoch:1823 d_loss:0.5053 g_loss:1.5032 epoch:1824 d_loss:0.5242 g_loss:1.4644 epoch:1825 d_loss:0.4683 g_loss:1.4998 epoch:1826 d_loss:0.5382 g_loss:1.5571 epoch:1827 d_loss:0.6115 g_loss:1.5174 epoch:1828 d_loss:0.3804 g_loss:1.8072 epoch:1829 d_loss:0.4802 g_loss:1.7731 epoch:1830 d_loss:0.5102 g_loss:1.5767 epoch:1831 d_loss:0.4739 g_loss:1.6262 epoch:1832 d_loss:0.4761 g_loss:1.5662 epoch:1833 d_loss:0.6274 g_loss:1.5176 epoch:1834 d_loss:0.5558 g_loss:1.4625 epoch:1835 d_loss:0.5149 g_loss:1.5827 epoch:1836 d_loss:0.6029 g_loss:1.3744 epoch:1837 d_loss:0.5621 g_loss:1.5698 epoch:1838 d_loss:0.5062 g_loss:1.5181 epoch:1839 d_loss:0.5041 g_loss:1.2507 epoch:1840 d_loss:0.6576 g_loss:1.4444 epoch:1841 d_loss:0.4352 g_loss:2.0109 epoch:1842 d_loss:0.6491 g_loss:2.0874 epoch:1843 d_loss:0.4160 g_loss:1.9268 epoch:1844 d_loss:0.6044 g_loss:2.0835 epoch:1845 d_loss:0.5780 g_loss:1.4920 epoch:1846 d_loss:0.3862 g_loss:1.7772 epoch:1847 d_loss:0.4454 g_loss:1.5298 epoch:1848 d_loss:0.4030 g_loss:1.7275 epoch:1849 d_loss:0.4562 g_loss:1.8466 epoch:1850 d_loss:0.4651 g_loss:1.3198 epoch:1851 d_loss:0.3255 g_loss:1.7936 epoch:1852 d_loss:0.3069 g_loss:1.8413 epoch:1853 d_loss:0.4641 g_loss:1.9052 epoch:1854 d_loss:0.3939 g_loss:1.7953 epoch:1855 d_loss:0.3433 g_loss:1.7622 epoch:1856 d_loss:0.3543 g_loss:1.6307 epoch:1857 d_loss:0.5046 g_loss:1.3243 epoch:1858 d_loss:0.4031 g_loss:1.9534 epoch:1859 d_loss:0.3625 g_loss:2.1653 epoch:1860 d_loss:0.3227 g_loss:2.3231 epoch:1861 d_loss:0.4900 g_loss:1.7528 epoch:1862 d_loss:0.4588 g_loss:1.6703 epoch:1863 d_loss:0.3640 g_loss:1.5105 epoch:1864 d_loss:0.4322 g_loss:1.4681 epoch:1865 d_loss:0.3634 g_loss:1.8792 epoch:1866 d_loss:0.3979 g_loss:1.9109 epoch:1867 d_loss:0.4782 g_loss:2.0222 epoch:1868 d_loss:0.3278 g_loss:1.8684 epoch:1869 d_loss:0.4908 g_loss:1.7078 epoch:1870 d_loss:0.4354 g_loss:1.7136 epoch:1871 d_loss:0.4840 g_loss:1.6854 epoch:1872 d_loss:0.4553 g_loss:1.7827 epoch:1873 d_loss:0.3190 g_loss:1.6061 epoch:1874 d_loss:0.4444 g_loss:1.9996 epoch:1875 d_loss:0.5878 g_loss:1.8219 epoch:1876 d_loss:0.6395 g_loss:1.9270 epoch:1877 d_loss:0.6508 g_loss:1.6068 epoch:1878 d_loss:0.5851 g_loss:2.0028 epoch:1879 d_loss:0.4757 g_loss:1.9269 epoch:1880 d_loss:0.7436 g_loss:1.3639 epoch:1881 d_loss:0.4222 g_loss:1.8018 epoch:1882 d_loss:0.5795 g_loss:1.7677 epoch:1883 d_loss:0.3483 g_loss:2.0733 epoch:1884 d_loss:0.4008 g_loss:2.2830 epoch:1885 d_loss:0.5401 g_loss:1.7131 epoch:1886 d_loss:0.5314 g_loss:1.8780 epoch:1887 d_loss:0.5850 g_loss:1.5531 epoch:1888 d_loss:0.3869 g_loss:2.0862 epoch:1889 d_loss:0.4509 g_loss:1.6242 epoch:1890 d_loss:0.5732 g_loss:2.1034 epoch:1891 d_loss:0.4461 g_loss:1.5932 epoch:1892 d_loss:0.4633 g_loss:1.6446 epoch:1893 