mp2893 / medgan Goto Github PK
View Code? Open in Web Editor NEWGenerative adversarial network for generating electronic health records.
License: BSD 3-Clause "New" or "Revised" License
medgan's People
Contributors
Stargazers
Watchers
Forkers
codeaudit smrtslckr knowledgefold ashutoshaay26 wolfhu baowaly bombrake ajaytalati breitensteinlab callmerudy bbardakk ritik99 allhailzzq taigi didayolo skaryyep asdncg yanhuiguo playezio rosefun zchaizju gkovaig haitwang-cloud jianfeidahai afcarl ml-lab cltsao ruiatelsevier ssbpv shubhampachori12110095 amirunpri2018 jbdatascience shuizhilinxin astorfi straymat michaelsmurray bkmargetts hezhang1994 geekyneuro uctoronto seonchoe cdchushig soft-nougat qiulinzhang shekerkamma ggg5438 brucejunlee shivajid xfw ashish1208 jdchuv tonydeep pchoengtawee nikolaospapachristou tzebin sjolly3 hamsam lizhongliu1996 sethdkelly kavyareddykatipally prerit1998jain gordondoo visionlogic-ai ashiakerwang lulubeatson binfnstats csetraynor 5l1v3r1 blancavazquez weldonj habibmrad lorraineyuan ag-labs-sys poornima-sivanand vicjoy cynthia-wang7 judyxyang aanaseer jsungit ancewer adderbyte venseven woodpecker1111 venkataduvvuri jbarsotti elianebelisle bengissu fabacha bqfanmedgan's Issues
A few questions
Hello Ed,
Thanks for sharing this great work with us!
After having trouble accessing the EHR dataset, I was wondering if we can generate synthetic data and I read this paper.
I have a few questions though:
-
It seems to me sequential patient data is more usable for many tasks, have you try to generate this kind of data? (as you mentioned in future work), for example, treat each patient as a matrix, each row will be a visit.
-
Have you try to do some real world tasks on synthetic data? If yes, can we trust the result we got form the synthetic data?
Thanks!
Xianlong
Training Losses and optimal parameters
Hi,
Thank you so much for this excellent work!
I have trained a model using the script you provided but with a different data set. I got the following output :
Pretrain_Epoch:96, trainLoss:17.692522, validLoss:103.652969, validReverseLoss:0.000000
Pretrain_Epoch:97, trainLoss:17.549919, validLoss:104.221916, validReverseLoss:0.000000
Pretrain_Epoch:98, trainLoss:17.376888, validLoss:104.022125, validReverseLoss:0.000000
Pretrain_Epoch:99, trainLoss:17.238510, validLoss:104.839447, validReverseLoss:0.000000
Epoch:0, d_loss:0.436150, g_loss:3.820657, accuracy:1.000000, AUC:1.000000
Epoch:1, d_loss:0.005911, g_loss:3.363690, accuracy:1.000000, AUC:1.000000
Epoch:2, d_loss:0.007880, g_loss:1.667129, accuracy:0.999333, AUC:0.999994
Epoch:3, d_loss:0.031970, g_loss:0.164756, accuracy:0.999583, AUC:1.000000
Epoch:4, d_loss:0.010160, g_loss:0.155293, accuracy:1.000000, AUC:1.000000
Epoch:5, d_loss:0.004382, g_loss:0.106739, accuracy:0.999500, AUC:1.000000
Epoch:6, d_loss:0.005284, g_loss:0.098650, accuracy:0.999667, AUC:1.000000
Is this similar to your result? Is there any way to tweak the model to improve it?
I changed aked the _VALIDATION_RATIO = 0.2 to avoid some errors. This should not affect my results I guess.
The learning rate (for the optimizer) was not explicitly passed, what learning rate would you recommend?
What is recommended batch size/epochs and how does this change when the dimension of the data increases?
Thank you!
All generatorDims must be equal to embeddingDim?
Hello,
Because of the architecture of the generator (shortcut connections), I think that all the hidden layers must have the same size of the input, right?
Thank you.
MedGAN on PyTorch?
Apologies if this question does not belong in this repo, but this seems to be the only place where MedGAN is being discussed.
Does anyone know of any implementations of MedGAN for PyTorch? I am considering doing it myself but it will be quite a challenge.
Thank you.
How to use code on own dataset
Hello, I am really fascinated by your code. I was wondering how I could implement your network on my own dataset?
Dimensions of input data
Hi Edward,
I did not use the MIMIC-III dataset, but used my own data set of patients and their diagnosis codes. I constructed a binary matrix like process_mimic.py where each row is a patient and each column is an ICD9/ICD10 code as my input. I have 1,064 unique ICD9/ICD10 codes and looking at medgan.py it looks like you set the inputDim=615. Is this for the number of unique codes in data set A?
I adjusted "inputDim" to be 1064 in my case and the resulting Numpy array has dimensions (10000,186). I thought the resulting dimensions would be (10000,1064). Are there other adjustments I need to make to the model?
Thank you!
Restoring of trained model
Thank you very much for the great paper and for providing the source code!
I'm trying to train a very basic model which should generate a single binomial variable. After the training is done I'm getting the following error during data generation (after commenting 'train' part and uncommenting 'generate' part):
Tensor name "autoencoder/aee_b_0" not found in checkpoint files out_binomial/02_1_50000-999.index
I guess the reason is in these two lines
Line 202 in e082e21
Line 206 in e082e21
There should be something like this instead:
saver = tf.train.Saver()
saver.restore(sess, tf.train.latest_checkpoint(modelDir))
sess.run(tf.global_variables_initializer())
But the problem is that with lines above there is no errors but generated data doesn't satisfy the same binomial distribution as original one so maybe it should be fixed in some other way?
Thank you!
REGARDING DATA SOURCE
CAN U PROVIDE ME THE DATA SOURCE
Synthetic Image
Hi, Can we generate synthetic image data using GAN? If yes, could you please provide the steps.
Why the google records project has been archived? what if i Still want to contribute?
Why the google records project has been archived? what if i Still want to contribute?
Input / Output dimensions differ
I am trying to reconstruct the evaluation process. To check the dimension-wise probability, I need a sample size that is as big as the number of patients from the dataset and generate a vector as input for my plot, if I understood correctly. The problem is, that my generated patients have a length of 906 each, whereas my input data has a length of 1071 each.
I determined the size of the vector for the generated patients by the shape of the numpy array that I receive as output.
I also compared the types dict size with the number of unique ICD9 codes (both 6985), so this does not seem to be the reason for losing dimensions.
If I switch from 3 digits to 5 digits, the dimensions stay the same size, shouldn't they go up to 6985?
Any tips on how to fix this?
One more question: in your paper you plot 615 codes, where does this number derive from?
Discrete data with both count and binary features
Congratulations on your excellent work!
I was wondering how can I implement medGAN when my data contains both count and binary features?
Thank you!
Generating different features
Hello,
If we generate data with two types of features let's say age and diagnosis code. Could we use directly data_type = "count" hence getting the number of times a person has been diagnosed with that problem and their age?
Otherwise for binary you mentioned that you need to modify the activation functions. For example if we use age and diagnosis code and the last feature is the age. Is it enough to use ReLu for the count variable and sigmoid for the binary variables? What about the Tanh, should I modify them too?
Thanks in advance.
Other fields in data generation
Hi Edward,
Thanks for the code, it really helps in understanding the paper better.
Currently your python code generates patient id and ICD9 diagnosis codes.
I wanted to know what changes or modifications do I have to do in your Process_mimic and medGAN code if I need to generate synthetic data to incorporate fields such as Age,gender,Procedures etc.?
Do I have to include the desired fields in process_mimic file only or do I need to make changes to medGAN.py also?
Secondly, the data that would be generated (i.e. pid, icd9, age,gender, procedures) will take into consideration impact of other variables or will it solely be dependent on the Patient id?
Thanks
Variable Misnomer outlayer of Generator
Hi guys, I think there's an issue in the output layer of the generator on line 99. I believe it is a variable misnomer from the execution graph (I hope I am wrong)
I think it should be
W = tf.get_variable('W_'+str(i), shape=[tempDim, self.generatorDims[-1]])
instead of
W = tf.get_variable('W'+str(i), shape=[tempDim, self.generatorDims[-1]])
How to interpret the samples?
Hi Ed,
thank you very much for adding the process_mimic.py script :)
It all worked fairly painlessly, following your clear instructions (I used "counts") - and now I'm the very proud owner of 10000 synthetic EHR's - woohoo !!!
So I loaded samples, but I'm not sure how to interpret them?
>>> import numpy as np
>>> X = np.load('/home/ajay/PythonProjects/medgan-master/samples/samples.npy')
>>> X
array([[ 0.42479137, 0.38992843, 0.3843686 , ..., 0.48570082,
0.44278869, 0.4656629 ],
[ 0.28643027, 0.45749718, 0.23394403, ..., 0.47090551,
0.41072363, 0.43643555],
[ 0.29359645, 0.46955556, 0.22549649, ..., 0.48150307,
0.41780272, 0.45492986],
...,
[ 0.56480783, 0.66771448, 0.54325938, ..., 0.47483209,
0.43128845, 0.45304856],
[ 0.68514657, 0.79574692, 0.73424697, ..., 0.47857872,
0.43853614, 0.44970644],
[ 0.17376943, 0.19806506, 0.27509841, ..., 0.47925362,
0.44123808, 0.46058744]], dtype=float32)
>>> X.shape
(10000, 1071)
>>> synthetic_ehr = X[0,:]
>>> synthetic_ehr
array([ 0.42479137, 0.38992843, 0.3843686 , ..., 0.48570082,
0.44278869, 0.4656629 ], dtype=float32)
I just realized I'm not sure what synthetic_ehr is? Does it look right to you?
I thought it would be like a row of a table where the columns are the 1071 ICD-9 codes, and the counts are the number of times those entities appear in the patients ehr? So the counts should be whole numbers, and would give some idea of co-morbidities? For example, cardiovascular and metabolic disorders would frequently co-occur?
So would one way of analysis be a correlation matrix?
Thanks very much 👍
Trained Model
Hello,
Is it possible to provide a trained model?
Best Regards
Error with numpy 1.16.3
Hi Edward,
First of all, congrats on your excellent work!
My current numpy version is 1.16.3. After process_mimic.py, I was running medgan.py and I received the following error:
python medgan.py test1.matrix test2 --data_type="count"
Traceback (most recent call last):
File "medgan.py", line 376, in <module>
data = np.load(args.data_file)
File "C:\Users\myusername\AppData\Local\Continuum\anaconda3\lib\site-packages\numpy\lib\npyio.py", line 451, in load
raise ValueError("Cannot load file containing pickled data "
ValueError: Cannot load file containing pickled data when allow_pickle=False
There seems to be two solutions:
- downgrading numpy to 1.16.2
- or adding
allow_pickle=Trueas an argument innp.load()
I tried solution 2) and it works. In numpy 1.16.3, the default value is allow_pickle=False.
Best,
Sylvain
outputs-0.data-00000-of-00001: DATA_LOSS: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
Hello, I have used the MIMIC data set, after training, I wanted to generate data but get the following Error: outputs-0.data-00000-of-00001: DATA_LOSS: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
can anyone help?
Best,
Navid
keep_prob always 1.0?
Hello,
Why is keep_prob always 1.0?
Does that mean that the dropout in the discriminator is always disabled?
Thank you.
Distribution of ICD Codes for generated patients
Hello,
after generating 10.000 patients I ran into two problems and I hope somebody can help with them:
- I checked the diagnoses and the most occurrences of appear for:
- D_01 (Cholera, 3612 times )
- D_72 (Mumps, 3089 times)
- D_76 (Incision Of Facial Bone Without Division, 2691 times)
Also the code D_1 appears which should be the same as D_01 if I'm correct.
This data seems quite random, do I maybe need to alter the hyperparameters or did I do something wrong with the training?
I am using the MIMIC-III dataset and followed the guide from the README, I used checkpoint -999 for generating the data.
- The ICD codes of the generated data just have three digits, although I uncommented the section from process_mimic.py (line 66 uncommented, 67 commented)
Here's my training log:
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:249: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:54: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:59: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:81: The name tf.log is deprecated. Please use tf.math.log instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:144: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:259: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:264: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:264: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:266: The name tf.train.AdamOptimizer is deprecated. Please use tf.compat.v1.train.AdamOptimizer instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:271: The name tf.global_variables_initializer is deprecated. Please use tf.compat.v1.global_variables_initializer instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:274: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.
WARNING:tensorflow:From /content/drive/My Drive/medGAN/medgan.py:277: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.
