diff --git a/modules/deeplearning/icing_fcn.py b/modules/deeplearning/icing_fcn.py
index cb5fdaa963e02ce85f4b4ddac3919b26e4b143f9..ba107a56c210ecd7510dd669afe10623e5986eb6 100644
--- a/modules/deeplearning/icing_fcn.py
+++ b/modules/deeplearning/icing_fcn.py
@@ -523,9 +523,9 @@ class IcingIntensityFCN:
         print('num test samples: ', tst_idxs.shape[0])
         print('setup_test_pipeline: Done')
 
-    def setup_eval_pipeline(self, data_dct):
+    def setup_eval_pipeline(self, data_dct, num_tiles=1):
         self.data_dct = data_dct
-        idxs = np.arange(1)
+        idxs = np.arange(num_tiles)
         self.num_data_samples = idxs.shape[0]
 
         self.get_evaluate_dataset(idxs)
@@ -1124,7 +1124,46 @@ def run_evaluate_static_avg(data_dct, ll, cc, ckpt_dir_s_path, day_night='DAY',
     return ice_lons, ice_lats, preds_2d
 
 
-def run_evaluate_static_fcn(data_dct, ckpt_dir_s_path, day_night='DAY', l1b_or_l2='both', prob_thresh=0.5,
+# def run_evaluate_static_fcn(data_dct, ckpt_dir_s_path, day_night='DAY', l1b_or_l2='both', prob_thresh=0.5,
+#                             flight_levels=[0, 1, 2, 3, 4], use_flight_altitude=False):
+#
+#     ckpt_dir_s = os.listdir(ckpt_dir_s_path)
+#     ckpt_dir = ckpt_dir_s_path + ckpt_dir_s[0]
+#
+#     if not use_flight_altitude:
+#         flight_levels = [0]
+#
+#     probs_dct = {flvl: None for flvl in flight_levels}
+#     preds_dct = {flvl: None for flvl in flight_levels}
+#
+#     nn = IcingIntensityFCN(day_night=day_night, l1b_or_l2=l1b_or_l2, use_flight_altitude=use_flight_altitude)
+#     nn.num_data_samples = 1
+#     nn.build_model()
+#     nn.build_training()
+#     nn.build_evaluation()
+#
+#     ckpt = tf.train.Checkpoint(step=tf.Variable(1), model=nn.model)
+#     ckpt_manager = tf.train.CheckpointManager(ckpt, ckpt_dir, max_to_keep=3)
+#     ckpt.restore(ckpt_manager.latest_checkpoint)
+#
+#     for flvl in flight_levels:
+#         nn.flight_level = flvl
+#         nn.setup_eval_pipeline(data_dct)
+#         nn.do_evaluate(ckpt_dir)
+#
+#         probs = nn.test_probs
+#         if NumClasses == 2:
+#             preds = np.where(probs > prob_thresh, 1, 0)
+#         else:
+#             preds = np.argmax(probs, axis=1)
+#
+#         probs_dct[flvl] = probs
+#         preds_dct[flvl] = preds
+#
+#     return preds_dct, probs_dct
+
+
+def run_evaluate_static_fcn(data_dct, num_tiles, ckpt_dir_s_path, day_night='DAY', l1b_or_l2='both', prob_thresh=0.5,
                             flight_levels=[0, 1, 2, 3, 4], use_flight_altitude=False):
 
     ckpt_dir_s = os.listdir(ckpt_dir_s_path)
@@ -1137,7 +1176,7 @@ def run_evaluate_static_fcn(data_dct, ckpt_dir_s_path, day_night='DAY', l1b_or_l
     preds_dct = {flvl: None for flvl in flight_levels}
 
     nn = IcingIntensityFCN(day_night=day_night, l1b_or_l2=l1b_or_l2, use_flight_altitude=use_flight_altitude)
-    nn.num_data_samples = 1
+    nn.num_data_samples = num_tiles
     nn.build_model()
     nn.build_training()
     nn.build_evaluation()
@@ -1148,7 +1187,7 @@ def run_evaluate_static_fcn(data_dct, ckpt_dir_s_path, day_night='DAY', l1b_or_l
 
     for flvl in flight_levels:
         nn.flight_level = flvl
-        nn.setup_eval_pipeline(data_dct)
+        nn.setup_eval_pipeline(data_dct, num_tiles)
         nn.do_evaluate(ckpt_dir)
 
         probs = nn.test_probs