changed to vae.metrics and pinned keras ---vae working

DM.py

@@ -1,39 +1,39 @@
 #!/usr/bin/env python
 # importing numpy, pandas, and matplotlib
+import matplotlib
 import numpy as np
 import pandas as pd
-import matplotlib
-matplotlib.use('agg')
-import matplotlib.pyplot as plt
 
-# importing sklearn
-from sklearn.model_selection import train_test_split
-from sklearn.model_selection import StratifiedKFold
-from sklearn.decomposition import PCA
-from sklearn.random_projection import GaussianRandomProjection
-from sklearn import cluster
-from sklearn.model_selection import GridSearchCV
-from sklearn.svm import SVC
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import roc_auc_score
-from sklearn.metrics import accuracy_score
-from sklearn.metrics import precision_score
-from sklearn.metrics import recall_score
-from sklearn.metrics import f1_score
+matplotlib.use('agg')
+# importing util libraries
+import datetime
+import importlib
+import math
+import os
+import time
 
 # importing keras
 import keras
 import keras.backend as K
-from keras.wrappers.scikit_learn import KerasClassifier
-from keras.callbacks import EarlyStopping, ModelCheckpoint, LambdaCallback
+import matplotlib.pyplot as plt
+from keras.callbacks import EarlyStopping, LambdaCallback, ModelCheckpoint
 from keras.models import Model, load_model
+from keras.wrappers.scikit_learn import KerasClassifier
+from sklearn import cluster
+from sklearn.decomposition import PCA
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import (
+    accuracy_score,
+    f1_score,
+    precision_score,
+    recall_score,
+    roc_auc_score,
+)
 
-# importing util libraries
-import datetime
-import time
-import math
-import os
-import importlib
+# importing sklearn
+from sklearn.model_selection import GridSearchCV, StratifiedKFold, train_test_split
+from sklearn.random_projection import GaussianRandomProjection
+from sklearn.svm import SVC
 
 # importing custom library
 import DNN_models

DNN_models.py

@@ -1,10 +1,24 @@
 
-from keras.models import Sequential, Model
-from keras.layers import Dense, Dropout, Input, Lambda, Conv2D, Conv2DTranspose, MaxPool2D, UpSampling2D, Flatten, Reshape, Cropping2D
-from keras import backend as K
-from keras.losses import mse, binary_crossentropy
 import math
+
 import numpy as np
+from keras import backend as K
+from keras.layers import (
+    Conv2D,
+    Conv2DTranspose,
+    Cropping2D,
+    Dense,
+    Dropout,
+    Flatten,
+    Input,
+    Lambda,
+    MaxPool2D,
+    Reshape,
+    UpSampling2D,
+)
+from keras.losses import binary_crossentropy, mse
+from keras.models import Model, Sequential
+
 
 # create MLP model
 def mlp_model(input_dim, numHiddenLayers=3, numUnits=64, dropout_rate=0.5):
@@ -257,9 +271,9 @@ def variational_AE(dims, act='relu', init='glorot_uniform', output_act = False,
 
     vae.compile(optimizer='adam', )
 
-    vae.metrics_tensors.append(K.mean(reconstruction_loss))
+    vae.metrics.append(K.mean(reconstruction_loss))
     vae.metrics_names.append("recon_loss")
-    vae.metrics_tensors.append(K.mean(beta * kl_loss))
+    vae.metrics.append(K.mean(beta * kl_loss))
     vae.metrics_names.append("kl_loss")
 
     return vae, encoder, decoder

requirements.txt

@@ -4,6 +4,6 @@ scipy
 scikit-learn 
 matplotlib-base 
 psutil 
-keras 
+keras >= 2.3.0
 tensorflow
 h5py