2019-11-21 14:38:40.946110: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2019-11-21 14:38:40.962195: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:40.963126: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: Tesla P100-PCIE-16GB major: 6 minor: 0 memoryClockRate(GHz): 1.3285
pciBusID: 0000:00:04.0
2019-11-21 14:38:40.966593: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1
2019-11-21 14:38:40.978076: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10
2019-11-21 14:38:40.985276: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10
2019-11-21 14:38:40.994541: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10
2019-11-21 14:38:41.010746: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10
2019-11-21 14:38:41.016653: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10
2019-11-21 14:38:41.043468: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2019-11-21 14:38:41.043668: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.044661: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.045570: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-11-21 14:38:41.051360: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2300000000 Hz
2019-11-21 14:38:41.051637: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1e01640 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2019-11-21 14:38:41.051672: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2019-11-21 14:38:41.142245: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.143277: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1e01d40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2019-11-21 14:38:41.143307: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Tesla P100-PCIE-16GB, Compute Capability 6.0
2019-11-21 14:38:41.143511: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.144279: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: Tesla P100-PCIE-16GB major: 6 minor: 0 memoryClockRate(GHz): 1.3285
pciBusID: 0000:00:04.0
2019-11-21 14:38:41.144353: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1
2019-11-21 14:38:41.144390: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10
2019-11-21 14:38:41.144418: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10
2019-11-21 14:38:41.144476: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10
2019-11-21 14:38:41.144511: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10
2019-11-21 14:38:41.144535: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10
2019-11-21 14:38:41.144560: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2019-11-21 14:38:41.144684: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.145608: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.146383: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-11-21 14:38:41.146461: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1
2019-11-21 14:38:41.147990: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-11-21 14:38:41.148016: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2019-11-21 14:38:41.148029: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2019-11-21 14:38:41.148157: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.149070: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-21 14:38:41.149855: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2019-11-21 14:38:41.149946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 15216 MB memory) -> physical GPU (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0)
2019-11-21 14:38:41.968358: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10
Pretrain_Epoch:0, trainLoss:91.632156, validLoss:49.859711, validReverseLoss:0.000000
Pretrain_Epoch:1, trainLoss:44.162811, validLoss:38.908810, validReverseLoss:0.000000
Pretrain_Epoch:2, trainLoss:36.714924, validLoss:33.333466, validReverseLoss:0.000000
Pretrain_Epoch:3, trainLoss:31.041992, validLoss:27.854301, validReverseLoss:0.000000
Pretrain_Epoch:4, trainLoss:25.633547, validLoss:22.974136, validReverseLoss:0.000000
Pretrain_Epoch:5, trainLoss:21.065298, validLoss:19.111172, validReverseLoss:0.000000
Pretrain_Epoch:6, trainLoss:17.603550, validLoss:16.332701, validReverseLoss:0.000000
Pretrain_Epoch:7, trainLoss:15.103946, validLoss:14.306634, validReverseLoss:0.000000
Pretrain_Epoch:8, trainLoss:13.297533, validLoss:12.856835, validReverseLoss:0.000000
Pretrain_Epoch:9, trainLoss:11.967052, validLoss:11.843672, validReverseLoss:0.000000
Pretrain_Epoch:10, trainLoss:10.958341, validLoss:11.032762, validReverseLoss:0.000000
Pretrain_Epoch:11, trainLoss:10.180580, validLoss:10.419333, validReverseLoss:0.000000
Pretrain_Epoch:12, trainLoss:9.582338, validLoss:9.962563, validReverseLoss:0.000000
Pretrain_Epoch:13, trainLoss:9.112109, validLoss:9.583471, validReverseLoss:0.000000
Pretrain_Epoch:14, trainLoss:8.746560, validLoss:9.310450, validReverseLoss:0.000000
Pretrain_Epoch:15, trainLoss:8.461577, validLoss:9.054235, validReverseLoss:0.000000
Pretrain_Epoch:16, trainLoss:8.224661, validLoss:8.902073, validReverseLoss:0.000000
Pretrain_Epoch:17, trainLoss:8.023074, validLoss:8.790389, validReverseLoss:0.000000
Pretrain_Epoch:18, trainLoss:7.845893, validLoss:8.618320, validReverseLoss:0.000000
Pretrain_Epoch:19, trainLoss:7.707201, validLoss:8.549589, validReverseLoss:0.000000
Pretrain_Epoch:20, trainLoss:7.581052, validLoss:8.441903, validReverseLoss:0.000000
Pretrain_Epoch:21, trainLoss:7.483572, validLoss:8.352224, validReverseLoss:0.000000
Pretrain_Epoch:22, trainLoss:7.401034, validLoss:8.320681, validReverseLoss:0.000000
Pretrain_Epoch:23, trainLoss:7.330626, validLoss:8.256131, validReverseLoss:0.000000
Pretrain_Epoch:24, trainLoss:7.265032, validLoss:8.222884, validReverseLoss:0.000000
Pretrain_Epoch:25, trainLoss:7.214301, validLoss:8.217128, validReverseLoss:0.000000
Pretrain_Epoch:26, trainLoss:7.167799, validLoss:8.175730, validReverseLoss:0.000000
Pretrain_Epoch:27, trainLoss:7.124703, validLoss:8.146324, validReverseLoss:0.000000
Pretrain_Epoch:28, trainLoss:7.092945, validLoss:8.140231, validReverseLoss:0.000000
Pretrain_Epoch:29, trainLoss:7.054426, validLoss:8.122950, validReverseLoss:0.000000
Pretrain_Epoch:30, trainLoss:7.022406, validLoss:8.084413, validReverseLoss:0.000000
Pretrain_Epoch:31, trainLoss:7.000129, validLoss:8.087962, validReverseLoss:0.000000
Pretrain_Epoch:32, trainLoss:6.972916, validLoss:8.076344, validReverseLoss:0.000000
Pretrain_Epoch:33, trainLoss:6.951451, validLoss:8.016294, validReverseLoss:0.000000
Pretrain_Epoch:34, trainLoss:6.929442, validLoss:8.047412, validReverseLoss:0.000000
Pretrain_Epoch:35, trainLoss:6.909639, validLoss:8.004986, validReverseLoss:0.000000
Pretrain_Epoch:36, trainLoss:6.890303, validLoss:8.034472, validReverseLoss:0.000000
Pretrain_Epoch:37, trainLoss:6.873143, validLoss:8.023901, validReverseLoss:0.000000
Pretrain_Epoch:38, trainLoss:6.859607, validLoss:8.012761, validReverseLoss:0.000000
Pretrain_Epoch:39, trainLoss:6.844871, validLoss:7.967826, validReverseLoss:0.000000
Pretrain_Epoch:40, trainLoss:6.833282, validLoss:7.992737, validReverseLoss:0.000000
Pretrain_Epoch:41, trainLoss:6.814266, validLoss:7.972634, validReverseLoss:0.000000
Pretrain_Epoch:42, trainLoss:6.806368, validLoss:7.954660, validReverseLoss:0.000000
Pretrain_Epoch:43, trainLoss:6.795738, validLoss:7.969618, validReverseLoss:0.000000
Pretrain_Epoch:44, trainLoss:6.782229, validLoss:7.936687, validReverseLoss:0.000000
Pretrain_Epoch:45, trainLoss:6.770532, validLoss:7.937439, validReverseLoss:0.000000
Pretrain_Epoch:46, trainLoss:6.761350, validLoss:7.902309, validReverseLoss:0.000000
Pretrain_Epoch:47, trainLoss:6.751661, validLoss:7.930335, validReverseLoss:0.000000
Pretrain_Epoch:48, trainLoss:6.733834, validLoss:7.932473, validReverseLoss:0.000000
Pretrain_Epoch:49, trainLoss:6.720202, validLoss:7.928168, validReverseLoss:0.000000
Pretrain_Epoch:50, trainLoss:6.706732, validLoss:7.901009, validReverseLoss:0.000000
Pretrain_Epoch:51, trainLoss:6.686815, validLoss:7.904763, validReverseLoss:0.000000
Pretrain_Epoch:52, trainLoss:6.671935, validLoss:7.884416, validReverseLoss:0.000000
Pretrain_Epoch:53, trainLoss:6.656465, validLoss:7.874551, validReverseLoss:0.000000
Pretrain_Epoch:54, trainLoss:6.644230, validLoss:7.862403, validReverseLoss:0.000000
Pretrain_Epoch:55, trainLoss:6.633656, validLoss:7.845164, validReverseLoss:0.000000
Pretrain_Epoch:56, trainLoss:6.621819, validLoss:7.847596, validReverseLoss:0.000000
Pretrain_Epoch:57, trainLoss:6.614031, validLoss:7.796778, validReverseLoss:0.000000
Pretrain_Epoch:58, trainLoss:6.607875, validLoss:7.855163, validReverseLoss:0.000000
Pretrain_Epoch:59, trainLoss:6.595439, validLoss:7.801251, validReverseLoss:0.000000
Pretrain_Epoch:60, trainLoss:6.588428, validLoss:7.840598, validReverseLoss:0.000000
Pretrain_Epoch:61, trainLoss:6.586468, validLoss:7.814472, validReverseLoss:0.000000
Pretrain_Epoch:62, trainLoss:6.574622, validLoss:7.822409, validReverseLoss:0.000000
Pretrain_Epoch:63, trainLoss:6.568933, validLoss:7.769971, validReverseLoss:0.000000
Pretrain_Epoch:64, trainLoss:6.555827, validLoss:7.775706, validReverseLoss:0.000000
Pretrain_Epoch:65, trainLoss:6.543493, validLoss:7.786043, validReverseLoss:0.000000
Pretrain_Epoch:66, trainLoss:6.532283, validLoss:7.795273, validReverseLoss:0.000000
Pretrain_Epoch:67, trainLoss:6.526275, validLoss:7.776935, validReverseLoss:0.000000
Pretrain_Epoch:68, trainLoss:6.508321, validLoss:7.743046, validReverseLoss:0.000000
Pretrain_Epoch:69, trainLoss:6.500664, validLoss:7.750890, validReverseLoss:0.000000
Pretrain_Epoch:70, trainLoss:6.483753, validLoss:7.734784, validReverseLoss:0.000000
Pretrain_Epoch:71, trainLoss:6.481430, validLoss:7.731408, validReverseLoss:0.000000
Pretrain_Epoch:72, trainLoss:6.470397, validLoss:7.726825, validReverseLoss:0.000000
Pretrain_Epoch:73, trainLoss:6.464901, validLoss:7.711414, validReverseLoss:0.000000
Pretrain_Epoch:74, trainLoss:6.453043, validLoss:7.717400, validReverseLoss:0.000000
Pretrain_Epoch:75, trainLoss:6.451079, validLoss:7.713556, validReverseLoss:0.000000
Pretrain_Epoch:76, trainLoss:6.444433, validLoss:7.702054, validReverseLoss:0.000000
Pretrain_Epoch:77, trainLoss:6.439002, validLoss:7.704195, validReverseLoss:0.000000
Pretrain_Epoch:78, trainLoss:6.433498, validLoss:7.729032, validReverseLoss:0.000000
Pretrain_Epoch:79, trainLoss:6.430214, validLoss:7.669126, validReverseLoss:0.000000
Pretrain_Epoch:80, trainLoss:6.423391, validLoss:7.670120, validReverseLoss:0.000000
Pretrain_Epoch:81, trainLoss:6.419544, validLoss:7.695985, validReverseLoss:0.000000
Pretrain_Epoch:82, trainLoss:6.417687, validLoss:7.706051, validReverseLoss:0.000000
Pretrain_Epoch:83, trainLoss:6.414234, validLoss:7.694446, validReverseLoss:0.000000
Pretrain_Epoch:84, trainLoss:6.409822, validLoss:7.685117, validReverseLoss:0.000000
Pretrain_Epoch:85, trainLoss:6.404850, validLoss:7.709420, validReverseLoss:0.000000
Pretrain_Epoch:86, trainLoss:6.403021, validLoss:7.703742, validReverseLoss:0.000000
Pretrain_Epoch:87, trainLoss:6.400425, validLoss:7.689323, validReverseLoss:0.000000
Pretrain_Epoch:88, trainLoss:6.393787, validLoss:7.684198, validReverseLoss:0.000000
Pretrain_Epoch:89, trainLoss:6.391764, validLoss:7.695581, validReverseLoss:0.000000
Pretrain_Epoch:90, trainLoss:6.387015, validLoss:7.688169, validReverseLoss:0.000000
Pretrain_Epoch:91, trainLoss:6.382489, validLoss:7.684075, validReverseLoss:0.000000
Pretrain_Epoch:92, trainLoss:6.383763, validLoss:7.685220, validReverseLoss:0.000000
Pretrain_Epoch:93, trainLoss:6.379379, validLoss:7.658064, validReverseLoss:0.000000
Pretrain_Epoch:94, trainLoss:6.379478, validLoss:7.701941, validReverseLoss:0.000000
Pretrain_Epoch:95, trainLoss:6.371755, validLoss:7.676590, validReverseLoss:0.000000
Pretrain_Epoch:96, trainLoss:6.371538, validLoss:7.701460, validReverseLoss:0.000000
Pretrain_Epoch:97, trainLoss:6.366984, validLoss:7.660957, validReverseLoss:0.000000
Pretrain_Epoch:98, trainLoss:6.368827, validLoss:7.656891, validReverseLoss:0.000000
Pretrain_Epoch:99, trainLoss:6.362263, validLoss:7.688737, validReverseLoss:0.000000
2019-11-21 14:40:21.567047: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
Epoch:0, d_loss:0.049718, g_loss:7.896662, accuracy:1.000000, AUC:1.000000
Epoch:1, d_loss:0.001711, g_loss:0.247020, accuracy:1.000000, AUC:1.000000
Epoch:2, d_loss:0.001532, g_loss:0.386267, accuracy:1.000000, AUC:1.000000
Epoch:3, d_loss:0.001439, g_loss:1.053180, accuracy:1.000000, AUC:1.000000
Epoch:4, d_loss:0.001324, g_loss:1.365029, accuracy:1.000000, AUC:1.000000
Epoch:5, d_loss:0.001201, g_loss:1.210130, accuracy:1.000000, AUC:1.000000
Epoch:6, d_loss:0.001051, g_loss:0.262837, accuracy:1.000000, AUC:1.000000
Epoch:7, d_loss:0.001092, g_loss:0.137890, accuracy:1.000000, AUC:1.000000