d_loss:0.5697 g_loss:1.8731 epoch:1894 d_loss:0.5395 g_loss:1.4693 epoch:1895 d_loss:0.5564 g_loss:1.7451 epoch:1896 d_loss:0.2934 g_loss:1.9285 epoch:1897 d_loss:0.5828 g_loss:1.5731 epoch:1898 d_loss:0.4804 g_loss:1.9299 epoch:1899 d_loss:0.4424 g_loss:1.8011 epoch:1900 d_loss:0.5498 g_loss:1.6158 epoch:1901 d_loss:0.4447 g_loss:1.7203 epoch:1902 d_loss:0.4969 g_loss:2.0956 epoch:1903 d_loss:0.5189 g_loss:2.0040 epoch:1904 d_loss:0.4786 g_loss:1.7939 epoch:1905 d_loss:0.4091 g_loss:2.1667 epoch:1906 d_loss:0.4274 g_loss:1.4451 epoch:1907 d_loss:0.5348 g_loss:1.6178 epoch:1908 d_loss:0.4830 g_loss:1.2542 epoch:1909 d_loss:0.6079 g_loss:1.3706 epoch:1910 d_loss:0.4684 g_loss:1.9017 epoch:1911 d_loss:0.3476 g_loss:1.9695 epoch:1912 d_loss:0.4746 g_loss:1.9741 epoch:1913 d_loss:0.5853 g_loss:1.8508 epoch:1914 d_loss:0.4550 g_loss:1.5061 epoch:1915 d_loss:0.4872 g_loss:1.6961 epoch:1916 d_loss:0.3930 g_loss:1.8791 epoch:1917 d_loss:0.3222 g_loss:2.1481 epoch:1918 d_loss:0.3816 g_loss:2.2162 epoch:1919 d_loss:0.3987 g_loss:1.8970 epoch:1920 d_loss:0.3994 g_loss:2.0873 epoch:1921 d_loss:0.4777 g_loss:1.5872 epoch:1922 d_loss:0.3219 g_loss:1.4803 epoch:1923 d_loss:0.3158 g_loss:2.0216 epoch:1924 d_loss:0.3833 g_loss:2.1419 epoch:1925 d_loss:0.5146 g_loss:1.9622 epoch:1926 d_loss:0.3785 g_loss:2.1048 epoch:1927 d_loss:0.5681 g_loss:2.3461 epoch:1928 d_loss:0.3803 g_loss:1.9472 epoch:1929 d_loss:0.3713 g_loss:1.6700 epoch:1930 d_loss:0.3670 g_loss:1.5249 epoch:1931 d_loss:0.5631 g_loss:1.7652 epoch:1932 d_loss:0.5090 g_loss:1.5857 epoch:1933 d_loss:0.3192 g_loss:2.2549 epoch:1934 d_loss:0.4803 g_loss:2.1252 epoch:1935 d_loss:0.4652 g_loss:1.9729 epoch:1936 d_loss:0.6430 g_loss:1.8596 epoch:1937 d_loss:0.4084 g_loss:1.8147 epoch:1938 d_loss:0.6527 g_loss:1.4936 epoch:1939 d_loss:0.4382 g_loss:1.7765 epoch:1940 d_loss:0.5007 g_loss:1.7339 epoch:1941 d_loss:0.5050 g_loss:2.0151 epoch:1942 d_loss:0.6854 g_loss:1.6136 epoch:1943 d_loss:0.5673 g_loss:1.4479 epoch:1944 d_loss:0.5147 g_loss:1.7273 epoch:1945 d_loss:0.4701 g_loss:1.7774 epoch:1946 d_loss:0.4596 g_loss:1.6636 epoch:1947 d_loss:0.4534 g_loss:1.6312 epoch:1948 d_loss:0.5817 g_loss:1.3566 epoch:1949 d_loss:0.5248 g_loss:1.4181 epoch:1950 d_loss:0.5095 g_loss:1.8784 epoch:1951 d_loss:0.5922 g_loss:1.9388 epoch:1952 d_loss:0.4624 g_loss:1.5831 epoch:1953 d_loss:0.4945 g_loss:1.4220 epoch:1954 d_loss:0.6142 g_loss:1.8312 epoch:1955 d_loss:0.5345 g_loss:1.4423 epoch:1956 d_loss:0.6380 g_loss:1.7527 epoch:1957 d_loss:0.4308 g_loss:1.8384 epoch:1958 d_loss:0.5323 g_loss:1.8247 epoch:1959 d_loss:0.4636 g_loss:1.4939 epoch:1960 d_loss:0.7175 g_loss:1.1010 epoch:1961 d_loss:0.4212 g_loss:1.6422 epoch:1962 d_loss:0.5390 g_loss:1.4921 epoch:1963 d_loss:0.3337 