snapshot...

modules/deeplearning/espcn_l1b_l2.py

@@ -382,25 +382,24 @@ class ESPCN:
 
         conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_3', scale=scale)
 
-        # conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_4', scale=scale)
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_4', scale=scale)
 
-        # conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_5', scale=scale)
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_5', scale=scale)
 
-        conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, activation=activation, kernel_initializer=kernel_initializer)(conv_b)
+        conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_6', scale=scale)
 
-        conv = conv + conv_b
-        print(conv.shape)
+        conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, kernel_initializer=kernel_initializer)(conv_b)
 
-        conv = tf.keras.layers.Conv2D(IMG_DEPTH * (factor ** 2), 3, padding=padding, activation=activation)(conv)
+        conv = conv + conv_b
         print(conv.shape)
 
-        conv = tf.keras.layers.Conv2D(IMG_DEPTH * (factor ** 2), 3, padding=padding, activation=activation)(conv)
+        conv = tf.keras.layers.Conv2D(num_filters * (factor ** 2), 3, padding=padding, activation=activation)(conv)
         print(conv.shape)
 
         conv = tf.nn.depth_to_space(conv, factor)
         print(conv.shape)
 
-        self.logits = tf.keras.layers.Conv2D(IMG_DEPTH, kernel_size=1, strides=1, padding=padding, name='regression')(conv)
+        self.logits = tf.keras.layers.Conv2D(IMG_DEPTH, kernel_size=3, strides=1, padding=padding, name='regression')(conv)
 
         print(self.logits.shape)