Epoch:8, d_loss:0.001030, g_loss:0.082081, accuracy:1.000000, AUC:1.000000
Epoch:9, d_loss:0.001196, g_loss:0.063162, accuracy:1.000000, AUC:1.000000
Epoch:10, d_loss:0.001634, g_loss:0.040523, accuracy:1.000000, AUC:1.000000
Epoch:11, d_loss:0.002393, g_loss:0.016229, accuracy:1.000000, AUC:1.000000
Epoch:12, d_loss:0.003662, g_loss:0.010670, accuracy:0.999929, AUC:1.000000
Epoch:13, d_loss:0.004564, g_loss:0.006378, accuracy:1.000000, AUC:1.000000
Epoch:14, d_loss:0.277425, g_loss:0.071394, accuracy:0.950393, AUC:0.983442
Epoch:15, d_loss:0.164884, g_loss:8.783463, accuracy:0.997810, AUC:0.999962
Epoch:16, d_loss:0.001950, g_loss:0.846287, accuracy:1.000000, AUC:1.000000
Epoch:17, d_loss:0.000658, g_loss:0.279623, accuracy:1.000000, AUC:1.000000
Epoch:18, d_loss:0.000843, g_loss:1.432047, accuracy:1.000000, AUC:1.000000
Epoch:19, d_loss:0.001847, g_loss:2.704693, accuracy:1.000000, AUC:1.000000
Epoch:20, d_loss:0.002777, g_loss:1.460213, accuracy:1.000000, AUC:1.000000
Epoch:21, d_loss:0.001460, g_loss:0.216559, accuracy:1.000000, AUC:1.000000
Epoch:22, d_loss:0.001971, g_loss:0.923061, accuracy:1.000000, AUC:1.000000
Epoch:23, d_loss:0.000861, g_loss:0.489755, accuracy:1.000000, AUC:1.000000
Epoch:24, d_loss:0.001161, g_loss:0.493051, accuracy:1.000000, AUC:1.000000
Epoch:25, d_loss:0.003009, g_loss:0.438455, accuracy:0.999833, AUC:1.000000
Epoch:26, d_loss:0.090678, g_loss:10.045500, accuracy:0.999690, AUC:1.000000
Epoch:27, d_loss:0.017689, g_loss:23.799906, accuracy:0.993952, AUC:0.999743
Epoch:28, d_loss:0.027158, g_loss:9.959446, accuracy:0.998774, AUC:0.999972
Epoch:29, d_loss:0.012947, g_loss:2.434124, accuracy:0.997643, AUC:0.999999
Epoch:30, d_loss:0.012352, g_loss:6.465405, accuracy:0.999726, AUC:0.999998
Epoch:31, d_loss:0.003908, g_loss:5.487545, accuracy:0.999940, AUC:1.000000
Epoch:32, d_loss:0.003172, g_loss:4.503617, accuracy:0.999631, AUC:1.000000
Epoch:33, d_loss:0.003661, g_loss:0.963288, accuracy:0.999929, AUC:1.000000
Epoch:34, d_loss:0.003996, g_loss:1.319031, accuracy:0.999476, AUC:1.000000
Epoch:35, d_loss:0.007080, g_loss:2.475548, accuracy:0.999762, AUC:1.000000
Epoch:36, d_loss:0.004227, g_loss:1.138083, accuracy:0.999988, AUC:1.000000
Epoch:37, d_loss:0.007417, g_loss:1.839218, accuracy:0.998976, AUC:1.000000
Epoch:38, d_loss:0.003696, g_loss:4.418096, accuracy:0.999881, AUC:1.000000
Epoch:39, d_loss:0.001041, g_loss:0.143046, accuracy:1.000000, AUC:1.000000
Epoch:40, d_loss:0.001035, g_loss:0.135447, accuracy:1.000000, AUC:1.000000
Epoch:41, d_loss:0.001491, g_loss:0.383494, accuracy:1.000000, AUC:1.000000
Epoch:42, d_loss:0.008228, g_loss:1.176462, accuracy:0.999226, AUC:0.999994
Epoch:43, d_loss:0.043005, g_loss:13.346050, accuracy:0.997869, AUC:0.999942
Epoch:44, d_loss:0.004486, g_loss:3.507468, accuracy:0.999512, AUC:1.000000
Epoch:45, d_loss:0.001725, g_loss:1.486231, accuracy:0.999571, AUC:1.000000
Epoch:46, d_loss:0.002282, g_loss:2.032250, accuracy:0.999524, AUC:0.999997
Epoch:47, d_loss:0.007465, g_loss:2.521219, accuracy:0.999357, AUC:1.000000
Epoch:48, d_loss:0.002913, g_loss:0.684709, accuracy:0.999964, AUC:1.000000
Epoch:49, d_loss:0.002961, g_loss:2.294880, accuracy:1.000000, AUC:1.000000
Epoch:50, d_loss:0.012542, g_loss:5.384086, accuracy:0.992179, AUC:0.999960
Epoch:51, d_loss:0.020586, g_loss:7.530181, accuracy:0.997667, AUC:0.999997
Epoch:52, d_loss:0.011325, g_loss:8.783360, accuracy:0.999786, AUC:1.000000
Epoch:53, d_loss:0.002088, g_loss:10.770844, accuracy:1.000000, AUC:1.000000
Epoch:54, d_loss:0.003013, g_loss:7.846245, accuracy:0.999714, AUC:0.999999
Epoch:55, d_loss:0.005933, g_loss:7.644459, accuracy:0.999905, AUC:1.000000
Epoch:56, d_loss:0.016897, g_loss:7.131822, accuracy:0.998881, AUC:0.999885
Epoch:57, d_loss:0.011657, g_loss:7.725665, accuracy:0.998774, AUC:0.999984
Epoch:58, d_loss:0.087327, g_loss:12.562397, accuracy:0.994238, AUC:0.999784
Epoch:59, d_loss:0.012797, g_loss:6.789739, accuracy:0.999155, AUC:0.999998
Epoch:60, d_loss:0.020635, g_loss:11.726823, accuracy:0.998357, AUC:0.999961
Epoch:61, d_loss:0.047137, g_loss:9.821184, accuracy:0.998214, AUC:0.999917
Epoch:62, d_loss:0.006660, g_loss:24.679989, accuracy:0.999702, AUC:1.000000
Epoch:63, d_loss:0.000119, g_loss:27.558016, accuracy:0.999881, AUC:1.000000
Epoch:64, d_loss:0.029063, g_loss:17.092463, accuracy:0.990762, AUC:0.997367
Epoch:65, d_loss:0.012097, g_loss:7.847376, accuracy:0.999536, AUC:1.000000
Epoch:66, d_loss:0.006709, g_loss:8.065302, accuracy:0.999429, AUC:1.000000
Epoch:67, d_loss:0.004122, g_loss:8.441065, accuracy:0.999988, AUC:1.000000
Epoch:68, d_loss:0.004637, g_loss:8.012487, accuracy:0.999762, AUC:1.000000
Epoch:69, d_loss:0.009491, g_loss:4.167251, accuracy:0.997381, AUC:0.999948
Epoch:70, d_loss:0.029092, g_loss:9.354600, accuracy:0.995857, AUC:0.999584
Epoch:71, d_loss:0.007381, g_loss:10.639298, accuracy:0.999714, AUC:1.000000
Epoch:72, d_loss:0.001799, g_loss:10.262123, accuracy:0.999940, AUC:1.000000
Epoch:73, d_loss:0.003625, g_loss:8.179542, accuracy:0.999536, AUC:1.000000
Epoch:74, d_loss:0.047728, g_loss:8.024260, accuracy:0.995798, AUC:0.999314
Epoch:75, d_loss:0.035380, g_loss:8.866292, accuracy:0.992810, AUC:0.999262
Epoch:76, d_loss:0.025499, g_loss:11.169952, accuracy:0.997012, AUC:0.999806
Epoch:77, d_loss:0.016608, g_loss:12.074912, accuracy:0.998024, AUC:0.999950
Epoch:78, d_loss:0.008359, g_loss:8.134660, accuracy:0.999929, AUC:1.000000
Epoch:79, d_loss:0.006145, g_loss:6.563352, accuracy:0.999488, AUC:0.999995
Epoch:80, d_loss:0.017890, g_loss:8.531808, accuracy:0.999095, AUC:0.999996
Epoch:81, d_loss:0.042272, g_loss:8.016152, accuracy:0.943881, AUC:0.997913
Epoch:82, d_loss:0.082864, g_loss:9.334076, accuracy:0.978786, AUC:0.996849
Epoch:83, d_loss:0.047900, g_loss:8.168279, accuracy:0.995488, AUC:0.998971
Epoch:84, d_loss:0.033266, g_loss:7.451588, accuracy:0.992190, AUC:0.999139
Epoch:85, d_loss:0.049577, g_loss:9.729424, accuracy:0.988476, AUC:0.999166
Epoch:86, d_loss:0.040682, g_loss:7.009021, accuracy:0.982679, AUC:0.999054
Epoch:87, d_loss:0.016207, g_loss:8.466186, accuracy:0.998274, AUC:0.999874
Epoch:88, d_loss:0.026103, g_loss:6.965075, accuracy:0.993226, AUC:0.999492
Epoch:89, d_loss:0.028044, g_loss:7.550342, accuracy:0.990095, AUC:0.999086
Epoch:90, d_loss:0.041404, g_loss:8.490033, accuracy:0.996333, AUC:0.999494
Epoch:91, d_loss:0.074535, g_loss:7.640459, accuracy:0.984786, AUC:0.998377
Epoch:92, d_loss:0.046804, g_loss:7.516972, accuracy:0.983905, AUC:0.998299
Epoch:93, d_loss:0.040718, g_loss:8.299964, accuracy:0.996393, AUC:0.999604
Epoch:94, d_loss:0.021298, g_loss:8.631792, accuracy:0.997869, AUC:0.999982
Epoch:95, d_loss:0.030025, g_loss:7.165719, accuracy:0.988655, AUC:0.999097
Epoch:96, d_loss:0.034444, g_loss:8.996050, accuracy:0.994976, AUC:0.999677
Epoch:97, d_loss:0.050180, g_loss:8.664614, accuracy:0.980321, AUC:0.998731
Epoch:98, d_loss:0.043007, g_loss:7.613390, accuracy:0.998107, AUC:0.999879
Epoch:99, d_loss:0.130581, g_loss:8.378064, accuracy:0.988464, AUC:0.998806
Epoch:100, d_loss:0.065312, g_loss:6.865179, accuracy:0.947714, AUC:0.997700
Epoch:101, d_loss:0.087800, g_loss:7.412004, accuracy:0.983000, AUC:0.998844
Epoch:102, d_loss:0.075549, g_loss:6.937455, accuracy:0.991667, AUC:0.999086
Epoch:103, d_loss:0.095052, g_loss:8.943425, accuracy:0.990095, AUC:0.999608
Epoch:104, d_loss:0.077673, g_loss:7.374744, accuracy:0.985833, AUC:0.996747
Epoch:105, d_loss:0.078252, g_loss:7.267321, accuracy:0.977107, AUC:0.996420
Epoch:106, d_loss:0.098872, g_loss:7.478019, accuracy:0.971393, AUC:0.996551
Epoch:107, d_loss:0.098120, g_loss:7.629163, accuracy:0.991012, AUC:0.998549
Epoch:108, d_loss:0.064481, g_loss:7.509043, accuracy:0.983167, AUC:0.996103
Epoch:109, d_loss:0.073878, g_loss:7.365418, accuracy:0.987226, AUC:0.997516
Epoch:110, d_loss:0.132010, g_loss:8.815269, accuracy:0.901226, AUC:0.993680
Epoch:111, d_loss:0.150023, g_loss:8.366915, accuracy:0.973667, AUC:0.994767
Epoch:112, d_loss:0.112788, g_loss:6.927614, accuracy:0.954452, AUC:0.993850
Epoch:113, d_loss:0.111835, g_loss:6.637422, accuracy:0.980083, AUC:0.995868
Epoch:114, d_loss:0.086097, g_loss:7.312734, accuracy:0.980714, AUC:0.996576
Epoch:115, d_loss:0.123149, g_loss:7.737255, accuracy:0.956298, AUC:0.992462
Epoch:116, d_loss:0.072535, g_loss:7.898670, accuracy:0.981119, AUC:0.996105
Epoch:117, d_loss:0.095736, g_loss:6.707363, accuracy:0.970583, AUC:0.994001
Epoch:118, d_loss:0.071433, g_loss:7.549909, accuracy:0.974417, AUC:0.993336
Epoch:119, d_loss:0.069308, g_loss:7.246675, accuracy:0.904250, AUC:0.995185
Epoch:120, d_loss:0.052142, g_loss:8.211670, accuracy:0.981238, AUC:0.997481
Epoch:121, d_loss:0.077712, g_loss:8.492375, accuracy:0.969560, AUC:0.998048
Epoch:122, d_loss:0.072892, g_loss:7.892231, accuracy:0.954262, AUC:0.996144
Epoch:123, d_loss:0.104401, g_loss:7.407002, accuracy:0.978548, AUC:0.995371
Epoch:124, d_loss:0.108907, g_loss:7.377442, accuracy:0.928619, AUC:0.992313
Epoch:125, d_loss:0.073378, g_loss:7.683291, accuracy:0.945238, AUC:0.994081
Epoch:126, d_loss:0.086222, g_loss:7.942225, accuracy:0.973250, AUC:0.995601
Epoch:127, d_loss:0.047094, g_loss:7.016489, accuracy:0.908060, AUC:0.995998
Epoch:128, d_loss:0.051372, g_loss:7.886880, accuracy:0.979429, AUC:0.994895
Epoch:129, d_loss:0.050422, g_loss:7.383032, accuracy:0.957190, AUC:0.992285
Epoch:130, d_loss:0.064995, g_loss:6.914652, accuracy:0.974869, AUC:0.998442
Epoch:131, d_loss:0.056859, g_loss:7.607286, accuracy:0.988143, AUC:0.998289
Epoch:132, d_loss:0.072353, g_loss:7.519107, accuracy:0.963702, AUC:0.995913
Epoch:133, d_loss:0.083625, g_loss:7.308177, accuracy:0.959179, AUC:0.990884
Epoch:134, d_loss:0.080228, g_loss:7.099856, accuracy:0.970595, AUC:0.995397
Epoch:135, d_loss:0.045459, g_loss:7.339122, accuracy:0.987369, AUC:0.998343
Epoch:136, d_loss:0.041670, g_loss:7.135579, accuracy:0.962012, AUC:0.992638
Epoch:137, d_loss:0.064690, g_loss:7.460423, accuracy:0.913679, AUC:0.991869
Epoch:138, d_loss:0.075501, g_loss:7.343169, accuracy:0.964000, AUC:0.995806
Epoch:139, d_loss:0.074825, g_loss:7.220914, accuracy:0.956071, AUC:0.992056
Epoch:140, d_loss:0.086134, g_loss:6.980189, accuracy:0.920667, AUC:0.984264
Epoch:141, d_loss:0.064323, g_loss:6.532271, accuracy:0.967738, AUC:0.993145
Epoch:142, d_loss:0.099939, g_loss:7.490509, accuracy:0.935619, AUC:0.995266
Epoch:143, d_loss:0.085324, g_loss:7.177705, accuracy:0.968917, AUC:0.994409
Epoch:144, d_loss:0.073310, g_loss:7.277663, accuracy:0.900655, AUC:0.985013
Epoch:145, d_loss:0.090483, g_loss:6.811230, accuracy:0.918405, AUC:0.991903
Epoch:146, d_loss:0.058886, g_loss:7.654165, accuracy:0.981690, AUC:0.995530
Epoch:147, d_loss:0.074002, g_loss:7.344094, accuracy:0.978440, AUC:0.996103
Epoch:148, d_loss:0.062865, g_loss:6.976796, accuracy:0.978071, AUC:0.996296
Epoch:149, d_loss:0.062726, g_loss:7.002886, accuracy:0.982036, AUC:0.997640
Epoch:150, d_loss:0.072673, g_loss:6.657517, accuracy:0.963262, AUC:0.992946
Epoch:151, d_loss:0.072548, g_loss:6.781895, accuracy:0.955905, AUC:0.992561
Epoch:152, d_loss:0.194857, g_loss:7.442107, accuracy:0.965381, AUC:0.995443
Epoch:153, d_loss:0.184960, g_loss:6.138431, accuracy:0.908286, AUC:0.966938
Epoch:154, d_loss:0.118356, g_loss:6.841249, accuracy:0.964726, AUC:0.994510
Epoch:155, d_loss:0.110671, g_loss:6.531414, accuracy:0.910488, AUC:0.971529
Epoch:156, d_loss:0.114469, g_loss:6.668738, accuracy:0.981964, AUC:0.997225
Epoch:157, d_loss:0.106193, g_loss:6.947374, accuracy:0.944917, AUC:0.987109
Epoch:158, d_loss:0.119195, g_loss:6.473263, accuracy:0.927131, AUC:0.991354
Epoch:159, d_loss:0.157652, g_loss:6.693114, accuracy:0.935548, AUC:0.987378
Epoch:160, d_loss:0.110699, g_loss:7.113831, accuracy:0.919607, AUC:0.972348
Epoch:161, d_loss:0.097131, g_loss:6.659311, accuracy:0.933298, AUC:0.987936
Epoch:162, d_loss:0.110306, g_loss:6.755966, accuracy:0.942857, AUC:0.989558
Epoch:163, d_loss:0.080944, g_loss:6.424718, accuracy:0.882738, AUC:0.987579
Epoch:164, d_loss:0.110314, g_loss:6.662391, accuracy:0.948595, AUC:0.988955
Epoch:165, d_loss:0.054995, g_loss:7.163562, accuracy:0.950988, AUC:0.989913
Epoch:166, d_loss:0.099998, g_loss:7.418950, accuracy:0.924190, AUC:0.990753
Epoch:167, d_loss:0.082210, g_loss:6.726200, accuracy:0.941476, AUC:0.983496
Epoch:168, d_loss:0.082125, g_loss:6.983229, accuracy:0.888083, AUC:0.974239
Epoch:169, d_loss:0.102077, g_loss:6.875807, accuracy:0.928702, AUC:0.976601
Epoch:170, d_loss:0.069189, g_loss:6.777496, accuracy:0.938560, AUC:0.986812
Epoch:171, d_loss:0.065483, g_loss:6.889385, accuracy:0.959940, AUC:0.990547
Epoch:172, d_loss:0.072823, g_loss:7.061434, accuracy:0.971905, AUC:0.995221
Epoch:173, d_loss:0.101068, g_loss:6.564700, accuracy:0.958571, AUC:0.992228
Epoch:174, d_loss:0.080232, g_loss:7.120638, accuracy:0.970548, AUC:0.994657
