diff --git a/modules/deeplearning/espcn_l1b_l2.py b/modules/deeplearning/espcn_l1b_l2.py
index ba349d134c5bd7ebd6ebcb2ddd1621f082cce055..6dc9e81619bdc6eb1dabc4e6650399782e8b81f3 100644
--- a/modules/deeplearning/espcn_l1b_l2.py
+++ b/modules/deeplearning/espcn_l1b_l2.py
@@ -359,16 +359,12 @@ class ESPCN:
         kernel_initializer = 'he_uniform'
         momentum = 0.99
 
-        num_filters = 64
+        num_filters = 32
 
         input_2d = self.inputs[0]
         print('input: ', input_2d.shape)
-        # conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding='VALID', activation=None)(input_2d)
-        conv = input_2d
-        print('input: ', conv.shape)
 
-        # conv = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, padding=padding)(input_2d)
-        conv = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, padding='VALID', kernel_initializer=kernel_initializer)(input_2d)
+        conv = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, padding='VALID', kernel_initializer=kernel_initializer, activation=activation)(input_2d)
         print(conv.shape)
 
         if NOISE_TRAINING:
@@ -394,8 +390,7 @@ class ESPCN:
         # conv = tf.keras.layers.Conv2D(num_filters * (factor ** 2), 3, padding='same')(conv)
         # print(conv.shape)
 
-        # conv = tf.nn.depth_to_space(conv, factor)
-        # #conv = tf.keras.layers.Conv2DTranspose(num_filters * (factor ** 2), 3, padding='same')(conv)
+        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)
@@ -425,8 +420,6 @@ class ESPCN:
         self.initial_learning_rate = initial_learning_rate
 
     def build_evaluation(self):
-        #self.train_loss = tf.keras.metrics.Mean(name='train_loss')
-        #self.test_loss = tf.keras.metrics.Mean(name='test_loss')
         self.train_accuracy = tf.keras.metrics.MeanAbsoluteError(name='train_accuracy')
         self.test_accuracy = tf.keras.metrics.MeanAbsoluteError(name='test_accuracy')
         self.train_loss = tf.keras.metrics.Mean(name='train_loss')
@@ -590,10 +583,6 @@ class ESPCN:
         self.writer_valid.close()
         self.writer_train_valid_loss.close()
 
-        # f = open(home_dir+'/best_stats_'+now+'.pkl', 'wb')
-        # pickle.dump((best_test_loss, best_test_acc, best_test_recall, best_test_precision, best_test_auc, best_test_f1, best_test_mcc), f)
-        # f.close()
-
     def build_model(self):
         self.build_espcn()
         self.model = tf.keras.Model(self.inputs, self.logits)
@@ -666,27 +655,6 @@ class ESPCN:
         return self.do_evaluate(nda_lr, param, ckpt_dir)
 
 
-def prepare(param_idx=1, filename='/Users/tomrink/data_valid_40.npy'):
-    nda = np.load(filename)
-    # nda = nda[:, param_idx, :, :]
-    nda_lr = nda[:, param_idx, 2:133:2, 2:133:2]
-    # nda_lr = resample(x_134, y_134, nda, x_134_2, y_134_2)
-    nda_lr = np.expand_dims(nda_lr, axis=3)
-    return nda_lr
-
-
-def run_evaluate_static(in_file, out_file, param='temp_11_0um_nom', ckpt_dir='/Users/tomrink/tf_model_sres/run-20220805173619/'):
-    nda = np.load(in_file)
-    nda = np.transpose(nda[0, 2, 3, 1])
-
-    nn = ESPCN()
-    out_sr = nn.run_evaluate(nda, param, ckpt_dir)
-    if out_file is not None:
-        np.save(out_file, out_sr)
-    else:
-        return out_sr
-
-
 if __name__ == "__main__":
     nn = ESPCN()
     nn.run('matchup_filename')