Fixed autoencoders

Author: vanpelt

keras-autoencoder/autoencoder.py

@@ -4,21 +4,11 @@
 from keras.datasets import mnist
 from keras.datasets import fashion_mnist
 
-from keras.callbacks import Callback
 import numpy as np
+from util import Images
 import wandb
 from wandb.keras import WandbCallback
 
-class Images(Callback):
-    def on_epoch_end(self, epoch, logs):
-        indices = np.random.randint(self.validation_data[0].shape[0], size=8)
-        test_data = self.validation_data[0][indices]
-        pred_data = self.model.predict(test_data)
-        wandb.log({
-             "examples": [
-                   wandb.Image(np.hstack([data, pred_data[i]]), caption=str(i))
-                   for i, data in enumerate(test_data)]
-        }, commit=False)
 
 run = wandb.init()
 config = run.config
@@ -43,7 +33,9 @@ def on_epoch_end(self, epoch, logs):
 decoder.add(Dense(28*28, activation="sigmoid"))
 decoder.add(Reshape((28,28)))
 
-model = Model(encoder, decoder)
+model = Sequential()
+model.add(encoder)
+model.add(decoder)
 
 model.compile(optimizer='adam', loss='mse')
 

keras-autoencoder/autoencoder_cnn.py

@@ -2,21 +2,31 @@
 from keras.models import Model, Sequential
 from keras.datasets import mnist
 from keras.callbacks import Callback
-from autoencoder import Images
 
 import numpy as np
+from util import Images
 import wandb
 from wandb.keras import WandbCallback
+class Images(Callback):
+    def on_epoch_end(self, epoch, logs):
+        indices = np.random.randint(self.validation_data[0].shape[0], size=8)
+        test_data = self.validation_data[0][indices]
+        pred_data = self.model.predict(test_data)
+        wandb.log({
+             "examples": [
+                   wandb.Image(np.hstack([data, pred_data[i]]), caption=str(i))
+                   for i, data in enumerate(test_data)]
+        }, commit=False)
 
 run = wandb.init()
 config = run.config
 
 config.epochs = 10
 
-(x_train, _), (x_test, _) = mnist.load_data()
+(X_train, _), (X_test, _) = mnist.load_data()
 
-x_train = x_train.astype('float32') / 255.
-x_test = x_test.astype('float32') / 255.
+X_train = X_train.astype('float32') / 255.
+X_test = X_test.astype('float32') / 255.
 
 model = Sequential()
 model.add(Reshape((28,28,1), input_shape=(28,28)))
@@ -29,12 +39,10 @@
 
 model.compile(optimizer='adam', loss='mse')
 
-model.fit(x_train, x_train,
-                epochs=config.epochs,
-                validation_data=(x_test, x_test), 
-                callbacks=[Images(), WandbCallback(save_model=False)])
-
-
-model.save('auto-cnn.h5')
+model.fit(X_train, X_train,
+          epochs=config.epochs,
+          validation_data=(X_test, X_test), 
+          callbacks=[Images(), WandbCallback(save_model=False)])
 
 
+model.save('auto-cnn.h5')