Epoch:175, d_loss:0.086506, g_loss:6.748380, accuracy:0.869262, AUC:0.960074
Epoch:176, d_loss:0.078628, g_loss:6.821851, accuracy:0.958155, AUC:0.995338
Epoch:177, d_loss:0.052165, g_loss:7.209396, accuracy:0.895714, AUC:0.986895
Epoch:178, d_loss:0.077500, g_loss:7.042245, accuracy:0.927393, AUC:0.995467
Epoch:179, d_loss:0.066090, g_loss:6.961568, accuracy:0.959202, AUC:0.995283
Epoch:180, d_loss:0.098178, g_loss:7.013987, accuracy:0.953929, AUC:0.987525
Epoch:181, d_loss:0.103108, g_loss:7.209926, accuracy:0.953988, AUC:0.991249
Epoch:182, d_loss:0.130179, g_loss:6.611453, accuracy:0.967845, AUC:0.992488
Epoch:183, d_loss:0.085021, g_loss:6.885527, accuracy:0.956881, AUC:0.988599
Epoch:184, d_loss:0.111372, g_loss:7.414159, accuracy:0.848238, AUC:0.988087
Epoch:185, d_loss:0.119822, g_loss:7.496799, accuracy:0.966333, AUC:0.993643
Epoch:186, d_loss:0.100551, g_loss:6.559425, accuracy:0.906440, AUC:0.968475
Epoch:187, d_loss:0.107674, g_loss:7.227368, accuracy:0.912702, AUC:0.974577
Epoch:188, d_loss:0.078038, g_loss:6.853116, accuracy:0.954345, AUC:0.984951
Epoch:189, d_loss:0.113757, g_loss:6.842789, accuracy:0.967333, AUC:0.991025
Epoch:190, d_loss:0.091532, g_loss:6.815268, accuracy:0.937226, AUC:0.982698
Epoch:191, d_loss:0.084834, g_loss:6.731766, accuracy:0.861440, AUC:0.966638
Epoch:192, d_loss:0.121470, g_loss:6.668952, accuracy:0.927833, AUC:0.993617
Epoch:193, d_loss:0.075038, g_loss:7.653888, accuracy:0.928238, AUC:0.979002
Epoch:194, d_loss:0.089716, g_loss:7.191800, accuracy:0.951274, AUC:0.981365
Epoch:195, d_loss:0.106186, g_loss:6.585323, accuracy:0.966798, AUC:0.995338
Epoch:196, d_loss:0.088910, g_loss:6.949481, accuracy:0.967524, AUC:0.992763
Epoch:197, d_loss:0.075169, g_loss:6.767637, accuracy:0.936714, AUC:0.991166
Epoch:198, d_loss:0.061336, g_loss:6.993880, accuracy:0.916774, AUC:0.990649
Epoch:199, d_loss:0.062713, g_loss:6.621217, accuracy:0.933583, AUC:0.981085
Epoch:200, d_loss:0.057506, g_loss:7.028312, accuracy:0.956667, AUC:0.988783
Epoch:201, d_loss:0.060462, g_loss:6.686753, accuracy:0.938500, AUC:0.996335
Epoch:202, d_loss:0.065382, g_loss:6.676390, accuracy:0.952571, AUC:0.990354
Epoch:203, d_loss:0.098554, g_loss:7.015841, accuracy:0.904488, AUC:0.986097
Epoch:204, d_loss:0.073371, g_loss:6.974054, accuracy:0.949810, AUC:0.992691
Epoch:205, d_loss:0.149546, g_loss:6.620938, accuracy:0.925964, AUC:0.989941
Epoch:206, d_loss:0.139987, g_loss:6.811313, accuracy:0.924274, AUC:0.985654
Epoch:207, d_loss:0.121379, g_loss:7.023602, accuracy:0.827869, AUC:0.984901
Epoch:208, d_loss:0.099283, g_loss:6.783880, accuracy:0.968988, AUC:0.992141
Epoch:209, d_loss:0.114787, g_loss:6.392585, accuracy:0.957440, AUC:0.986921
Epoch:210, d_loss:0.078560, g_loss:6.565986, accuracy:0.937131, AUC:0.981535
Epoch:211, d_loss:0.093179, g_loss:6.394118, accuracy:0.918095, AUC:0.985457
Epoch:212, d_loss:0.123011, g_loss:6.242034, accuracy:0.954798, AUC:0.985465
Epoch:213, d_loss:0.118147, g_loss:7.265682, accuracy:0.898131, AUC:0.994866
Epoch:214, d_loss:0.101319, g_loss:6.649540, accuracy:0.901595, AUC:0.972733
Epoch:215, d_loss:0.078088, g_loss:7.038384, accuracy:0.946714, AUC:0.984563
Epoch:216, d_loss:0.077952, g_loss:6.656772, accuracy:0.860655, AUC:0.978999
Epoch:217, d_loss:0.095049, g_loss:7.061019, accuracy:0.951893, AUC:0.988475
Epoch:218, d_loss:0.120595, g_loss:6.292142, accuracy:0.947952, AUC:0.985002
Epoch:219, d_loss:0.076080, g_loss:6.014092, accuracy:0.927452, AUC:0.983633
Epoch:220, d_loss:0.091767, g_loss:6.745488, accuracy:0.951238, AUC:0.989238
Epoch:221, d_loss:0.108191, g_loss:7.029654, accuracy:0.908774, AUC:0.987412
Epoch:222, d_loss:0.082262, g_loss:6.513996, accuracy:0.891393, AUC:0.978445
Epoch:223, d_loss:0.062587, g_loss:6.420957, accuracy:0.959238, AUC:0.990744
Epoch:224, d_loss:0.074162, g_loss:6.845954, accuracy:0.925750, AUC:0.990626
Epoch:225, d_loss:0.048883, g_loss:7.334310, accuracy:0.976262, AUC:0.995705
Epoch:226, d_loss:0.088293, g_loss:6.703572, accuracy:0.941024, AUC:0.984667
Epoch:227, d_loss:0.093656, g_loss:6.048128, accuracy:0.962548, AUC:0.989664
Epoch:228, d_loss:0.062120, g_loss:6.486962, accuracy:0.940369, AUC:0.992606
Epoch:229, d_loss:0.088269, g_loss:6.813138, accuracy:0.982524, AUC:0.996553
Epoch:230, d_loss:0.075885, g_loss:6.581292, accuracy:0.937036, AUC:0.993988
Epoch:231, d_loss:0.109177, g_loss:7.242789, accuracy:0.991262, AUC:0.999167
Epoch:232, d_loss:0.091512, g_loss:7.114054, accuracy:0.977690, AUC:0.995687
Epoch:233, d_loss:0.108867, g_loss:6.882621, accuracy:0.947333, AUC:0.993284
Epoch:234, d_loss:0.131202, g_loss:6.653155, accuracy:0.940821, AUC:0.980606
Epoch:235, d_loss:0.086815, g_loss:6.686411, accuracy:0.941536, AUC:0.988969
Epoch:236, d_loss:0.116578, g_loss:6.918539, accuracy:0.889226, AUC:0.994342
Epoch:237, d_loss:0.087007, g_loss:7.206471, accuracy:0.941643, AUC:0.986475
Epoch:238, d_loss:0.139618, g_loss:6.186009, accuracy:0.963500, AUC:0.994991
Epoch:239, d_loss:0.133992, g_loss:6.158677, accuracy:0.961071, AUC:0.991385
Epoch:240, d_loss:0.139344, g_loss:6.809594, accuracy:0.932488, AUC:0.980399
Epoch:241, d_loss:0.107071, g_loss:6.610597, accuracy:0.943869, AUC:0.986755
Epoch:242, d_loss:0.087514, g_loss:6.286758, accuracy:0.895786, AUC:0.974758
Epoch:243, d_loss:0.113414, g_loss:6.376040, accuracy:0.941452, AUC:0.984529
Epoch:244, d_loss:0.115763, g_loss:6.432592, accuracy:0.934881, AUC:0.986157
Epoch:245, d_loss:0.109862, g_loss:6.403211, accuracy:0.924071, AUC:0.971974
Epoch:246, d_loss:0.077032, g_loss:6.497431, accuracy:0.966798, AUC:0.990716
Epoch:247, d_loss:0.123995, g_loss:6.478757, accuracy:0.949000, AUC:0.987154
Epoch:248, d_loss:0.090677, g_loss:6.814417, accuracy:0.963536, AUC:0.993724
Epoch:249, d_loss:0.074431, g_loss:6.661056, accuracy:0.901071, AUC:0.987310
Epoch:250, d_loss:0.101422, g_loss:7.271680, accuracy:0.980702, AUC:0.995150
Epoch:251, d_loss:0.063933, g_loss:6.808713, accuracy:0.907667, AUC:0.986944
Epoch:252, d_loss:0.050874, g_loss:7.136870, accuracy:0.903750, AUC:0.985005
Epoch:253, d_loss:0.073125, g_loss:6.703754, accuracy:0.946964, AUC:0.985882
Epoch:254, d_loss:0.065732, g_loss:7.145774, accuracy:0.856464, AUC:0.969104
Epoch:255, d_loss:0.094812, g_loss:6.083599, accuracy:0.954548, AUC:0.989574
Epoch:256, d_loss:0.125329, g_loss:6.364668, accuracy:0.981964, AUC:0.996718
Epoch:257, d_loss:0.097929, g_loss:6.478648, accuracy:0.903714, AUC:0.978398
Epoch:258, d_loss:0.086504, g_loss:6.916619, accuracy:0.974774, AUC:0.995200
Epoch:259, d_loss:0.106977, g_loss:6.368508, accuracy:0.925274, AUC:0.995474
Epoch:260, d_loss:0.097435, g_loss:6.696167, accuracy:0.947667, AUC:0.990678
Epoch:261, d_loss:0.094887, g_loss:6.830615, accuracy:0.948345, AUC:0.993655
Epoch:262, d_loss:0.074490, g_loss:6.788080, accuracy:0.935012, AUC:0.991565
Epoch:263, d_loss:0.169470, g_loss:6.355512, accuracy:0.957048, AUC:0.989393
Epoch:264, d_loss:0.087189, g_loss:6.966127, accuracy:0.972000, AUC:0.995102
Epoch:265, d_loss:0.096391, g_loss:6.497391, accuracy:0.873512, AUC:0.975110
Epoch:266, d_loss:0.042445, g_loss:6.830654, accuracy:0.964476, AUC:0.993517
Epoch:267, d_loss:0.140368, g_loss:6.000636, accuracy:0.984964, AUC:0.997706
Epoch:268, d_loss:0.089193, g_loss:6.464874, accuracy:0.937881, AUC:0.983303
Epoch:269, d_loss:0.068698, g_loss:6.799448, accuracy:0.948833, AUC:0.985357
Epoch:270, d_loss:0.096421, g_loss:6.234778, accuracy:0.926298, AUC:0.978556
Epoch:271, d_loss:0.094863, g_loss:6.559546, accuracy:0.968488, AUC:0.993493
Epoch:272, d_loss:0.069620, g_loss:6.750161, accuracy:0.970512, AUC:0.993603
Epoch:273, d_loss:0.072854, g_loss:7.369662, accuracy:0.952012, AUC:0.992638
Epoch:274, d_loss:0.067079, g_loss:6.867965, accuracy:0.846405, AUC:0.970039
Epoch:275, d_loss:0.089871, g_loss:6.524342, accuracy:0.914083, AUC:0.989856
Epoch:276, d_loss:0.133662, g_loss:6.715050, accuracy:0.864607, AUC:0.981611
Epoch:277, d_loss:0.108302, g_loss:7.254221, accuracy:0.938690, AUC:0.979289
Epoch:278, d_loss:0.102510, g_loss:6.717463, accuracy:0.946262, AUC:0.990305
Epoch:279, d_loss:0.068061, g_loss:5.949107, accuracy:0.945440, AUC:0.989460
Epoch:280, d_loss:0.104489, g_loss:6.775084, accuracy:0.920845, AUC:0.983294
Epoch:281, d_loss:0.093407, g_loss:6.864989, accuracy:0.957464, AUC:0.987275
Epoch:282, d_loss:0.090345, g_loss:6.388844, accuracy:0.965988, AUC:0.993722
Epoch:283, d_loss:0.060729, g_loss:6.582823, accuracy:0.934048, AUC:0.980149
Epoch:284, d_loss:0.073309, g_loss:6.561574, accuracy:0.960631, AUC:0.989798
Epoch:285, d_loss:0.087484, g_loss:6.557438, accuracy:0.960738, AUC:0.989321
Epoch:286, d_loss:0.099121, g_loss:6.493825, accuracy:0.921833, AUC:0.990538
Epoch:287, d_loss:0.052395, g_loss:6.531547, accuracy:0.938238, AUC:0.989594
Epoch:288, d_loss:0.074543, g_loss:5.986147, accuracy:0.978524, AUC:0.995560
Epoch:289, d_loss:0.069520, g_loss:6.375990, accuracy:0.897845, AUC:0.986084
Epoch:290, d_loss:0.114416, g_loss:6.618052, accuracy:0.945321, AUC:0.994203
Epoch:291, d_loss:0.097763, g_loss:7.119496, accuracy:0.939440, AUC:0.982452
Epoch:292, d_loss:0.102645, g_loss:6.315044, accuracy:0.945119, AUC:0.985760
Epoch:293, d_loss:0.113972, g_loss:6.282133, accuracy:0.902893, AUC:0.986682
Epoch:294, d_loss:0.091821, g_loss:6.772233, accuracy:0.941690, AUC:0.988535
Epoch:295, d_loss:0.066762, g_loss:6.794907, accuracy:0.959083, AUC:0.991063
Epoch:296, d_loss:0.122396, g_loss:6.786599, accuracy:0.765881, AUC:0.987105
Epoch:297, d_loss:0.130066, g_loss:6.286452, accuracy:0.934893, AUC:0.981840
Epoch:298, d_loss:0.133260, g_loss:6.271439, accuracy:0.931357, AUC:0.988657
Epoch:299, d_loss:0.076049, g_loss:6.270113, accuracy:0.914107, AUC:0.972975
Epoch:300, d_loss:0.115547, g_loss:6.175061, accuracy:0.965619, AUC:0.993770
Epoch:301, d_loss:0.122689, g_loss:7.077242, accuracy:0.919095, AUC:0.992994
Epoch:302, d_loss:0.053648, g_loss:7.109667, accuracy:0.972274, AUC:0.995325
Epoch:303, d_loss:0.072443, g_loss:6.722173, accuracy:0.915560, AUC:0.989183
Epoch:304, d_loss:0.053181, g_loss:6.898899, accuracy:0.943214, AUC:0.990392
Epoch:305, d_loss:0.060679, g_loss:6.660762, accuracy:0.963190, AUC:0.993800
Epoch:306, d_loss:0.100643, g_loss:6.467166, accuracy:0.947821, AUC:0.988333
Epoch:307, d_loss:0.059704, g_loss:6.271926, accuracy:0.924167, AUC:0.983027
Epoch:308, d_loss:0.081446, g_loss:6.411751, accuracy:0.956095, AUC:0.993554
Epoch:309, d_loss:0.103049, g_loss:6.729914, accuracy:0.958107, AUC:0.994442
Epoch:310, d_loss:0.119175, g_loss:6.303141, accuracy:0.867595, AUC:0.970717
Epoch:311, d_loss:0.096650, g_loss:6.486417, accuracy:0.960738, AUC:0.991281
Epoch:312, d_loss:0.109901, g_loss:6.688353, accuracy:0.986012, AUC:0.997458
Epoch:313, d_loss:0.093517, g_loss:6.719886, accuracy:0.960190, AUC:0.993222
Epoch:314, d_loss:0.074847, g_loss:6.478080, accuracy:0.976024, AUC:0.995885
Epoch:315, d_loss:0.122540, g_loss:6.306532, accuracy:0.937786, AUC:0.979688
Epoch:316, d_loss:0.084967, g_loss:6.646139, accuracy:0.969131, AUC:0.992886
Epoch:317, d_loss:0.083917, g_loss:6.318406, accuracy:0.984333, AUC:0.997413
Epoch:318, d_loss:0.064741, g_loss:6.578665, accuracy:0.959048, AUC:0.991627
Epoch:319, d_loss:0.087052, g_loss:6.657841, accuracy:0.965179, AUC:0.993663
Epoch:320, d_loss:0.099493, g_loss:6.704720, accuracy:0.856190, AUC:0.969440
Epoch:321, d_loss:0.073813, g_loss:6.615256, accuracy:0.963464, AUC:0.990866
Epoch:322, d_loss:0.161109, g_loss:6.464239, accuracy:0.977500, AUC:0.995337
Epoch:323, d_loss:0.099539, g_loss:6.404167, accuracy:0.952095, AUC:0.987310
Epoch:324, d_loss:0.093349, g_loss:6.047296, accuracy:0.960571, AUC:0.989714
Epoch:325, d_loss:0.092389, g_loss:6.639265, accuracy:0.962048, AUC:0.996102
Epoch:326, d_loss:0.085969, g_loss:6.623008, accuracy:0.912226, AUC:0.970569
Epoch:327, d_loss:0.117070, g_loss:6.796571, accuracy:0.838464, AUC:0.977861
Epoch:328, d_loss:0.109928, g_loss:6.504201, accuracy:0.898060, AUC:0.982047
Epoch:329, d_loss:0.065630, g_loss:6.738151, accuracy:0.789440, AUC:0.964124
Epoch:330, d_loss:0.129170, g_loss:6.681136, accuracy:0.964917, AUC:0.994307
Epoch:331, d_loss:0.085970, g_loss:6.352908, accuracy:0.880369, AUC:0.983345
Epoch:332, d_loss:0.111508, g_loss:6.700319, accuracy:0.970452, AUC:0.996187
Epoch:333, d_loss:0.099312, g_loss:6.076455, accuracy:0.964940, AUC:0.995658
Epoch:334, d_loss:0.109176, g_loss:6.781664, accuracy:0.952143, AUC:0.991476
Epoch:335, d_loss:0.097216, g_loss:6.705494, accuracy:0.951738, AUC:0.997258
Epoch:336, d_loss:0.085948, g_loss:6.740792, accuracy:0.971595, AUC:0.995048
Epoch:337, d_loss:0.164834, g_loss:6.353797, accuracy:0.976750, AUC:0.995696
Epoch:338, d_loss:0.084401, g_loss:6.349582, accuracy:0.838083, AUC:0.980860
Epoch:339, d_loss:0.109632, g_loss:6.521516, accuracy:0.867214, AUC:0.972637
