snapshot...

modules/deeplearning/icing_fcn.py

@@ -87,12 +87,12 @@ def build_residual_block_1x1(input_layer, num_filters, activation, block_name, p
         conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=activation)(input_layer)
         print(conv.shape)
 
-        if do_drop_out:
-            conv = tf.keras.layers.Dropout(drop_rate)(conv)
-        if do_batch_norm:
-            conv = tf.keras.layers.BatchNormalization()(conv)
-        conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=activation)(conv)
-        print(conv.shape)
+        # if do_drop_out:
+        #     conv = tf.keras.layers.Dropout(drop_rate)(conv)
+        # if do_batch_norm:
+        #     conv = tf.keras.layers.BatchNormalization()(conv)
+        # conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=activation)(conv)
+        # print(conv.shape)
 
         if do_drop_out:
             conv = tf.keras.layers.Dropout(drop_rate)(conv)
@@ -582,25 +582,53 @@ class IcingIntensityFCN:
         conv = conv + skip
         conv = tf.keras.layers.LeakyReLU()(conv)
         print(conv.shape)
+        # -----------------------------------------------------------------------------------------------------------
 
+        skip = conv
         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)
         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)
+        # ----------------------------------------------------------------------------------------------------------
+
+        skip = conv
         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)
         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)
+        # -----------------------------------------------------------------------------------------------------------
+
+        skip = conv
         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)
         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)
+
         return conv
 
     def build_fcl(self, input_layer):
@@ -619,6 +647,8 @@ class IcingIntensityFCN:
 
         conv = build_residual_block_1x1(conv, num_filters, activation, 'Residual_Block_2', padding=padding)
 
+        conv = build_residual_block_1x1(conv, num_filters, activation, 'Residual_Block_3', padding=padding)
+
         print(conv.shape)
 
         if NumClasses == 2: