diff --git a/modules/deeplearning/icing_cnn.py b/modules/deeplearning/icing_cnn.py
index d73948e47a00e8fbb4c750a044b6a4d1667d6326..5221e041c2ec230b2c010ccdca82dba44affb5cc 100644
--- a/modules/deeplearning/icing_cnn.py
+++ b/modules/deeplearning/icing_cnn.py
@@ -419,7 +419,7 @@ class IcingIntensityNN:
         momentum = 0.99
 
         # num_filters = 16
-        num_filters = 12
+        num_filters = 24
 
         conv = tf.keras.layers.Conv2D(num_filters, 5, strides=[1, 1], padding=padding, activation=activation)(self.inputs[0])
         conv = tf.keras.layers.MaxPool2D(padding=padding)(conv)
@@ -871,12 +871,16 @@ class IcingIntensityNN:
         return filename, ice_lons, ice_lats
 
 
-def run_restore_static(filename_tst, ckpt_dir_s):
+def run_restore_static(filename_tst, ckpt_dir_s_path):
+    ckpt_dir_s = os.listdir(ckpt_dir_s_path)
     cm_s = []
-    for ckpt_dir in ckpt_dir_s:
+    for ckpt in ckpt_dir_s:
+        ckpt_dir = ckpt_dir_s_path + ckpt
+        if not os.path.isdir(ckpt_dir):
+            continue
         nn = IcingIntensityNN()
         nn.run_restore(filename_tst, ckpt_dir)
-        cm_s.append(tf.math.confusion_matrix(nn.test_labels, nn.test_preds))
+        cm_s.append(tf.math.confusion_matrix(nn.test_labels.flatten(), nn.test_preds.flatten()))
     num = len(cm_s)
     cm_avg = cm_s[0]
     for k in range(num-1):