Epoch:340, d_loss:0.127205, g_loss:6.158876, accuracy:0.911500, AUC:0.973742
Epoch:341, d_loss:0.095530, g_loss:6.729342, accuracy:0.967512, AUC:0.996410
Epoch:342, d_loss:0.084559, g_loss:6.525840, accuracy:0.967595, AUC:0.993485
Epoch:343, d_loss:0.086567, g_loss:6.208171, accuracy:0.908107, AUC:0.984112
Epoch:344, d_loss:0.062234, g_loss:6.791748, accuracy:0.953571, AUC:0.988375
Epoch:345, d_loss:0.132101, g_loss:6.624076, accuracy:0.953476, AUC:0.992204
Epoch:346, d_loss:0.090714, g_loss:6.215948, accuracy:0.922893, AUC:0.974035
Epoch:347, d_loss:0.108493, g_loss:6.526122, accuracy:0.944643, AUC:0.981886
Epoch:348, d_loss:0.091256, g_loss:6.343461, accuracy:0.918119, AUC:0.988545
Epoch:349, d_loss:0.062849, g_loss:6.205253, accuracy:0.952143, AUC:0.985310
Epoch:350, d_loss:0.089412, g_loss:6.683742, accuracy:0.895238, AUC:0.988073
Epoch:351, d_loss:0.114584, g_loss:6.238491, accuracy:0.964548, AUC:0.994018
Epoch:352, d_loss:0.119621, g_loss:6.367475, accuracy:0.878107, AUC:0.983862
Epoch:353, d_loss:0.106495, g_loss:6.056060, accuracy:0.955524, AUC:0.988373
Epoch:354, d_loss:0.073357, g_loss:6.388845, accuracy:0.932155, AUC:0.985970
Epoch:355, d_loss:0.071806, g_loss:6.688017, accuracy:0.959548, AUC:0.990136
Epoch:356, d_loss:0.117604, g_loss:5.941802, accuracy:0.931595, AUC:0.991353
Epoch:357, d_loss:0.121650, g_loss:6.588953, accuracy:0.811917, AUC:0.985753
Epoch:358, d_loss:0.159133, g_loss:6.125580, accuracy:0.951048, AUC:0.991697
Epoch:359, d_loss:0.100483, g_loss:6.560902, accuracy:0.952488, AUC:0.994414
Epoch:360, d_loss:0.151192, g_loss:6.695687, accuracy:0.889893, AUC:0.997574
Epoch:361, d_loss:0.108000, g_loss:6.634530, accuracy:0.947786, AUC:0.993241
Epoch:362, d_loss:0.146751, g_loss:6.531337, accuracy:0.967095, AUC:0.994406
Epoch:363, d_loss:0.127983, g_loss:5.973937, accuracy:0.941286, AUC:0.983659
Epoch:364, d_loss:0.077187, g_loss:6.530611, accuracy:0.948083, AUC:0.992108
Epoch:365, d_loss:0.142186, g_loss:5.978481, accuracy:0.882262, AUC:0.988910
Epoch:366, d_loss:0.097657, g_loss:6.106592, accuracy:0.938869, AUC:0.993866
Epoch:367, d_loss:0.086920, g_loss:6.239352, accuracy:0.897548, AUC:0.969685
Epoch:368, d_loss:0.118602, g_loss:6.447818, accuracy:0.951131, AUC:0.986761
Epoch:369, d_loss:0.110276, g_loss:6.296955, accuracy:0.843738, AUC:0.992789
Epoch:370, d_loss:0.160547, g_loss:6.632661, accuracy:0.900107, AUC:0.990925
Epoch:371, d_loss:0.086922, g_loss:6.448205, accuracy:0.906857, AUC:0.985620
Epoch:372, d_loss:0.091330, g_loss:6.235157, accuracy:0.967381, AUC:0.992026
Epoch:373, d_loss:0.128043, g_loss:6.133227, accuracy:0.898595, AUC:0.976349
Epoch:374, d_loss:0.091091, g_loss:6.150736, accuracy:0.962940, AUC:0.990567
Epoch:375, d_loss:0.091582, g_loss:6.117698, accuracy:0.960321, AUC:0.989975
Epoch:376, d_loss:0.091044, g_loss:5.966961, accuracy:0.910798, AUC:0.982673
Epoch:377, d_loss:0.085636, g_loss:6.366093, accuracy:0.946107, AUC:0.994511
Epoch:378, d_loss:0.100644, g_loss:6.621278, accuracy:0.883905, AUC:0.975260
Epoch:379, d_loss:0.095249, g_loss:6.549299, accuracy:0.952381, AUC:0.993927
Epoch:380, d_loss:0.092597, g_loss:6.036115, accuracy:0.900167, AUC:0.979204
Epoch:381, d_loss:0.093017, g_loss:6.757840, accuracy:0.977607, AUC:0.995575
Epoch:382, d_loss:0.154722, g_loss:6.295998, accuracy:0.853048, AUC:0.969596
Epoch:383, d_loss:0.101764, g_loss:5.783584, accuracy:0.929250, AUC:0.985657
Epoch:384, d_loss:0.065001, g_loss:6.407979, accuracy:0.955071, AUC:0.992678
Epoch:385, d_loss:0.147642, g_loss:6.263937, accuracy:0.937000, AUC:0.983530
Epoch:386, d_loss:0.088878, g_loss:6.264767, accuracy:0.946798, AUC:0.987112
Epoch:387, d_loss:0.100787, g_loss:6.447501, accuracy:0.934952, AUC:0.983928
Epoch:388, d_loss:0.102010, g_loss:6.239312, accuracy:0.948369, AUC:0.996017
Epoch:389, d_loss:0.133313, g_loss:6.364273, accuracy:0.949167, AUC:0.993265
Epoch:390, d_loss:0.118583, g_loss:6.141754, accuracy:0.920381, AUC:0.988010
Epoch:391, d_loss:0.107085, g_loss:5.751449, accuracy:0.920250, AUC:0.972115
Epoch:392, d_loss:0.132950, g_loss:6.745242, accuracy:0.911702, AUC:0.993927
Epoch:393, d_loss:0.109290, g_loss:6.101328, accuracy:0.963095, AUC:0.992985
Epoch:394, d_loss:0.087999, g_loss:6.494290, accuracy:0.910119, AUC:0.983939
Epoch:395, d_loss:0.096584, g_loss:6.104601, accuracy:0.962595, AUC:0.991869
Epoch:396, d_loss:0.079559, g_loss:6.639843, accuracy:0.933738, AUC:0.985659
Epoch:397, d_loss:0.102312, g_loss:6.383723, accuracy:0.950833, AUC:0.987554
Epoch:398, d_loss:0.092968, g_loss:6.118130, accuracy:0.941071, AUC:0.993226
Epoch:399, d_loss:0.077856, g_loss:6.739861, accuracy:0.927262, AUC:0.974934
Epoch:400, d_loss:0.113834, g_loss:6.370267, accuracy:0.962762, AUC:0.994227
Epoch:401, d_loss:0.074053, g_loss:6.024987, accuracy:0.933690, AUC:0.986268
Epoch:402, d_loss:0.120206, g_loss:6.476950, accuracy:0.970976, AUC:0.995203
Epoch:403, d_loss:0.065644, g_loss:6.596545, accuracy:0.941821, AUC:0.992809
Epoch:404, d_loss:0.082403, g_loss:6.247463, accuracy:0.907000, AUC:0.985729
Epoch:405, d_loss:0.088226, g_loss:6.194877, accuracy:0.975500, AUC:0.996370
Epoch:406, d_loss:0.126318, g_loss:6.125005, accuracy:0.949750, AUC:0.992827
Epoch:407, d_loss:0.121024, g_loss:6.408021, accuracy:0.954857, AUC:0.986715
Epoch:408, d_loss:0.074509, g_loss:6.235833, accuracy:0.962655, AUC:0.992545
Epoch:409, d_loss:0.091986, g_loss:6.474186, accuracy:0.903976, AUC:0.982533
Epoch:410, d_loss:0.100611, g_loss:6.065969, accuracy:0.923131, AUC:0.983035
Epoch:411, d_loss:0.115049, g_loss:6.886932, accuracy:0.975571, AUC:0.996037
Epoch:412, d_loss:0.106141, g_loss:6.129299, accuracy:0.935964, AUC:0.982998
Epoch:413, d_loss:0.123291, g_loss:6.222795, accuracy:0.915262, AUC:0.985651
Epoch:414, d_loss:0.074936, g_loss:6.509634, accuracy:0.962655, AUC:0.993169
Epoch:415, d_loss:0.129303, g_loss:6.211364, accuracy:0.956607, AUC:0.991898
Epoch:416, d_loss:0.086259, g_loss:6.111231, accuracy:0.949274, AUC:0.990345
Epoch:417, d_loss:0.073394, g_loss:6.239717, accuracy:0.924964, AUC:0.989075
Epoch:418, d_loss:0.101120, g_loss:6.061936, accuracy:0.982964, AUC:0.997910
Epoch:419, d_loss:0.088516, g_loss:6.473983, accuracy:0.942179, AUC:0.987353
Epoch:420, d_loss:0.109718, g_loss:6.299361, accuracy:0.952060, AUC:0.995941
Epoch:421, d_loss:0.101935, g_loss:6.745619, accuracy:0.918048, AUC:0.993767
Epoch:422, d_loss:0.077659, g_loss:6.627415, accuracy:0.965690, AUC:0.991621
Epoch:423, d_loss:0.139912, g_loss:6.173229, accuracy:0.970524, AUC:0.994232
Epoch:424, d_loss:0.113317, g_loss:6.023692, accuracy:0.933190, AUC:0.986027
Epoch:425, d_loss:0.164075, g_loss:6.017115, accuracy:0.943393, AUC:0.988004
Epoch:426, d_loss:0.092377, g_loss:6.255706, accuracy:0.932655, AUC:0.988182
Epoch:427, d_loss:0.069689, g_loss:6.454144, accuracy:0.963560, AUC:0.991513
Epoch:428, d_loss:0.113773, g_loss:6.274517, accuracy:0.894381, AUC:0.959804
Epoch:429, d_loss:0.086188, g_loss:6.480113, accuracy:0.965357, AUC:0.992450
Epoch:430, d_loss:0.136592, g_loss:6.028665, accuracy:0.941500, AUC:0.983013
Epoch:431, d_loss:0.116578, g_loss:5.974267, accuracy:0.922738, AUC:0.982577
Epoch:432, d_loss:0.092129, g_loss:6.321857, accuracy:0.930131, AUC:0.979028
Epoch:433, d_loss:0.115154, g_loss:5.943235, accuracy:0.965976, AUC:0.993332
Epoch:434, d_loss:0.075991, g_loss:6.342864, accuracy:0.962464, AUC:0.990738
Epoch:435, d_loss:0.102476, g_loss:6.277070, accuracy:0.963131, AUC:0.993002
Epoch:436, d_loss:0.075699, g_loss:6.410719, accuracy:0.889345, AUC:0.991579
Epoch:437, d_loss:0.083978, g_loss:6.392550, accuracy:0.957048, AUC:0.991764
Epoch:438, d_loss:0.089652, g_loss:5.860469, accuracy:0.962214, AUC:0.996188
Epoch:439, d_loss:0.090161, g_loss:6.675567, accuracy:0.931321, AUC:0.981305
Epoch:440, d_loss:0.099506, g_loss:6.628604, accuracy:0.924631, AUC:0.991478
Epoch:441, d_loss:0.143053, g_loss:6.043718, accuracy:0.898440, AUC:0.992718
Epoch:442, d_loss:0.098199, g_loss:6.391569, accuracy:0.974964, AUC:0.994545
Epoch:443, d_loss:0.096964, g_loss:6.266687, accuracy:0.903143, AUC:0.972652
Epoch:444, d_loss:0.093100, g_loss:6.586470, accuracy:0.916869, AUC:0.969756
Epoch:445, d_loss:0.112275, g_loss:6.319071, accuracy:0.877381, AUC:0.993223
Epoch:446, d_loss:0.126023, g_loss:6.519483, accuracy:0.895512, AUC:0.979542
Epoch:447, d_loss:0.130478, g_loss:5.550596, accuracy:0.905560, AUC:0.985948
Epoch:448, d_loss:0.095338, g_loss:6.123811, accuracy:0.956929, AUC:0.992474
Epoch:449, d_loss:0.077998, g_loss:5.801192, accuracy:0.941321, AUC:0.987161
Epoch:450, d_loss:0.110949, g_loss:6.182319, accuracy:0.853000, AUC:0.985308
Epoch:451, d_loss:0.106408, g_loss:6.263477, accuracy:0.928976, AUC:0.988453
Epoch:452, d_loss:0.084576, g_loss:6.261638, accuracy:0.951738, AUC:0.990969
Epoch:453, d_loss:0.104230, g_loss:6.426328, accuracy:0.881655, AUC:0.974513
Epoch:454, d_loss:0.127669, g_loss:6.179420, accuracy:0.964048, AUC:0.993394
Epoch:455, d_loss:0.120678, g_loss:5.944529, accuracy:0.940500, AUC:0.990732
Epoch:456, d_loss:0.126047, g_loss:6.282724, accuracy:0.863762, AUC:0.953745
Epoch:457, d_loss:0.097982, g_loss:5.989430, accuracy:0.840274, AUC:0.982624
Epoch:458, d_loss:0.120287, g_loss:6.441854, accuracy:0.859452, AUC:0.995059
Epoch:459, d_loss:0.111800, g_loss:5.873356, accuracy:0.960071, AUC:0.989118
Epoch:460, d_loss:0.090667, g_loss:6.657006, accuracy:0.909333, AUC:0.981802
Epoch:461, d_loss:0.111758, g_loss:6.059055, accuracy:0.944381, AUC:0.985531
Epoch:462, d_loss:0.073248, g_loss:6.138673, accuracy:0.975298, AUC:0.994717
Epoch:463, d_loss:0.083096, g_loss:6.016381, accuracy:0.977381, AUC:0.996167
Epoch:464, d_loss:0.073929, g_loss:6.279853, accuracy:0.956524, AUC:0.990502
Epoch:465, d_loss:0.106133, g_loss:6.316438, accuracy:0.954369, AUC:0.996301
Epoch:466, d_loss:0.115352, g_loss:6.427995, accuracy:0.958500, AUC:0.988904
Epoch:467, d_loss:0.092290, g_loss:6.274652, accuracy:0.892226, AUC:0.981580
Epoch:468, d_loss:0.127199, g_loss:6.602687, accuracy:0.982524, AUC:0.997823
Epoch:469, d_loss:0.088359, g_loss:6.482780, accuracy:0.921452, AUC:0.980703
Epoch:470, d_loss:0.108040, g_loss:6.110493, accuracy:0.970786, AUC:0.992439
Epoch:471, d_loss:0.089926, g_loss:5.899621, accuracy:0.926452, AUC:0.985501
Epoch:472, d_loss:0.075966, g_loss:6.515128, accuracy:0.953607, AUC:0.988922
Epoch:473, d_loss:0.120413, g_loss:5.830106, accuracy:0.863940, AUC:0.991732
Epoch:474, d_loss:0.131730, g_loss:6.216115, accuracy:0.915857, AUC:0.989672
Epoch:475, d_loss:0.145509, g_loss:6.135907, accuracy:0.816750, AUC:0.957306
Epoch:476, d_loss:0.106957, g_loss:6.121274, accuracy:0.937321, AUC:0.984485
Epoch:477, d_loss:0.121559, g_loss:6.528004, accuracy:0.950512, AUC:0.988355
Epoch:478, d_loss:0.151231, g_loss:6.349215, accuracy:0.903226, AUC:0.968485
Epoch:479, d_loss:0.083412, g_loss:6.405080, accuracy:0.961286, AUC:0.990734
Epoch:480, d_loss:0.095312, g_loss:5.521733, accuracy:0.930036, AUC:0.982167
Epoch:481, d_loss:0.105394, g_loss:5.972333, accuracy:0.870179, AUC:0.980084
Epoch:482, d_loss:0.103104, g_loss:6.483292, accuracy:0.953595, AUC:0.989544
Epoch:483, d_loss:0.101451, g_loss:5.840199, accuracy:0.941012, AUC:0.987222
Epoch:484, d_loss:0.105716, g_loss:6.155879, accuracy:0.961821, AUC:0.989804
Epoch:485, d_loss:0.073888, g_loss:6.730484, accuracy:0.962298, AUC:0.993054
Epoch:486, d_loss:0.127176, g_loss:6.705548, accuracy:0.949262, AUC:0.998120
Epoch:487, d_loss:0.086482, g_loss:6.441834, accuracy:0.954607, AUC:0.992735
Epoch:488, d_loss:0.120785, g_loss:6.033972, accuracy:0.920214, AUC:0.973960
Epoch:489, d_loss:0.071861, g_loss:6.240034, accuracy:0.915738, AUC:0.981167
Epoch:490, d_loss:0.093730, g_loss:6.603472, accuracy:0.937738, AUC:0.989237
Epoch:491, d_loss:0.070276, g_loss:6.220985, accuracy:0.918179, AUC:0.986080
Epoch:492, d_loss:0.087295, g_loss:6.232809, accuracy:0.967226, AUC:0.995328
Epoch:493, d_loss:0.125961, g_loss:6.520615, accuracy:0.888940, AUC:0.988696
Epoch:494, d_loss:0.127791, g_loss:6.284145, accuracy:0.961988, AUC:0.989660
Epoch:495, d_loss:0.095046, g_loss:5.595455, accuracy:0.859619, AUC:0.967072
Epoch:496, d_loss:0.119861, g_loss:5.927981, accuracy:0.890452, AUC:0.989947
Epoch:497, d_loss:0.080060, g_loss:6.609385, accuracy:0.902571, AUC:0.978224
Epoch:498, d_loss:0.110934, g_loss:5.993641, accuracy:0.964798, AUC:0.992769
Epoch:499, d_loss:0.125393, g_loss:6.165252, accuracy:0.885440, AUC:0.985603
Epoch:500, d_loss:0.078101, g_loss:5.980324, accuracy:0.954048, AUC:0.988297
Epoch:501, d_loss:0.129174, g_loss:5.828422, accuracy:0.979321, AUC:0.997219
Epoch:502, d_loss:0.128427, g_loss:6.284268, accuracy:0.970274, AUC:0.995067
Epoch:503, d_loss:0.115634, g_loss:6.132873, accuracy:0.888155, AUC:0.977372
Epoch:504, d_loss:0.096174, g_loss:6.207890, accuracy:0.910726, AUC:0.976910
