minor

modules/deeplearning/espcn.py

@@ -60,7 +60,7 @@ data_param = data_params[data_idx]
 label_param = label_params[label_idx]
 
 
-def build_conv2d_block(conv, num_filters, block_name, activation=tf.nn.leaky_relu, padding='SAME'):
+def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.leaky_relu, padding='SAME'):
 
     with tf.name_scope(block_name):
         skip = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, activation=activation)(conv)
@@ -349,13 +349,13 @@ class ESPCN:
         if NOISE_TRAINING:
             conv = conv_b = tf.keras.layers.GaussianNoise(stddev=NOISE_STDDEV)(conv)
 
-        conv_b = build_conv2d_block(conv_b, num_filters, 'Residual_Block_1')
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_1')
 
-        conv_b = build_conv2d_block(conv_b, num_filters, 'Residual_Block_2')
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_2')
 
-        conv_b = build_conv2d_block(conv_b, num_filters, 'Residual_Block_3')
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_3')
 
-        conv_b = build_conv2d_block(conv_b, num_filters, 'Residual_Block_4')
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_4')
 
         conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding)(conv_b)