g_loss:2.3357 epoch:1964 d_loss:0.6342 g_loss:1.9303 epoch:1965 d_loss:0.5829 g_loss:1.6996 epoch:1966 d_loss:0.4897 g_loss:1.4998 epoch:1967 d_loss:0.5500 g_loss:1.4726 epoch:1968 d_loss:0.3897 g_loss:1.9733 epoch:1969 d_loss:0.3832 g_loss:2.0089 epoch:1970 d_loss:0.4834 g_loss:1.9614 epoch:1971 d_loss:0.5186 g_loss:1.8034 epoch:1972 d_loss:0.5835 g_loss:1.3622 epoch:1973 d_loss:0.3469 g_loss:1.7024 epoch:1974 d_loss:0.4388 g_loss:1.6338 epoch:1975 d_loss:0.4589 g_loss:1.6749 epoch:1976 d_loss:0.4353 g_loss:1.9457 epoch:1977 d_loss:0.3809 g_loss:1.9991 epoch:1978 d_loss:0.3848 g_loss:1.8846 epoch:1979 d_loss:0.4414 g_loss:1.8097 epoch:1980 d_loss:0.4713 g_loss:1.5171 epoch:1981 d_loss:0.4366 g_loss:1.6943 epoch:1982 d_loss:0.3614 g_loss:1.4380 epoch:1983 d_loss:0.4743 g_loss:1.7526 epoch:1984 d_loss:0.3889 g_loss:2.0147 epoch:1985 d_loss:0.3005 g_loss:2.2371 epoch:1986 d_loss:0.5264 g_loss:1.8134 epoch:1987 d_loss:0.4846 g_loss:1.7306 epoch:1988 d_loss:0.5497 g_loss:1.3760 epoch:1989 d_loss:0.5380 g_loss:1.3887 epoch:1990 d_loss:0.4802 g_loss:1.7312 epoch:1991 d_loss:0.5528 g_loss:1.8907 epoch:1992 d_loss:0.5266 g_loss:2.0335 epoch:1993 d_loss:0.5355 g_loss:1.5226 epoch:1994 d_loss:0.5505 g_loss:1.5617 epoch:1995 d_loss:0.6501 g_loss:1.4506 epoch:1996 d_loss:0.4359 g_loss:1.2530 epoch:1997 d_loss:0.5128 g_loss:1.4710 epoch:1998 d_loss:0.5366 g_loss:1.3517 epoch:1999 d_loss:0.5661 g_loss:1.6145 epoch:2000 d_loss:0.4667 g_loss:2.1844
4. 이미지의 특징을 추출하는 오토인코더¶
실습: 오토인코더 실습하기¶
In [3]:
Copied!
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D, Flatten, Reshape
import matplotlib.pyplot as plt
import numpy as np
# MNIST 데이터셋을 불러옵니다.
(X_train, _), (X_test, _) = mnist.load_data()
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32') / 255
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1).astype('float32') / 255
# 생성자 모델을 만듭니다.
autoencoder = Sequential()
# 인코딩 부분입니다.
autoencoder.add(Conv2D(16, kernel_size=3, padding='same', input_shape=(28,28,1), activation='relu'))
autoencoder.add(MaxPooling2D(pool_size=2, padding='same'))
autoencoder.add(Conv2D(8, kernel_size=3, activation='relu', padding='same'))
autoencoder.add(MaxPooling2D(pool_size=2, padding='same'))
autoencoder.add(Conv2D(8, kernel_size=3, strides=2, padding='same', activation='relu'))
# 디코딩 부분이 이어집니다.
autoencoder.add(Conv2D(8, kernel_size=3, padding='same', activation='relu'))
autoencoder.add(UpSampling2D())
autoencoder.add(Conv2D(8, kernel_size=3, padding='same', activation='relu'))
autoencoder.add(UpSampling2D())
autoencoder.add(Conv2D(16, kernel_size=3, activation='relu'))
autoencoder.add(UpSampling2D())
autoencoder.add(Conv2D(1, kernel_size=3, padding='same', activation='sigmoid'))
# 전체 구조를 확인해 봅니다.
autoencoder.summary()
