snapshot...

modules/deeplearning/icing_fcn.py

@@ -33,7 +33,7 @@ TRIPLET = False
 CONV3D = False
 
 NOISE_TRAINING = False
-NOISE_STDDEV = 0.01
+NOISE_STDDEV = 0.10
 
 img_width = 16
 
@@ -75,45 +75,6 @@ zero_out_params = ['cld_reff_dcomp', 'cld_opd_dcomp', 'iwc_dcomp', 'lwc_dcomp']
 DO_ZERO_OUT = False
 
 
-# def build_residual_block(input, drop_rate, num_neurons, activation, block_name, doDropout=True, doBatchNorm=True):
-#     with tf.name_scope(block_name):
-#         if doDropout:
-#             fc = tf.keras.layers.Dropout(drop_rate)(input)
-#             fc = tf.keras.layers.Dense(num_neurons, activation=activation)(fc)
-#         else:
-#             fc = tf.keras.layers.Dense(num_neurons, activation=activation)(input)
-#         if doBatchNorm:
-#             fc = tf.keras.layers.BatchNormalization()(fc)
-#         print(fc.shape)
-#         fc_skip = fc
-#
-#         if doDropout:
-#             fc = tf.keras.layers.Dropout(drop_rate)(fc)
-#         fc = tf.keras.layers.Dense(num_neurons, activation=activation)(fc)
-#         if doBatchNorm:
-#             fc = tf.keras.layers.BatchNormalization()(fc)
-#         print(fc.shape)
-#
-#         if doDropout:
-#             fc = tf.keras.layers.Dropout(drop_rate)(fc)
-#         fc = tf.keras.layers.Dense(num_neurons, activation=activation)(fc)
-#         if doBatchNorm:
-#             fc = tf.keras.layers.BatchNormalization()(fc)
-#         print(fc.shape)
-#
-#         if doDropout:
-#             fc = tf.keras.layers.Dropout(drop_rate)(fc)
-#         fc = tf.keras.layers.Dense(num_neurons, activation=None)(fc)
-#         if doBatchNorm:
-#             fc = tf.keras.layers.BatchNormalization()(fc)
-#
-#         fc = fc + fc_skip
-#         fc = tf.keras.layers.LeakyReLU()(fc)
-#         print(fc.shape)
-#
-#     return fc
-
-
 def build_residual_block_1x1(input_layer, num_filters, activation, block_name, padding='SAME', drop_rate=0.5,
                              do_drop_out=True, do_batch_norm=True):
 
@@ -599,16 +560,27 @@ class IcingIntensityFCN:
 
         num_filters = len(self.train_params) * 4
 
-        if NOISE_TRAINING:
-            input_2d = tf.keras.layers.GaussianNoise(stddev=NOISE_STDDEV)(self.inputs[0])
-        else:
         input_2d = self.inputs[0]
+        conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding=padding, activation=None)(input_2d)
+        print(conv.shape)
+        skip = conv
 
-        conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding=padding, activation=activation)(input_2d)
+        if NOISE_TRAINING:
+            conv = tf.keras.layers.GaussianNoise(stddev=NOISE_STDDEV)(conv)
+
+        conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding=padding, activation=activation)(conv)
         conv = tf.keras.layers.MaxPool2D(padding=padding)(conv)
         conv = tf.keras.layers.BatchNormalization()(conv)
         print(conv.shape)
 
+        skip = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, activation=None)(skip)
+        skip = tf.keras.layers.MaxPool2D(padding=padding)(skip)
+        skip = tf.keras.layers.BatchNormalization()(skip)
+
+        conv = conv + skip
+        conv = tf.keras.layers.LeakyReLU()(conv)
+        print(conv.shape)
+
         num_filters *= 2
         conv = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, activation=activation)(conv)
         conv = tf.keras.layers.MaxPool2D(padding=padding)(conv)