Epoch:505, d_loss:0.166858, g_loss:6.124264, accuracy:0.822381, AUC:0.975571
Epoch:506, d_loss:0.149130, g_loss:5.430354, accuracy:0.951857, AUC:0.986243
Epoch:507, d_loss:0.101574, g_loss:6.245105, accuracy:0.900405, AUC:0.979092
Epoch:508, d_loss:0.111364, g_loss:6.309246, accuracy:0.975833, AUC:0.997863
Epoch:509, d_loss:0.116660, g_loss:5.894476, accuracy:0.963548, AUC:0.994451
Epoch:510, d_loss:0.072910, g_loss:6.480739, accuracy:0.959524, AUC:0.992699
Epoch:511, d_loss:0.089778, g_loss:6.430595, accuracy:0.904119, AUC:0.989304
Epoch:512, d_loss:0.145690, g_loss:5.909214, accuracy:0.916667, AUC:0.980437
Epoch:513, d_loss:0.084165, g_loss:6.461891, accuracy:0.965488, AUC:0.993428
Epoch:514, d_loss:0.096511, g_loss:5.706788, accuracy:0.806250, AUC:0.964975
Epoch:515, d_loss:0.100345, g_loss:6.115537, accuracy:0.945667, AUC:0.985044
Epoch:516, d_loss:0.195049, g_loss:6.014976, accuracy:0.922131, AUC:0.978014
Epoch:517, d_loss:0.084335, g_loss:6.215215, accuracy:0.946571, AUC:0.994597
Epoch:518, d_loss:0.095500, g_loss:6.020040, accuracy:0.937631, AUC:0.992157
Epoch:519, d_loss:0.121566, g_loss:6.154949, accuracy:0.939964, AUC:0.990122
Epoch:520, d_loss:0.158229, g_loss:6.257561, accuracy:0.830940, AUC:0.969750
Epoch:521, d_loss:0.112084, g_loss:6.012263, accuracy:0.926964, AUC:0.990012
Epoch:522, d_loss:0.126754, g_loss:5.869465, accuracy:0.952893, AUC:0.990655
Epoch:523, d_loss:0.090430, g_loss:6.177242, accuracy:0.929250, AUC:0.989903
Epoch:524, d_loss:0.109441, g_loss:5.934695, accuracy:0.904548, AUC:0.982122
Epoch:525, d_loss:0.088143, g_loss:6.042454, accuracy:0.915167, AUC:0.973256
Epoch:526, d_loss:0.128172, g_loss:6.102994, accuracy:0.980667, AUC:0.997629
Epoch:527, d_loss:0.157028, g_loss:5.885496, accuracy:0.937417, AUC:0.985068
Epoch:528, d_loss:0.079339, g_loss:5.946748, accuracy:0.931940, AUC:0.979536
Epoch:529, d_loss:0.113554, g_loss:5.814467, accuracy:0.896762, AUC:0.982555
Epoch:530, d_loss:0.091320, g_loss:6.332127, accuracy:0.958119, AUC:0.992752
Epoch:531, d_loss:0.081189, g_loss:6.381134, accuracy:0.929393, AUC:0.990248
Epoch:532, d_loss:0.100025, g_loss:6.025480, accuracy:0.893679, AUC:0.985631
Epoch:533, d_loss:0.098441, g_loss:6.315064, accuracy:0.946821, AUC:0.983112
Epoch:534, d_loss:0.137068, g_loss:6.299584, accuracy:0.946119, AUC:0.980821
Epoch:535, d_loss:0.081097, g_loss:6.099567, accuracy:0.946619, AUC:0.985198
Epoch:536, d_loss:0.088334, g_loss:6.194376, accuracy:0.928417, AUC:0.991136
Epoch:537, d_loss:0.100879, g_loss:6.378196, accuracy:0.942655, AUC:0.988513
Epoch:538, d_loss:0.100210, g_loss:6.553735, accuracy:0.854881, AUC:0.990255
Epoch:539, d_loss:0.089412, g_loss:6.326105, accuracy:0.968238, AUC:0.995319
Epoch:540, d_loss:0.087794, g_loss:6.205258, accuracy:0.963964, AUC:0.992323
Epoch:541, d_loss:0.109083, g_loss:6.350944, accuracy:0.958690, AUC:0.992427
Epoch:542, d_loss:0.125280, g_loss:6.135776, accuracy:0.895202, AUC:0.981177
Epoch:543, d_loss:0.104695, g_loss:6.537647, accuracy:0.961679, AUC:0.989026
Epoch:544, d_loss:0.121126, g_loss:5.984757, accuracy:0.908833, AUC:0.974069
Epoch:545, d_loss:0.093658, g_loss:5.987675, accuracy:0.926548, AUC:0.991548
Epoch:546, d_loss:0.102635, g_loss:5.829398, accuracy:0.942810, AUC:0.993657
Epoch:547, d_loss:0.096913, g_loss:6.337219, accuracy:0.950929, AUC:0.995032
Epoch:548, d_loss:0.116590, g_loss:5.953722, accuracy:0.945655, AUC:0.988307
Epoch:549, d_loss:0.123696, g_loss:6.326202, accuracy:0.963107, AUC:0.989703
Epoch:550, d_loss:0.229857, g_loss:5.825363, accuracy:0.923964, AUC:0.983528
Epoch:551, d_loss:0.108867, g_loss:5.963230, accuracy:0.949321, AUC:0.985732
Epoch:552, d_loss:0.147246, g_loss:6.103302, accuracy:0.950345, AUC:0.987685
Epoch:553, d_loss:0.069134, g_loss:6.702268, accuracy:0.917893, AUC:0.976504
Epoch:554, d_loss:0.117222, g_loss:5.505149, accuracy:0.953381, AUC:0.990074
Epoch:555, d_loss:0.086937, g_loss:6.520221, accuracy:0.933202, AUC:0.985241
Epoch:556, d_loss:0.129237, g_loss:5.899034, accuracy:0.953726, AUC:0.989010
Epoch:557, d_loss:0.115723, g_loss:6.249393, accuracy:0.944488, AUC:0.984297
Epoch:558, d_loss:0.078547, g_loss:6.432505, accuracy:0.908905, AUC:0.986650
Epoch:559, d_loss:0.116076, g_loss:5.901826, accuracy:0.849643, AUC:0.969612
Epoch:560, d_loss:0.100607, g_loss:7.199610, accuracy:0.967738, AUC:0.995851
Epoch:561, d_loss:0.125842, g_loss:5.748837, accuracy:0.927345, AUC:0.977906
Epoch:562, d_loss:0.115872, g_loss:5.785716, accuracy:0.935357, AUC:0.985428
Epoch:563, d_loss:0.090474, g_loss:5.973669, accuracy:0.888321, AUC:0.986877
Epoch:564, d_loss:0.092930, g_loss:6.304097, accuracy:0.962190, AUC:0.993575
Epoch:565, d_loss:0.111218, g_loss:6.078416, accuracy:0.892262, AUC:0.993472
Epoch:566, d_loss:0.113912, g_loss:5.926479, accuracy:0.918500, AUC:0.981750
Epoch:567, d_loss:0.118523, g_loss:6.069231, accuracy:0.907095, AUC:0.991877
Epoch:568, d_loss:0.139655, g_loss:6.009657, accuracy:0.898905, AUC:0.980680
Epoch:569, d_loss:0.149995, g_loss:5.834888, accuracy:0.929857, AUC:0.979815
Epoch:570, d_loss:0.120472, g_loss:5.984247, accuracy:0.926905, AUC:0.992406
Epoch:571, d_loss:0.139971, g_loss:5.860495, accuracy:0.913452, AUC:0.987106
Epoch:572, d_loss:0.181623, g_loss:5.780727, accuracy:0.899631, AUC:0.972800
Epoch:573, d_loss:0.140092, g_loss:5.819016, accuracy:0.779333, AUC:0.955036
Epoch:574, d_loss:0.167430, g_loss:5.639819, accuracy:0.899845, AUC:0.980846
Epoch:575, d_loss:0.106540, g_loss:6.359537, accuracy:0.944607, AUC:0.988438
Epoch:576, d_loss:0.154680, g_loss:5.471718, accuracy:0.903940, AUC:0.970297
Epoch:577, d_loss:0.095345, g_loss:5.849913, accuracy:0.846143, AUC:0.973049
Epoch:578, d_loss:0.115086, g_loss:5.631576, accuracy:0.910893, AUC:0.983634
Epoch:579, d_loss:0.089988, g_loss:6.163556, accuracy:0.916536, AUC:0.986996
Epoch:580, d_loss:0.158769, g_loss:6.164396, accuracy:0.942060, AUC:0.990443
Epoch:581, d_loss:0.091348, g_loss:5.637835, accuracy:0.889607, AUC:0.965261
Epoch:582, d_loss:0.145932, g_loss:6.171922, accuracy:0.918202, AUC:0.972117
Epoch:583, d_loss:0.129456, g_loss:5.904469, accuracy:0.928976, AUC:0.985564
Epoch:584, d_loss:0.084324, g_loss:5.945016, accuracy:0.928810, AUC:0.982427
Epoch:585, d_loss:0.096434, g_loss:5.707813, accuracy:0.892905, AUC:0.974511
Epoch:586, d_loss:0.093527, g_loss:5.676763, accuracy:0.962774, AUC:0.993898
Epoch:587, d_loss:0.120653, g_loss:6.259352, accuracy:0.891738, AUC:0.981258
Epoch:588, d_loss:0.102055, g_loss:6.173481, accuracy:0.865179, AUC:0.969924
Epoch:589, d_loss:0.093616, g_loss:6.443227, accuracy:0.964929, AUC:0.992824
Epoch:590, d_loss:0.119615, g_loss:5.625038, accuracy:0.909905, AUC:0.973552
Epoch:591, d_loss:0.086810, g_loss:5.927842, accuracy:0.915333, AUC:0.978452
Epoch:592, d_loss:0.087068, g_loss:6.519320, accuracy:0.913321, AUC:0.979956
Epoch:593, d_loss:0.149809, g_loss:5.791656, accuracy:0.936440, AUC:0.983554
Epoch:594, d_loss:0.106137, g_loss:6.090642, accuracy:0.907262, AUC:0.982456
Epoch:595, d_loss:0.097737, g_loss:5.647514, accuracy:0.969321, AUC:0.993135
Epoch:596, d_loss:0.101525, g_loss:6.279088, accuracy:0.959476, AUC:0.993597
Epoch:597, d_loss:0.087658, g_loss:5.882982, accuracy:0.869452, AUC:0.984475
Epoch:598, d_loss:0.124905, g_loss:5.736737, accuracy:0.933714, AUC:0.980506
Epoch:599, d_loss:0.111078, g_loss:6.276761, accuracy:0.946345, AUC:0.985427
Epoch:600, d_loss:0.109975, g_loss:6.138955, accuracy:0.746821, AUC:0.991248
Epoch:601, d_loss:0.147850, g_loss:6.270422, accuracy:0.936988, AUC:0.992568
Epoch:602, d_loss:0.074703, g_loss:6.511057, accuracy:0.903000, AUC:0.978164
Epoch:603, d_loss:0.113901, g_loss:5.762598, accuracy:0.913310, AUC:0.989407
Epoch:604, d_loss:0.104641, g_loss:5.952458, accuracy:0.928131, AUC:0.985046
Epoch:605, d_loss:0.150018, g_loss:5.820913, accuracy:0.962762, AUC:0.994844
Epoch:606, d_loss:0.103767, g_loss:6.338827, accuracy:0.957417, AUC:0.991494
Epoch:607, d_loss:0.211431, g_loss:5.572416, accuracy:0.901833, AUC:0.984455
Epoch:608, d_loss:0.129048, g_loss:5.816247, accuracy:0.967655, AUC:0.990346
Epoch:609, d_loss:0.103157, g_loss:6.269906, accuracy:0.907571, AUC:0.987002
Epoch:610, d_loss:0.117654, g_loss:6.382080, accuracy:0.950333, AUC:0.994294
Epoch:611, d_loss:0.078688, g_loss:6.227109, accuracy:0.904929, AUC:0.982611
Epoch:612, d_loss:0.130712, g_loss:5.885184, accuracy:0.962774, AUC:0.995643
Epoch:613, d_loss:0.066006, g_loss:6.309995, accuracy:0.926595, AUC:0.981816
Epoch:614, d_loss:0.130719, g_loss:6.107946, accuracy:0.955762, AUC:0.989258
Epoch:615, d_loss:0.117607, g_loss:5.951826, accuracy:0.940167, AUC:0.980132
Epoch:616, d_loss:0.138285, g_loss:5.454540, accuracy:0.928357, AUC:0.986524
Epoch:617, d_loss:0.107110, g_loss:6.398640, accuracy:0.938048, AUC:0.993412
Epoch:618, d_loss:0.102728, g_loss:5.929277, accuracy:0.942893, AUC:0.988180
Epoch:619, d_loss:0.123028, g_loss:5.919162, accuracy:0.961452, AUC:0.994751
Epoch:620, d_loss:0.081987, g_loss:5.830968, accuracy:0.931429, AUC:0.989371
Epoch:621, d_loss:0.109040, g_loss:5.973792, accuracy:0.935107, AUC:0.987757
Epoch:622, d_loss:0.098937, g_loss:6.170189, accuracy:0.947143, AUC:0.989854
Epoch:623, d_loss:0.099390, g_loss:6.008451, accuracy:0.966024, AUC:0.995264
Epoch:624, d_loss:0.100932, g_loss:5.997196, accuracy:0.804381, AUC:0.981157
Epoch:625, d_loss:0.097131, g_loss:6.318699, accuracy:0.820202, AUC:0.977484
Epoch:626, d_loss:0.167884, g_loss:6.133373, accuracy:0.934905, AUC:0.993071
Epoch:627, d_loss:0.088788, g_loss:6.304166, accuracy:0.900821, AUC:0.980024
Epoch:628, d_loss:0.101165, g_loss:6.224615, accuracy:0.920833, AUC:0.986852
Epoch:629, d_loss:0.127681, g_loss:6.183495, accuracy:0.949381, AUC:0.986987
Epoch:630, d_loss:0.105847, g_loss:5.870075, accuracy:0.857857, AUC:0.986072
Epoch:631, d_loss:0.094642, g_loss:5.941588, accuracy:0.869536, AUC:0.985135
Epoch:632, d_loss:0.083834, g_loss:6.197042, accuracy:0.932631, AUC:0.989121
Epoch:633, d_loss:0.128170, g_loss:6.064734, accuracy:0.970095, AUC:0.994828
Epoch:634, d_loss:0.115188, g_loss:6.806531, accuracy:0.864000, AUC:0.971271
Epoch:635, d_loss:0.107451, g_loss:5.908390, accuracy:0.954560, AUC:0.991359
Epoch:636, d_loss:0.125553, g_loss:6.065533, accuracy:0.905298, AUC:0.993470
Epoch:637, d_loss:0.092079, g_loss:6.473591, accuracy:0.941488, AUC:0.988371
Epoch:638, d_loss:0.128278, g_loss:6.236431, accuracy:0.932643, AUC:0.988486
Epoch:639, d_loss:0.124710, g_loss:5.857805, accuracy:0.892512, AUC:0.985169
Epoch:640, d_loss:0.083662, g_loss:6.132327, accuracy:0.946179, AUC:0.992537
Epoch:641, d_loss:0.118905, g_loss:5.739061, accuracy:0.961464, AUC:0.991985
Epoch:642, d_loss:0.131434, g_loss:6.080054, accuracy:0.958488, AUC:0.990171
Epoch:643, d_loss:0.107910, g_loss:5.769645, accuracy:0.957893, AUC:0.988613
Epoch:644, d_loss:0.094860, g_loss:6.099168, accuracy:0.960560, AUC:0.992835
Epoch:645, d_loss:0.107447, g_loss:6.296738, accuracy:0.813560, AUC:0.947398
Epoch:646, d_loss:0.093389, g_loss:6.202766, accuracy:0.958667, AUC:0.992161
Epoch:647, d_loss:0.129772, g_loss:5.844794, accuracy:0.882940, AUC:0.975713
Epoch:648, d_loss:0.083700, g_loss:6.100433, accuracy:0.781810, AUC:0.964686
Epoch:649, d_loss:0.115105, g_loss:6.629955, accuracy:0.907369, AUC:0.985103
Epoch:650, d_loss:0.170006, g_loss:5.614356, accuracy:0.927274, AUC:0.972135
Epoch:651, d_loss:0.090052, g_loss:5.751386, accuracy:0.940214, AUC:0.987831
Epoch:652, d_loss:0.157415, g_loss:6.228714, accuracy:0.943643, AUC:0.987351
Epoch:653, d_loss:0.072338, g_loss:6.118211, accuracy:0.935429, AUC:0.977384
Epoch:654, d_loss:0.114457, g_loss:5.365719, accuracy:0.924905, AUC:0.982389
Epoch:655, d_loss:0.101571, g_loss:5.862843, accuracy:0.975369, AUC:0.996258
Epoch:656, d_loss:0.125177, g_loss:5.868646, accuracy:0.904524, AUC:0.966686
Epoch:657, d_loss:0.195147, g_loss:6.373850, accuracy:0.960071, AUC:0.990597
Epoch:658, d_loss:0.098952, g_loss:6.177013, accuracy:0.894345, AUC:0.971439
Epoch:659, d_loss:0.195687, g_loss:5.774056, accuracy:0.944060, AUC:0.988083
Epoch:660, d_loss:0.100618, g_loss:6.136115, accuracy:0.940024, AUC:0.985780
Epoch:661, d_loss:0.129405, g_loss:5.905527, accuracy:0.930548, AUC:0.981346
Epoch:662, d_loss:0.098475, g_loss:6.029114, accuracy:0.944286, AUC:0.990057
Epoch:663, d_loss:0.085773, g_loss:6.082324, accuracy:0.963214, AUC:0.993221
Epoch:664, d_loss:0.112220, g_loss:5.675978, accuracy:0.959964, AUC:0.988747
Epoch:665, d_loss:0.092000, g_loss:6.108706, accuracy:0.936798, AUC:0.990546
Epoch:666, d_loss:0.144068, g_loss:5.557775, accuracy:0.938476, AUC:0.992618
Epoch:667, d_loss:0.111970, g_loss:5.652993, accuracy:0.855988, AUC:0.967059
Epoch:668, d_loss:0.203587, g_loss:5.848067, accuracy:0.928012, AUC:0.979811
Epoch:669, d_loss:0.109859, g_loss:5.799406, accuracy:0.875286, AUC:0.966255
Epoch:670, d_loss:0.124972, g_loss:5.490053, accuracy:0.908298, AUC:0.971034