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D, Flatten, Reshape
import matplotlib.pyplot as plt
import numpy as np
# MNIST 데이터셋을 불러옵니다.
(X_train, _), (X_test, _) = mnist.load_data()
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32') / 255
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1).astype('float32') / 255
# 생성자 모델을 만듭니다.
autoencoder = Sequential()
# 인코딩 부분입니다.
autoencoder.add(Conv2D(16, kernel_size=3, padding='same', input_shape=(28,28,1), activation='relu'))
autoencoder.add(MaxPooling2D(pool_size=2, padding='same'))
autoencoder.add(Conv2D(8, kernel_size=3, activation='relu', padding='same'))
autoencoder.add(MaxPooling2D(pool_size=2, padding='same'))
autoencoder.add(Conv2D(8, kernel_size=3, strides=2, padding='same', activation='relu'))
# 디코딩 부분이 이어집니다.
autoencoder.add(Conv2D(8, kernel_size=3, padding='same', activation='relu'))
autoencoder.add(UpSampling2D())
autoencoder.add(Conv2D(8, kernel_size=3, padding='same', activation='relu'))
autoencoder.add(UpSampling2D())
autoencoder.add(Conv2D(16, kernel_size=3, activation='relu'))
autoencoder.add(UpSampling2D())
autoencoder.add(Conv2D(1, kernel_size=3, padding='same', activation='sigmoid'))
# 전체 구조를 확인해 봅니다.
autoencoder.summary()
Model: "sequential_4" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv2d_8 (Conv2D) (None, 28, 28, 16) 160 _________________________________________________________________ max_pooling2d (MaxPooling2D) (None, 14, 14, 16) 0 _________________________________________________________________ conv2d_9 (Conv2D) (None, 14, 14, 8) 1160 _________________________________________________________________ max_pooling2d_1 (MaxPooling2 (None, 7, 7, 8) 0 _________________________________________________________________ conv2d_10 (Conv2D) (None, 4, 4, 8) 584 _________________________________________________________________ conv2d_11 (Conv2D) (None, 4, 4, 8) 584 _________________________________________________________________ up_sampling2d_4 (UpSampling2 (None, 8, 8, 8) 0 _________________________________________________________________ conv2d_12 (Conv2D) (None, 8, 8, 8) 584 _________________________________________________________________ up_sampling2d_5 (UpSampling2 (None, 16, 16, 8) 0 _________________________________________________________________ conv2d_13 (Conv2D) (None, 14, 14, 16) 1168 _________________________________________________________________ up_sampling2d_6 (UpSampling2 (None, 28, 28, 16) 0 _________________________________________________________________ conv2d_14 (Conv2D) (None, 28, 28, 1) 145 ================================================================= Total params: 4,385 Trainable params: 4,385 Non-trainable params: 0 _________________________________________________________________
In [4]:
Copied!
# 컴파일 및 학습을 하는 부분입니다.
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
autoencoder.fit(X_train, X_train, epochs=50, batch_size=128, validation_data=(X_test, X_test))
# 학습된 결과를 출력하는 부분입니다.
random_test = np.random.randint(X_test.shape[0], size=5) # 테스트할 이미지를 랜덤하게 불러옵니다.
ae_imgs = autoencoder.predict(X_test) # 앞서 만든 오토인코더 모델에 집어 넣습니다.
plt.figure(figsize=(7, 2)) # 출력될 이미지의 크기를 정합니다.
for i, image_idx in enumerate(random_test): # 랜덤하게 뽑은 이미지를 차례로 나열합니다.
ax = plt.subplot(2, 7, i + 1)
plt.imshow(X_test[image_idx].reshape(28, 28)) # 테스트할 이미지를 먼저 그대로 보여줍니다.
ax.axis('off')
ax = plt.subplot(2, 7, 7 + i +1)
plt.imshow(ae_imgs[image_idx].reshape(28, 28)) # 오토인코딩 결과를 다음열에 출력합니다.
