版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_41185868/article/details/82960621
TF之pix2pix：基于TF利用Facades数据集训练pix2pix模型、测试并进行生成过程全记录
输出结果
1、训练
2、测试
训练代码运行过程全记录
开始训练
aspect_ratio = 1.0
batch_size = 1
beta1 = 0.5
checkpoint = None
display_freq = 0
flip = True
gan_weight = 1.0
input_dir = facades/train
l1_weight = 100.0
lab_colorization = False
lr = 0.0002
max_epochs = 200
max_steps = None
mode = train
ndf = 64
ngf = 64
output_dir = facades_train
output_filetype = png
progress_freq = 50
save_freq = 5000
scale_size = 286
seed = 407313043
summary_freq = 100
trace_freq = 0
which_direction = BtoA
2018-10-07 19:44:30.158758:
parameter_count = 57183616
progress epoch 1 step 50 image/sec 0.4 remaining 3618m
discrim_loss 0.60436237
gen_loss_GAN 0.35850993
gen_loss_L1 0.14340873
recording summary
progress epoch 1 step 100 image/sec 0.3 remaining 3951m
discrim_loss 0.7865979
gen_loss_GAN 0.68436635
gen_loss_L1 0.22767533
progress epoch 1 step 150 image/sec 0.3 remaining 3966m
discrim_loss 0.7580325
gen_loss_GAN 1.1571432
gen_loss_L1 0.2595716
recording summary
progress epoch 1 step 200 image/sec 0.3 remaining 4001m
discrim_loss 0.68745524
gen_loss_GAN 1.5107139
gen_loss_L1 0.29375646
progress epoch 1 step 250 image/sec 0.3 remaining 4006m
discrim_loss 0.6075255
gen_loss_GAN 1.8473383
gen_loss_L1 0.3171888
recording summary
progress epoch 1 step 300 image/sec 0.3 remaining 4037m
discrim_loss 0.5854379
gen_loss_GAN 2.027368
gen_loss_L1 0.32994485
progress epoch 1 step 350 image/sec 0.3 remaining 4009m
discrim_loss 0.5662487
gen_loss_GAN 2.1688633
gen_loss_L1 0.33538958
recording summary
progress epoch 1 step 400 image/sec 0.3 remaining 3983m
discrim_loss 0.5435342
gen_loss_GAN 2.2247393
gen_loss_L1 0.3391656
progress epoch 2 step 50 image/sec 0.3 remaining 3985m
discrim_loss 0.55237687
gen_loss_GAN 2.3303561
gen_loss_L1 0.34268096
recording summary
progress epoch 2 step 100 image/sec 0.3 remaining 3991m
discrim_loss 0.62108487
gen_loss_GAN 2.3037076
gen_loss_L1 0.34408635
progress epoch 2 step 150 image/sec 0.3 remaining 3988m
discrim_loss 0.62168205
gen_loss_GAN 2.3057084
gen_loss_L1 0.34629545
recording summary
progress epoch 2 step 200 image/sec 0.3 remaining 4032m
discrim_loss 0.59550333
gen_loss_GAN 2.3486025
gen_loss_L1 0.3454899
progress epoch 2 step 250 image/sec 0.3 remaining 4032m
discrim_loss 0.6070777
gen_loss_GAN 2.2781825
gen_loss_L1 0.34619838
recording summary
progress epoch 2 step 300 image/sec 0.3 remaining 4040m
discrim_loss 0.59475785
gen_loss_GAN 2.3086784
gen_loss_L1 0.34744877
progress epoch 2 step 350 image/sec 0.3 remaining 4041m
discrim_loss 0.58981085
gen_loss_GAN 2.3018146
gen_loss_L1 0.35565904
……
测试代码全记录
开始测试
loaded lab_colorization = False
loaded ndf = 64
loaded ngf = 64
loaded which_direction = BtoA
aspect_ratio = 1.0
batch_size = 1
beta1 = 0.5
checkpoint = facades_train
display_freq = 0
flip = False
gan_weight = 1.0
input_dir = facades/val
l1_weight = 100.0
lab_colorization = False
lr = 0.0002
max_epochs = None
max_steps = None
mode = test
ndf = 64
ngf = 64
output_dir = facades_test
output_filetype = png
progress_freq = 50
save_freq = 5000
scale_size = 256
seed = 651085994
summary_freq = 100
trace_freq = 0
which_direction = BtoA
examples count = 100
parameter_count = 57183616