diff --git a/modules/deeplearning/srcnn_l1b_l2.py b/modules/deeplearning/srcnn_l1b_l2.py
index 682c86bac9399dea471a4657f836dba3a4576b7c..8c989a17c557fa94f956cbbf740c7a56cb834834 100644
--- a/modules/deeplearning/srcnn_l1b_l2.py
+++ b/modules/deeplearning/srcnn_l1b_l2.py
@@ -711,32 +711,23 @@ def run_restore_static(directory, ckpt_dir):
 def run_evaluate_static(in_file, out_file, ckpt_dir):
     h5f = h5py.File(in_file, 'r')
     grd_a = get_grid_values_all(h5f, 'temp_11_0um_nom')
-    grd_a = grd_a[2432:4032, 2432:4032]
-    grd_a = grd_a[::2, ::2]
-
-    grd_b = get_grid_values_all(h5f, 'refl_0_65um_nom')
-    grd_b = grd_b[2432:4032, 2432:4032]
-
-    grd_c = get_grid_values_all(h5f, label_param)
-    grd_c = grd_c[2432:4032, 2432:4032]
-    grd_c = grd_c[::2, ::2]
-
-    leny, lenx = grd_a.shape
-    x = np.arange(lenx)
-    y = np.arange(leny)
-    x_up = np.arange(0, lenx, 0.5)
-    y_up = np.arange(0, leny, 0.5)
-
+    grd_a = grd_a[2432:2944, 2432:2944]
+    grd_a = grd_a[slc_y_2, slc_x_2]
     grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
-    grd_a = resample_2d_linear_one(x, y, grd_a, x_up, y_up)
+    grd_a = resample_2d_linear_one(x_2, y_2, grd_a, t, s)
 
+    grd_b = get_grid_values_all(h5f, 'refl_0_65um_nom')
+    grd_b = grd_b[2432:2944, 2432:2944]
+    grd_b = grd_b[slc_y_2, slc_x_2]
     grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
+    grd_b = resample_2d_linear_one(x_2, y_2, grd_b, t, s)
 
-    if label_param == 'cloud_fraction':
-        grd_c = np.where(np.isnan(grd_c), 0, grd_c)
-    else:
+    grd_c = get_grid_values_all(h5f, label_param)
+    grd_c = grd_c[2432:2944, 2432:2944]
+    grd_c = grd_c[slc_y_2, slc_x_2]
+    if label_param != 'cloud_fraction':
         grd_c = normalize(grd_c, label_param, mean_std_dct)
-    grd_c = resample_2d_linear_one(x, y, grd_c, x_up, y_up)
+    grd_c = resample_2d_linear_one(x_2, y_2, grd_c, t, s)
 
     data = np.stack([grd_a, grd_b, grd_c], axis=2)
     data = np.expand_dims(data, axis=0)