diff --git a/modules/deeplearning/espcn.py b/modules/deeplearning/espcn.py
index f72ed3db6cfdb6f642f37cf67626ff03eb545e18..8e41c165569c4a3a54710b60540d2006346bf762 100644
--- a/modules/deeplearning/espcn.py
+++ b/modules/deeplearning/espcn.py
@@ -200,13 +200,12 @@ class ESPCN:
         label = np.concatenate(label_s)
 
         data = data[:, data_idx, :, :]
-        #data = data[:, data_idx, 3:67, 3:67]
         data = resample(x_70, y_70, data, x_70_2, y_70_2)
         data = np.expand_dims(data, axis=3)
-        # data = tf.image.resize(data, (32, 32)).numpy()
 
         # label = label[:, label_idx, :, :]
-        label = label[:, label_idx, 3:67:2, 3:67:2]
+        # label = label[:, label_idx, 3:67:2, 3:67:2]
+        label = label[:, label_idx, 3:67, 3:67]
         label = np.expand_dims(label, axis=3)
 
         data = data.astype(np.float32)
@@ -370,12 +369,12 @@ class ESPCN:
         conv = conv + conv_b
         print(conv.shape)
 
-        #conv = tf.keras.layers.Conv2D(num_filters * (factor ** 2), 3, padding='same')(conv)
+        conv = tf.keras.layers.Conv2D(num_filters * (factor ** 2), 3, padding='same')(conv)
         # conv = tf.keras.layers.Conv2D((factor ** 2), 3, padding='same')(conv)
         print(conv.shape)
 
-        # conv = tf.nn.depth_to_space(conv, factor)
-        # print(conv.shape)
+        conv = tf.nn.depth_to_space(conv, factor)
+        print(conv.shape)
 
         self.logits = tf.keras.layers.Conv2D(1, kernel_size=3, strides=1, padding=padding, name='regression')(conv)
 
@@ -732,10 +731,9 @@ class ESPCN:
 def prepare(param_idx=1, filename='/Users/tomrink/data_valid_40.npy'):
     nda = np.load(filename)
     #nda = nda[:, param_idx, :, :]
-    nda = nda[:, param_idx, 3:67, 3:67]
-    nda = np.expand_dims(nda, axis=3)
-    # nda_lr = tf.image.resize(nda, (36, 36)).numpy()
-    nda_lr = tf.image.resize(nda, (32, 32)).numpy()
+    nda_lr = nda[:, param_idx, 3:67:2, 3:67:2]
+    # nda_lr = resample(x_70, y_70, nda, x_70_2, y_70_2)
+    nda_lr = np.expand_dims(nda_lr, axis=3)
     return nda_lr