snapshot...

modules/deeplearning/icing.py

@@ -14,11 +14,11 @@ LOG_DEVICE_PLACEMENT = False
 
 CACHE_DATA_IN_MEM = True
 
-PROC_BATCH_SIZE = 60
+PROC_BATCH_SIZE = 10240
 PROC_BATCH_BUFFER_SIZE = 50000
 NumLabels = 1
-BATCH_SIZE = 512
-NUM_EPOCHS = 200
+BATCH_SIZE = 256
+NUM_EPOCHS = 20
 
 TRACK_MOVING_AVERAGE = False
 
@@ -350,7 +350,7 @@ class IcingIntensityNN:
         else:
             flat = self.X_img
             n_hidden = self.X_img.shape[1]
-            n_hidden = 100
+            n_hidden = 40
 
         fac = 1
 
@@ -358,11 +358,11 @@ class IcingIntensityNN:
 
         fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_2')
 
-        fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_3')
+        #fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_3')
 
-        fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_4')
+        #fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_4')
 
-        fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_5')
+        #fc = build_residual_block(fc, drop_rate, fac*n_hidden, activation, 'Residual_Block_5')
 
         fc = tf.keras.layers.Dense(n_hidden, activation=activation)(fc)
         fc = tf.keras.layers.BatchNormalization()(fc)
@@ -402,8 +402,8 @@ class IcingIntensityNN:
         self.initial_learning_rate = initial_learning_rate
 
     def build_evaluation(self):
-        self.train_accuracy = tf.keras.metrics.MeanAbsoluteError(name='train_accuracy')
-        self.test_accuracy = tf.keras.metrics.MeanAbsoluteError(name='test_accuracy')
+        self.train_accuracy = tf.keras.metrics.BinaryAccuracy(name='train_accuracy')
+        self.test_accuracy = tf.keras.metrics.BinaryAccuracy(name='test_accuracy')
         self.train_loss = tf.keras.metrics.Mean(name='train_loss')
         self.test_loss = tf.keras.metrics.Mean(name='test_loss')