ax.axis('off')
plt.show()
# 컴파일 및 학습을 하는 부분입니다.
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
autoencoder.fit(X_train, X_train, epochs=50, batch_size=128, validation_data=(X_test, X_test))
# 학습된 결과를 출력하는 부분입니다.
random_test = np.random.randint(X_test.shape[0], size=5) # 테스트할 이미지를 랜덤하게 불러옵니다.
ae_imgs = autoencoder.predict(X_test) # 앞서 만든 오토인코더 모델에 집어 넣습니다.
plt.figure(figsize=(7, 2)) # 출력될 이미지의 크기를 정합니다.
for i, image_idx in enumerate(random_test): # 랜덤하게 뽑은 이미지를 차례로 나열합니다.
ax = plt.subplot(2, 7, i + 1)
plt.imshow(X_test[image_idx].reshape(28, 28)) # 테스트할 이미지를 먼저 그대로 보여줍니다.
ax.axis('off')
ax = plt.subplot(2, 7, 7 + i +1)
plt.imshow(ae_imgs[image_idx].reshape(28, 28)) # 오토인코딩 결과를 다음열에 출력합니다.
ax.axis('off')
plt.show()
Epoch 1/50 469/469 [==============================] - 4s 8ms/step - loss: 0.2041 - val_loss: 0.1329 Epoch 2/50 469/469 [==============================] - 3s 6ms/step - loss: 0.1245 - val_loss: 0.1169 Epoch 3/50 469/469 [==============================] - 3s 7ms/step - loss: 0.1133 - val_loss: 0.1088 Epoch 4/50 469/469 [==============================] - 3s 7ms/step - loss: 0.1073 - val_loss: 0.1038 Epoch 5/50 469/469 [==============================] - 3s 6ms/step - loss: 0.1034 - val_loss: 0.1005 Epoch 6/50 469/469 [==============================] - 3s 6ms/step - loss: 0.1005 - val_loss: 0.0982 Epoch 7/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0982 - val_loss: 0.0962 Epoch 8/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0964 - val_loss: 0.0943 Epoch 9/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0950 - val_loss: 0.0931 Epoch 10/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0937 - val_loss: 0.0933 Epoch 11/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0928 - val_loss: 0.0926 Epoch 12/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0919 - val_loss: 0.0903 Epoch 13/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0911 - val_loss: 0.0895 Epoch 14/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0904 - val_loss: 0.0889 Epoch 15/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0898 - val_loss: 0.0892 Epoch 16/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0893 - val_loss: 0.0884 Epoch 17/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0888 - val_loss: 0.0875 Epoch 18/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0884 - val_loss: 0.0874 Epoch 19/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0879 - val_loss: 0.0866 Epoch 20/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0875 - val_loss: 0.0863 Epoch 21/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0872 - val_loss: 0.0861 Epoch 22/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0869 - val_loss: 0.0856 Epoch 23/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0865 - val_loss: 0.0854 Epoch 24/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0863 - val_loss: 0.0852 Epoch 25/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0860 - val_loss: 0.0849 Epoch 26/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0858 - val_loss: 0.0850 Epoch 27/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0855 - val_loss: 0.0844 Epoch 28/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0853 - val_loss: 0.0845 Epoch 29/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0850 - val_loss: 0.0839 Epoch 30/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0849 - val_loss: 0.0838 Epoch 31/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0847 - val_loss: 0.0834 Epoch 32/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0845 - val_loss: 0.0835 Epoch 33/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0843 - val_loss: 0.0836 Epoch 34/50 469/469 [==============================] - 3s 6ms/step - loss: 0.0841 - val_loss: 0.0831 Epoch 35/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0840 - val_loss: 0.0832 Epoch 36/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0838 - val_loss: 0.0833 Epoch 37/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0837 - val_loss: 0.0827 Epoch 38/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0835 - val_loss: 0.0825 Epoch 39/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0834 - val_loss: 0.0825 Epoch 40/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0832 - val_loss: 0.0824 Epoch 41/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0831 - val_loss: 0.0821 Epoch 42/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0830 - val_loss: 0.0819 Epoch 43/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0829 - val_loss: 0.0817 Epoch 44/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0828 - val_loss: 0.0819 Epoch 45/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0827 - val_loss: 0.0816 Epoch 46/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0826 - val_loss: 0.0817 Epoch 47/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0824 - val_loss: 0.0814 Epoch 48/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0824 - val_loss: 0.0820 Epoch 49/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0822 - val_loss: 0.0816 Epoch 50/50 469/469 [==============================] - 3s 7ms/step - loss: 0.0822 - val_loss: 0.0813
In [ ]:
Copied!