Epoch:671, d_loss:0.114654, g_loss:6.061728, accuracy:0.922869, AUC:0.977966
Epoch:672, d_loss:0.091394, g_loss:6.326465, accuracy:0.908369, AUC:0.973728
Epoch:673, d_loss:0.131302, g_loss:6.076204, accuracy:0.949155, AUC:0.987503
Epoch:674, d_loss:0.098825, g_loss:6.406799, accuracy:0.920726, AUC:0.985657
Epoch:675, d_loss:0.102023, g_loss:5.475666, accuracy:0.910012, AUC:0.981537
Epoch:676, d_loss:0.076472, g_loss:5.933988, accuracy:0.955631, AUC:0.995178
Epoch:677, d_loss:0.107902, g_loss:6.269098, accuracy:0.897893, AUC:0.977463
Epoch:678, d_loss:0.103514, g_loss:5.885916, accuracy:0.940333, AUC:0.990837
Epoch:679, d_loss:0.097683, g_loss:6.134706, accuracy:0.937310, AUC:0.984363
Epoch:680, d_loss:0.099625, g_loss:6.053278, accuracy:0.961869, AUC:0.994191
Epoch:681, d_loss:0.137820, g_loss:6.331500, accuracy:0.819167, AUC:0.974239
Epoch:682, d_loss:0.078158, g_loss:6.083430, accuracy:0.939274, AUC:0.986450
Epoch:683, d_loss:0.143304, g_loss:5.537621, accuracy:0.899369, AUC:0.988191
Epoch:684, d_loss:0.114271, g_loss:6.371948, accuracy:0.928952, AUC:0.979916
Epoch:685, d_loss:0.138019, g_loss:6.002611, accuracy:0.943476, AUC:0.985350
Epoch:686, d_loss:0.121307, g_loss:6.446516, accuracy:0.860476, AUC:0.975164
Epoch:687, d_loss:0.174323, g_loss:5.719744, accuracy:0.937238, AUC:0.990439
Epoch:688, d_loss:0.117468, g_loss:6.020416, accuracy:0.907940, AUC:0.983504
Epoch:689, d_loss:0.084956, g_loss:6.450130, accuracy:0.930655, AUC:0.991720
Epoch:690, d_loss:0.129496, g_loss:6.191366, accuracy:0.876750, AUC:0.975489
Epoch:691, d_loss:0.104179, g_loss:6.054064, accuracy:0.868214, AUC:0.979057
Epoch:692, d_loss:0.082761, g_loss:6.002272, accuracy:0.956667, AUC:0.994410
Epoch:693, d_loss:0.086954, g_loss:5.861441, accuracy:0.893964, AUC:0.988472
Epoch:694, d_loss:0.080309, g_loss:6.308361, accuracy:0.929476, AUC:0.979030
Epoch:695, d_loss:0.126254, g_loss:5.702407, accuracy:0.982833, AUC:0.998264
Epoch:696, d_loss:0.133138, g_loss:6.240038, accuracy:0.769643, AUC:0.949432
Epoch:697, d_loss:0.125307, g_loss:6.300401, accuracy:0.963905, AUC:0.996025
Epoch:698, d_loss:0.186127, g_loss:5.848862, accuracy:0.925524, AUC:0.980902
Epoch:699, d_loss:0.140872, g_loss:5.811147, accuracy:0.948619, AUC:0.986558
Epoch:700, d_loss:0.147496, g_loss:5.752964, accuracy:0.965238, AUC:0.995935
Epoch:701, d_loss:0.093534, g_loss:6.022712, accuracy:0.867821, AUC:0.959518
Epoch:702, d_loss:0.156132, g_loss:6.214547, accuracy:0.909905, AUC:0.974911
Epoch:703, d_loss:0.170537, g_loss:5.940531, accuracy:0.934310, AUC:0.990741
Epoch:704, d_loss:0.134717, g_loss:6.081831, accuracy:0.954452, AUC:0.989450
Epoch:705, d_loss:0.107501, g_loss:5.861230, accuracy:0.948143, AUC:0.990513
Epoch:706, d_loss:0.122473, g_loss:5.607648, accuracy:0.855071, AUC:0.977029
Epoch:707, d_loss:0.122218, g_loss:6.362524, accuracy:0.858238, AUC:0.989658
Epoch:708, d_loss:0.140927, g_loss:6.113331, accuracy:0.960571, AUC:0.993924
Epoch:709, d_loss:0.088409, g_loss:5.922442, accuracy:0.936119, AUC:0.986138
Epoch:710, d_loss:0.089470, g_loss:6.023093, accuracy:0.955679, AUC:0.990122
Epoch:711, d_loss:0.121750, g_loss:5.780986, accuracy:0.884476, AUC:0.985410
Epoch:712, d_loss:0.124404, g_loss:6.142077, accuracy:0.964893, AUC:0.992000
Epoch:713, d_loss:0.111923, g_loss:6.158509, accuracy:0.937155, AUC:0.980137
Epoch:714, d_loss:0.128708, g_loss:5.908738, accuracy:0.922262, AUC:0.976843
Epoch:715, d_loss:0.149178, g_loss:6.026486, accuracy:0.833405, AUC:0.987313
Epoch:716, d_loss:0.152995, g_loss:5.849546, accuracy:0.822488, AUC:0.944275
Epoch:717, d_loss:0.097734, g_loss:6.515792, accuracy:0.936095, AUC:0.989281
Epoch:718, d_loss:0.176063, g_loss:6.187440, accuracy:0.971845, AUC:0.994778
Epoch:719, d_loss:0.102800, g_loss:5.925279, accuracy:0.844988, AUC:0.963932
Epoch:720, d_loss:0.129776, g_loss:5.564886, accuracy:0.933131, AUC:0.976951
Epoch:721, d_loss:0.127089, g_loss:6.112531, accuracy:0.959905, AUC:0.990866
Epoch:722, d_loss:0.109955, g_loss:5.949454, accuracy:0.952714, AUC:0.987971
Epoch:723, d_loss:0.132010, g_loss:6.159826, accuracy:0.859048, AUC:0.985328
Epoch:724, d_loss:0.100482, g_loss:5.802021, accuracy:0.875857, AUC:0.973081
Epoch:725, d_loss:0.121128, g_loss:5.696305, accuracy:0.927131, AUC:0.976976
Epoch:726, d_loss:0.078890, g_loss:6.027787, accuracy:0.922429, AUC:0.981354
Epoch:727, d_loss:0.137632, g_loss:5.970093, accuracy:0.870560, AUC:0.995218
Epoch:728, d_loss:0.136964, g_loss:6.140002, accuracy:0.856798, AUC:0.972550
Epoch:729, d_loss:0.104676, g_loss:5.801705, accuracy:0.946929, AUC:0.988556
Epoch:730, d_loss:0.108911, g_loss:5.932624, accuracy:0.925893, AUC:0.991727
Epoch:731, d_loss:0.100696, g_loss:6.166547, accuracy:0.884452, AUC:0.982402
Epoch:732, d_loss:0.131112, g_loss:6.096169, accuracy:0.907786, AUC:0.969801
Epoch:733, d_loss:0.172440, g_loss:6.054119, accuracy:0.833226, AUC:0.973248
Epoch:734, d_loss:0.120857, g_loss:5.872098, accuracy:0.907869, AUC:0.988117
Epoch:735, d_loss:0.125915, g_loss:5.644084, accuracy:0.892714, AUC:0.960188
Epoch:736, d_loss:0.100946, g_loss:5.871668, accuracy:0.887833, AUC:0.981917
Epoch:737, d_loss:0.116172, g_loss:5.969833, accuracy:0.929548, AUC:0.982934
Epoch:738, d_loss:0.120044, g_loss:5.840597, accuracy:0.793571, AUC:0.978323
Epoch:739, d_loss:0.092025, g_loss:6.153018, accuracy:0.943571, AUC:0.983390
Epoch:740, d_loss:0.099906, g_loss:6.038877, accuracy:0.881095, AUC:0.979056
Epoch:741, d_loss:0.136892, g_loss:6.447467, accuracy:0.958690, AUC:0.991608
Epoch:742, d_loss:0.112408, g_loss:5.678551, accuracy:0.961810, AUC:0.990098
Epoch:743, d_loss:0.075448, g_loss:6.157809, accuracy:0.947476, AUC:0.988073
Epoch:744, d_loss:0.098499, g_loss:5.943014, accuracy:0.974238, AUC:0.997346
Epoch:745, d_loss:0.092508, g_loss:6.113839, accuracy:0.892667, AUC:0.978594
Epoch:746, d_loss:0.087770, g_loss:5.895537, accuracy:0.951619, AUC:0.990615
Epoch:747, d_loss:0.145401, g_loss:6.245987, accuracy:0.912298, AUC:0.986569
Epoch:748, d_loss:0.128271, g_loss:6.172382, accuracy:0.943452, AUC:0.986770
Epoch:749, d_loss:0.120413, g_loss:6.067491, accuracy:0.951310, AUC:0.988408
Epoch:750, d_loss:0.125605, g_loss:6.133420, accuracy:0.953202, AUC:0.989233
Epoch:751, d_loss:0.112448, g_loss:5.927020, accuracy:0.857774, AUC:0.978958
Epoch:752, d_loss:0.157789, g_loss:5.978641, accuracy:0.960298, AUC:0.990828
Epoch:753, d_loss:0.103201, g_loss:6.114161, accuracy:0.935548, AUC:0.985726
Epoch:754, d_loss:0.124234, g_loss:5.553539, accuracy:0.921940, AUC:0.974604
Epoch:755, d_loss:0.098307, g_loss:5.675671, accuracy:0.922286, AUC:0.977131
Epoch:756, d_loss:0.102120, g_loss:5.519321, accuracy:0.939405, AUC:0.994446
Epoch:757, d_loss:0.082513, g_loss:5.845795, accuracy:0.866607, AUC:0.959181
Epoch:758, d_loss:0.087632, g_loss:5.708512, accuracy:0.931238, AUC:0.990683
Epoch:759, d_loss:0.151196, g_loss:5.566555, accuracy:0.881369, AUC:0.979592
Epoch:760, d_loss:0.141286, g_loss:5.654372, accuracy:0.963012, AUC:0.991459
Epoch:761, d_loss:0.140757, g_loss:5.957092, accuracy:0.857190, AUC:0.989758
Epoch:762, d_loss:0.145162, g_loss:5.512084, accuracy:0.857560, AUC:0.970772
Epoch:763, d_loss:0.129467, g_loss:5.570251, accuracy:0.861048, AUC:0.962482
Epoch:764, d_loss:0.137461, g_loss:5.931765, accuracy:0.843988, AUC:0.983264
Epoch:765, d_loss:0.102439, g_loss:6.233873, accuracy:0.870000, AUC:0.967404
Epoch:766, d_loss:0.149530, g_loss:6.109094, accuracy:0.963405, AUC:0.991404
Epoch:767, d_loss:0.171330, g_loss:5.627318, accuracy:0.943583, AUC:0.988202
Epoch:768, d_loss:0.113533, g_loss:5.969403, accuracy:0.907071, AUC:0.977717
Epoch:769, d_loss:0.120597, g_loss:5.956702, accuracy:0.877857, AUC:0.974852
Epoch:770, d_loss:0.125895, g_loss:6.056890, accuracy:0.957357, AUC:0.993227
Epoch:771, d_loss:0.102994, g_loss:6.183090, accuracy:0.897631, AUC:0.962856
Epoch:772, d_loss:0.099023, g_loss:6.129323, accuracy:0.959440, AUC:0.992121
Epoch:773, d_loss:0.146157, g_loss:5.709248, accuracy:0.796393, AUC:0.979885
Epoch:774, d_loss:0.108707, g_loss:6.341961, accuracy:0.934631, AUC:0.984174
Epoch:775, d_loss:0.148749, g_loss:6.151721, accuracy:0.911750, AUC:0.988623
Epoch:776, d_loss:0.128592, g_loss:5.673567, accuracy:0.840202, AUC:0.944665
Epoch:777, d_loss:0.172103, g_loss:6.087414, accuracy:0.883226, AUC:0.964348
Epoch:778, d_loss:0.146212, g_loss:5.635280, accuracy:0.880643, AUC:0.967616
Epoch:779, d_loss:0.091872, g_loss:6.589738, accuracy:0.866333, AUC:0.979270
Epoch:780, d_loss:0.099084, g_loss:5.971507, accuracy:0.815702, AUC:0.989353
Epoch:781, d_loss:0.083888, g_loss:5.980905, accuracy:0.916393, AUC:0.977773
Epoch:782, d_loss:0.132168, g_loss:6.234906, accuracy:0.865786, AUC:0.972918
Epoch:783, d_loss:0.117707, g_loss:5.397388, accuracy:0.861440, AUC:0.981540
Epoch:784, d_loss:0.147994, g_loss:5.902656, accuracy:0.954655, AUC:0.990083
Epoch:785, d_loss:0.150333, g_loss:5.645112, accuracy:0.871845, AUC:0.941105
Epoch:786, d_loss:0.121233, g_loss:6.186032, accuracy:0.907869, AUC:0.983690
Epoch:787, d_loss:0.141678, g_loss:5.639534, accuracy:0.915048, AUC:0.979304
Epoch:788, d_loss:0.114700, g_loss:5.949063, accuracy:0.858571, AUC:0.974928
Epoch:789, d_loss:0.140847, g_loss:6.479014, accuracy:0.932012, AUC:0.987038
Epoch:790, d_loss:0.152085, g_loss:5.781447, accuracy:0.935762, AUC:0.978890
Epoch:791, d_loss:0.125434, g_loss:5.459836, accuracy:0.916595, AUC:0.981825
Epoch:792, d_loss:0.129093, g_loss:6.031391, accuracy:0.908369, AUC:0.973791
Epoch:793, d_loss:0.104379, g_loss:6.239796, accuracy:0.910512, AUC:0.979264
Epoch:794, d_loss:0.120969, g_loss:5.736600, accuracy:0.918560, AUC:0.973952
Epoch:795, d_loss:0.126958, g_loss:5.968479, accuracy:0.940524, AUC:0.992131
Epoch:796, d_loss:0.129618, g_loss:5.870033, accuracy:0.815262, AUC:0.955269
Epoch:797, d_loss:0.097117, g_loss:6.008042, accuracy:0.903000, AUC:0.965846
Epoch:798, d_loss:0.158665, g_loss:6.022683, accuracy:0.836583, AUC:0.944812
Epoch:799, d_loss:0.131108, g_loss:6.124910, accuracy:0.935107, AUC:0.986973
Epoch:800, d_loss:0.129949, g_loss:6.176974, accuracy:0.933226, AUC:0.983709
Epoch:801, d_loss:0.150633, g_loss:5.680827, accuracy:0.743750, AUC:0.949827
Epoch:802, d_loss:0.127582, g_loss:5.537059, accuracy:0.894619, AUC:0.958092
Epoch:803, d_loss:0.111541, g_loss:5.489213, accuracy:0.947440, AUC:0.984512
Epoch:804, d_loss:0.134496, g_loss:5.839081, accuracy:0.889512, AUC:0.970211
Epoch:805, d_loss:0.110800, g_loss:6.133703, accuracy:0.937595, AUC:0.980686
Epoch:806, d_loss:0.138815, g_loss:5.856695, accuracy:0.841714, AUC:0.953965
Epoch:807, d_loss:0.135102, g_loss:5.914082, accuracy:0.885500, AUC:0.984248
Epoch:808, d_loss:0.122800, g_loss:5.923324, accuracy:0.960595, AUC:0.989539
Epoch:809, d_loss:0.121619, g_loss:5.856308, accuracy:0.922857, AUC:0.974866
Epoch:810, d_loss:0.115593, g_loss:6.154803, accuracy:0.929524, AUC:0.982931
Epoch:811, d_loss:0.083635, g_loss:6.225306, accuracy:0.941345, AUC:0.989702
Epoch:812, d_loss:0.114961, g_loss:5.812478, accuracy:0.841976, AUC:0.984118
Epoch:813, d_loss:0.098483, g_loss:6.035475, accuracy:0.887000, AUC:0.986548
Epoch:814, d_loss:0.088589, g_loss:5.916929, accuracy:0.910690, AUC:0.980734
Epoch:815, d_loss:0.190950, g_loss:5.977135, accuracy:0.824298, AUC:0.978106
Epoch:816, d_loss:0.112483, g_loss:6.550988, accuracy:0.928155, AUC:0.980106
Epoch:817, d_loss:0.137263, g_loss:5.809434, accuracy:0.956560, AUC:0.989306
Epoch:818, d_loss:0.095409, g_loss:6.132555, accuracy:0.795143, AUC:0.970978
Epoch:819, d_loss:0.146322, g_loss:6.020476, accuracy:0.927071, AUC:0.976060
Epoch:820, d_loss:0.100859, g_loss:6.286836, accuracy:0.962143, AUC:0.991186
Epoch:821, d_loss:0.139345, g_loss:5.826086, accuracy:0.887905, AUC:0.976824
Epoch:822, d_loss:0.097690, g_loss:5.873246, accuracy:0.926500, AUC:0.979204
Epoch:823, d_loss:0.099789, g_loss:6.379055, accuracy:0.926714, AUC:0.989969
Epoch:824, d_loss:0.112475, g_loss:5.590096, accuracy:0.931048, AUC:0.985325
Epoch:825, d_loss:0.087825, g_loss:5.852357, accuracy:0.941167, AUC:0.985437
Epoch:826, d_loss:0.148186, g_loss:5.934766, accuracy:0.803762, AUC:0.945066
Epoch:827, d_loss:0.132943, g_loss:5.966840, accuracy:0.857845, AUC:0.981542
Epoch:828, d_loss:0.185905, g_loss:5.434254, accuracy:0.932429, AUC:0.976815
Epoch:829, d_loss:0.135877, g_loss:5.568925, accuracy:0.915536, AUC:0.970364
Epoch:830, d_loss:0.097398, g_loss:6.212654, accuracy:0.899286, AUC:0.975023
Epoch:831, d_loss:0.120253, g_loss:5.569920, accuracy:0.940738, AUC:0.985462
Epoch:832, d_loss:0.098259, g_loss:6.114593, accuracy:0.949357, AUC:0.992816
Epoch:833, d_loss:0.085755, g_loss:5.947034, accuracy:0.950345, AUC:0.990531
Epoch:834, d_loss:0.128679, g_loss:5.747793, accuracy:0.876845, AUC:0.982705
Epoch:835, d_loss:0.081166, g_loss:6.045760, accuracy:0.923440, AUC:0.978890
Epoch:836, d_loss:0.162390, g_loss:5.536468, accuracy:0.935321, AUC:0.982694
Epoch:837, d_loss:0.118187, g_loss:5.809713, accuracy:0.808464, AUC:0.947229
Epoch:838, d_loss:0.148693, g_loss:6.169950, accuracy:0.937333, AUC:0.984866
Epoch:839, d_loss:0.126491, g_loss:6.637860, accuracy:0.912202, AUC:0.986971
Epoch:840, d_loss:0.128214, g_loss:5.736769, accuracy:0.886821, AUC:0.979880
Epoch:841, d_loss:0.134421, g_loss:5.813989, accuracy:0.866429, AUC:0.944068
Epoch:842, d_loss:0.138789, g_loss:6.021732, accuracy:0.919024, AUC:0.973125
Epoch:843, d_loss:0.129835, g_loss:5.642156, accuracy:0.942310, AUC:0.982284
Epoch:844, d_loss:0.126397, g_loss:6.278370, accuracy:0.891024, AUC:0.989655
Epoch:845, d_loss:0.114655, g_loss:5.930965, accuracy:0.909988, AUC:0.969541
Epoch:846, d_loss:0.100804, g_loss:6.040424, accuracy:0.821369, AUC:0.978861
Epoch:847, d_loss:0.130195, g_loss:5.467538, accuracy:0.899988, AUC:0.965019
Epoch:848, d_loss:0.089175, g_loss:5.889319, accuracy:0.962321, AUC:0.994812
Epoch:849, d_loss:0.130854, g_loss:5.826790, accuracy:0.877012, AUC:0.976595
Epoch:850, d_loss:0.105789, g_loss:5.513053, accuracy:0.841024, AUC:0.972610
Epoch:851, d_loss:0.123731, g_loss:5.983550, accuracy:0.926083, AUC:0.987107
Epoch:852, d_loss:0.126688, g_loss:5.661203, accuracy:0.925333, AUC:0.976178
Epoch:853, d_loss:0.091519, g_loss:6.247187, accuracy:0.763000, AUC:0.960723
Epoch:854, d_loss:0.137124, g_loss:5.802152, accuracy:0.921500, AUC:0.976146
Epoch:855, d_loss:0.114955, g_loss:6.040704, accuracy:0.858464, AUC:0.989454
Epoch:856, d_loss:0.103562, g_loss:5.714250, accuracy:0.856214, AUC:0.988104
Epoch:857, d_loss:0.168968, g_loss:5.689659, accuracy:0.902333, AUC:0.971294
Epoch:858, d_loss:0.156183, g_loss:5.536794, accuracy:0.910250, AUC:0.972826
Epoch:859, d_loss:0.116109, g_loss:5.761109, accuracy:0.884321, AUC:0.975461
Epoch:860, d_loss:0.110799, g_loss:5.948968, accuracy:0.927560, AUC:0.986699
Epoch:861, d_loss:0.152463, g_loss:5.772094, accuracy:0.950690, AUC:0.989666
Epoch:862, d_loss:0.107399, g_loss:6.065192, accuracy:0.905071, AUC:0.964683
Epoch:863, d_loss:0.146365, g_loss:5.575047, accuracy:0.892345, AUC:0.959213
Epoch:864, d_loss:0.104200, g_loss:5.750233, accuracy:0.928702, AUC:0.982224
Epoch:865, d_loss:0.117445, g_loss:5.987871, accuracy:0.873167, AUC:0.984733
Epoch:866, d_loss:0.104319, g_loss:6.185202, accuracy:0.928869, AUC:0.980731
Epoch:867, d_loss:0.125728, g_loss:5.473974, accuracy:0.915476, AUC:0.982850
Epoch:868, d_loss:0.138240, g_loss:6.348680, accuracy:0.966488, AUC:0.992116
Epoch:869, d_loss:0.126702, g_loss:5.408978, accuracy:0.882417, AUC:0.959952
Epoch:870, d_loss:0.109747, g_loss:5.762968, accuracy:0.913940, AUC:0.975706
Epoch:871, d_loss:0.109370, g_loss:5.957576, accuracy:0.934357, AUC:0.981378
Epoch:872, d_loss:0.139985, g_loss:6.083799, accuracy:0.950786, AUC:0.992414
Epoch:873, d_loss:0.110035, g_loss:5.737137, accuracy:0.932226, AUC:0.984643
Epoch:874, d_loss:0.103646, g_loss:5.863496, accuracy:0.851262, AUC:0.941235
Epoch:875, d_loss:0.124268, g_loss:5.563386, accuracy:0.960036, AUC:0.991392
Epoch:876, d_loss:0.172500, g_loss:5.541215, accuracy:0.924655, AUC:0.980044
Epoch:877, d_loss:0.097824, g_loss:5.892498, accuracy:0.777702, AUC:0.974868
Epoch:878, d_loss:0.187349, g_loss:5.393118, accuracy:0.895321, AUC:0.974053
Epoch:879, d_loss:0.136658, g_loss:5.673293, accuracy:0.888679, AUC:0.966093
Epoch:880, d_loss:0.121184, g_loss:5.474224, accuracy:0.930881, AUC:0.983190
Epoch:881, d_loss:0.154715, g_loss:5.716923, accuracy:0.922012, AUC:0.976678
Epoch:882, d_loss:0.110302, g_loss:6.124564, accuracy:0.902440, AUC:0.962672
Epoch:883, d_loss:0.188178, g_loss:5.987539, accuracy:0.899857, AUC:0.973352
Epoch:884, d_loss:0.129073, g_loss:5.675667, accuracy:0.963869, AUC:0.993205
Epoch:885, d_loss:0.125807, g_loss:5.888499, accuracy:0.924500, AUC:0.982900
Epoch:886, d_loss:0.122434, g_loss:6.273860, accuracy:0.930631, AUC:0.988522
Epoch:887, d_loss:0.161815, g_loss:5.808809, accuracy:0.924226, AUC:0.994360
Epoch:888, d_loss:0.130840, g_loss:5.952233, accuracy:0.810571, AUC:0.981565
Epoch:889, d_loss:0.150985, g_loss:5.505743, accuracy:0.926857, AUC:0.977004
Epoch:890, d_loss:0.159409, g_loss:5.674103, accuracy:0.900167, AUC:0.964436
Epoch:891, d_loss:0.120972, g_loss:6.294226, accuracy:0.890714, AUC:0.964365
Epoch:892, d_loss:0.173518, g_loss:5.609308, accuracy:0.913798, AUC:0.986857
Epoch:893, d_loss:0.127642, g_loss:5.861459, accuracy:0.858452, AUC:0.986353
Epoch:894, d_loss:0.112385, g_loss:5.988540, accuracy:0.867250, AUC:0.957684
Epoch:895, d_loss:0.094264, g_loss:5.924504, accuracy:0.926190, AUC:0.975976
Epoch:896, d_loss:0.113729, g_loss:5.360259, accuracy:0.938881, AUC:0.983683
Epoch:897, d_loss:0.095382, g_loss:5.532877, accuracy:0.946381, AUC:0.988513
Epoch:898, d_loss:0.134133, g_loss:6.019868, accuracy:0.882964, AUC:0.986380
Epoch:899, d_loss:0.098576, g_loss:5.751451, accuracy:0.729214, AUC:0.877278
Epoch:900, d_loss:0.152933, g_loss:5.686993, accuracy:0.959417, AUC:0.990848
Epoch:901, d_loss:0.104209, g_loss:5.637911, accuracy:0.903381, AUC:0.970185
Epoch:902, d_loss:0.117846, g_loss:5.714909, accuracy:0.949738, AUC:0.985780
Epoch:903, d_loss:0.127624, g_loss:5.656970, accuracy:0.930345, AUC:0.978802
Epoch:904, d_loss:0.080947, g_loss:5.977066, accuracy:0.922369, AUC:0.982209
Epoch:905, d_loss:0.149603, g_loss:5.761589, accuracy:0.958893, AUC:0.989655
Epoch:906, d_loss:0.140102, g_loss:5.731617, accuracy:0.864274, AUC:0.988161
Epoch:907, d_loss:0.144005, g_loss:5.777527, accuracy:0.943238, AUC:0.986887
Epoch:908, d_loss:0.151625, g_loss:5.816535, accuracy:0.884988, AUC:0.965426
Epoch:909, d_loss:0.097166, g_loss:5.523342, accuracy:0.834286, AUC:0.962171
Epoch:910, d_loss:0.120017, g_loss:5.874125, accuracy:0.933024, AUC:0.983980
Epoch:911, d_loss:0.085726, g_loss:6.195056, accuracy:0.925071, AUC:0.980966
Epoch:912, d_loss:0.136350, g_loss:5.868463, accuracy:0.948012, AUC:0.984636
Epoch:913, d_loss:0.070344, g_loss:6.123452, accuracy:0.940202, AUC:0.980701
Epoch:914, d_loss:0.110799, g_loss:5.492614, accuracy:0.954583, AUC:0.990163
Epoch:915, d_loss:0.103253, g_loss:5.857829, accuracy:0.902226, AUC:0.969512
Epoch:916, d_loss:0.133287, g_loss:5.362263, accuracy:0.948345, AUC:0.986291
Epoch:917, d_loss:0.128310, g_loss:6.223301, accuracy:0.939702, AUC:0.983773
Epoch:918, d_loss:0.163249, g_loss:5.817014, accuracy:0.913726, AUC:0.982222
Epoch:919, d_loss:0.116842, g_loss:5.549168, accuracy:0.936952, AUC:0.982948
Epoch:920, d_loss:0.100635, g_loss:5.961181, accuracy:0.918821, AUC:0.975746
Epoch:921, d_loss:0.115536, g_loss:5.795691, accuracy:0.864095, AUC:0.976507
Epoch:922, d_loss:0.087908, g_loss:5.757625, accuracy:0.900060, AUC:0.969450
Epoch:923, d_loss:0.172948, g_loss:6.170240, accuracy:0.919655, AUC:0.974601
Epoch:924, d_loss:0.131750, g_loss:5.780980, accuracy:0.927155, AUC:0.977653
Epoch:925, d_loss:0.105449, g_loss:5.995741, accuracy:0.938524, AUC:0.978794
Epoch:926, d_loss:0.123277, g_loss:5.941535, accuracy:0.916274, AUC:0.983316
Epoch:927, d_loss:0.142465, g_loss:6.037484, accuracy:0.855857, AUC:0.980916
Epoch:928, d_loss:0.157150, g_loss:5.554653, accuracy:0.878274, AUC:0.981268
Epoch:929, d_loss:0.081308, g_loss:5.817252, accuracy:0.889595, AUC:0.973109
Epoch:930, d_loss:0.135463, g_loss:5.436837, accuracy:0.892857, AUC:0.976092
Epoch:931, d_loss:0.088635, g_loss:5.668280, accuracy:0.854726, AUC:0.961355
Epoch:932, d_loss:0.106507, g_loss:5.495480, accuracy:0.951679, AUC:0.992875
Epoch:933, d_loss:0.155103, g_loss:5.669253, accuracy:0.822274, AUC:0.953848
Epoch:934, d_loss:0.122006, g_loss:6.362940, accuracy:0.909810, AUC:0.970048
Epoch:935, d_loss:0.097005, g_loss:6.023756, accuracy:0.950607, AUC:0.988470
Epoch:936, d_loss:0.115977, g_loss:5.650770, accuracy:0.902238, AUC:0.986712
Epoch:937, d_loss:0.153787, g_loss:5.908469, accuracy:0.940940, AUC:0.983296
Epoch:938, d_loss:0.124719, g_loss:5.396062, accuracy:0.853321, AUC:0.973585
Epoch:939, d_loss:0.199724, g_loss:5.408403, accuracy:0.877548, AUC:0.961503
Epoch:940, d_loss:0.104777, g_loss:5.908904, accuracy:0.906536, AUC:0.971003
Epoch:941, d_loss:0.104069, g_loss:5.769778, accuracy:0.944845, AUC:0.987162
Epoch:942, d_loss:0.099154, g_loss:5.728420, accuracy:0.862702, AUC:0.978656
Epoch:943, d_loss:0.080075, g_loss:6.000546, accuracy:0.963071, AUC:0.992568
Epoch:944, d_loss:0.130393, g_loss:5.603393, accuracy:0.926893, AUC:0.978290
Epoch:945, d_loss:0.072724, g_loss:6.234395, accuracy:0.913750, AUC:0.980009
Epoch:946, d_loss:0.107638, g_loss:6.494443, accuracy:0.967417, AUC:0.994320
Epoch:947, d_loss:0.165285, g_loss:6.652368, accuracy:0.954107, AUC:0.989457
Epoch:948, d_loss:0.129377, g_loss:6.248029, accuracy:0.935893, AUC:0.994034
Epoch:949, d_loss:0.099325, g_loss:5.915551, accuracy:0.934274, AUC:0.978310
Epoch:950, d_loss:0.084145, g_loss:5.966546, accuracy:0.841560, AUC:0.979531
Epoch:951, d_loss:0.098719, g_loss:5.674295, accuracy:0.899762, AUC:0.983580
Epoch:952, d_loss:0.067424, g_loss:5.852781, accuracy:0.869119, AUC:0.979929
Epoch:953, d_loss:0.189668, g_loss:5.696758, accuracy:0.849833, AUC:0.961343
Epoch:954, d_loss:0.162413, g_loss:5.565835, accuracy:0.826798, AUC:0.974238
Epoch:955, d_loss:0.137116, g_loss:6.251512, accuracy:0.917452, AUC:0.973604
Epoch:956, d_loss:0.126331, g_loss:5.826392, accuracy:0.935714, AUC:0.984134
Epoch:957, d_loss:0.103156, g_loss:5.493851, accuracy:0.943345, AUC:0.984244
Epoch:958, d_loss:0.120939, g_loss:5.565445, accuracy:0.880750, AUC:0.990347
Epoch:959, d_loss:0.111928, g_loss:5.587272, accuracy:0.921321, AUC:0.982477
Epoch:960, d_loss:0.115210, g_loss:5.515973, accuracy:0.810845, AUC:0.960795
Epoch:961, d_loss:0.098311, g_loss:6.083838, accuracy:0.883869, AUC:0.975495
Epoch:962, d_loss:0.157095, g_loss:5.727165, accuracy:0.901381, AUC:0.964010
Epoch:963, d_loss:0.134754, g_loss:5.824664, accuracy:0.893679, AUC:0.966179
Epoch:964, d_loss:0.112979, g_loss:5.907776, accuracy:0.847417, AUC:0.974836
Epoch:965, d_loss:0.127740, g_loss:5.700751, accuracy:0.875917, AUC:0.975458
Epoch:966, d_loss:0.092536, g_loss:5.908080, accuracy:0.929286, AUC:0.984216
Epoch:967, d_loss:0.105001, g_loss:5.821704, accuracy:0.925464, AUC:0.976263
Epoch:968, d_loss:0.136423, g_loss:5.862754, accuracy:0.916940, AUC:0.993363
Epoch:969, d_loss:0.103039, g_loss:6.012010, accuracy:0.939214, AUC:0.989753
Epoch:970, d_loss:0.157880, g_loss:5.548028, accuracy:0.864762, AUC:0.958704
Epoch:971, d_loss:0.097394, g_loss:5.852093, accuracy:0.889155, AUC:0.982805
Epoch:972, d_loss:0.104481, g_loss:6.139295, accuracy:0.943131, AUC:0.983693
Epoch:973, d_loss:0.172332, g_loss:5.659040, accuracy:0.969369, AUC:0.993078
Epoch:974, d_loss:0.123343, g_loss:5.695590, accuracy:0.874524, AUC:0.956476
Epoch:975, d_loss:0.105774, g_loss:5.458178, accuracy:0.863214, AUC:0.948141
Epoch:976, d_loss:0.152762, g_loss:5.658334, accuracy:0.953726, AUC:0.991416
Epoch:977, d_loss:0.102428, g_loss:6.261888, accuracy:0.844060, AUC:0.991709
Epoch:978, d_loss:0.131457, g_loss:5.614196, accuracy:0.819000, AUC:0.974243
Epoch:979, d_loss:0.118071, g_loss:5.510216, accuracy:0.921333, AUC:0.981141
Epoch:980, d_loss:0.117198, g_loss:5.504435, accuracy:0.923131, AUC:0.981138
Epoch:981, d_loss:0.111742, g_loss:6.030589, accuracy:0.899464, AUC:0.977139
Epoch:982, d_loss:0.088624, g_loss:5.691006, accuracy:0.886548, AUC:0.977632
Epoch:983, d_loss:0.095196, g_loss:5.939431, accuracy:0.799179, AUC:0.934625
Epoch:984, d_loss:0.119924, g_loss:5.960817, accuracy:0.923250, AUC:0.981693
Epoch:985, d_loss:0.086000, g_loss:5.535325, accuracy:0.945381, AUC:0.988902
Epoch:986, d_loss:0.126156, g_loss:5.963750, accuracy:0.910226, AUC:0.977143
Epoch:987, d_loss:0.093978, g_loss:6.155254, accuracy:0.942619, AUC:0.990271
Epoch:988, d_loss:0.116684, g_loss:5.541513, accuracy:0.871476, AUC:0.988466
Epoch:989, d_loss:0.102026, g_loss:6.074908, accuracy:0.948690, AUC:0.987441
Epoch:990, d_loss:0.124258, g_loss:5.857306, accuracy:0.933964, AUC:0.984180
Epoch:991, d_loss:0.129127, g_loss:5.688305, accuracy:0.879869, AUC:0.978089
Epoch:992, d_loss:0.123470, g_loss:5.758518, accuracy:0.897988, AUC:0.966999
Epoch:993, d_loss:0.110957, g_loss:5.448343, accuracy:0.932024, AUC:0.982560
Epoch:994, d_loss:0.082421, g_loss:6.043900, accuracy:0.936548, AUC:0.984089
Epoch:995, d_loss:0.123207, g_loss:5.705862, accuracy:0.960321, AUC:0.991538
Epoch:996, d_loss:0.111102, g_loss:5.779712, accuracy:0.934500, AUC:0.986859
Epoch:997, d_loss:0.118481, g_loss:5.778784, accuracy:0.910095, AUC:0.985309
Epoch:998, d_loss:0.132374, g_loss:5.593990, accuracy:0.825869, AUC:0.969515
Epoch:999, d_loss:0.099673, g_loss:6.383139, accuracy:0.945226, AUC:0.990201
/content/drive/My Drive/medGAN/mixed_binary/-999
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.