diff --git a/modules/deeplearning/cloud_opd_srcnn_viirs.py b/modules/deeplearning/cloud_opd_srcnn_viirs.py
index 9c0d4e58d8b9f84ec1cd13e1f95db81501cf31c8..60c6333402ac3489b5d22da4f3175c2394a3a711 100644
--- a/modules/deeplearning/cloud_opd_srcnn_viirs.py
+++ b/modules/deeplearning/cloud_opd_srcnn_viirs.py
@@ -741,20 +741,20 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     # refl_hi = np.squeeze(refl_hi)
     # refl_avg = np.squeeze(refl_avg)
 
-    cld_opd = np.where(np.isnan(cld_opd), 0, cld_opd)
-    cld_opd = cld_opd[nn.slc_y_2, nn.slc_x_2]
-    cld_opd = np.expand_dims(cld_opd, axis=0)
-    cld_opd = nn.upsample(cld_opd)
-    cld_opd = smooth_2d(cld_opd)
-    cld_opd = normalize(cld_opd, label_param, mean_std_dct)
-
-    # cld_opd = np.where(np.isnan(cld_opd_orig), 0, cld_opd_orig)
-    # cld_opd = cld_opd[nn.slc_y_m, nn.slc_x_m]
+    # cld_opd = np.where(np.isnan(cld_opd), 0, cld_opd)
+    # cld_opd = cld_opd[nn.slc_y_2, nn.slc_x_2]
     # cld_opd = np.expand_dims(cld_opd, axis=0)
     # cld_opd = nn.upsample(cld_opd)
     # cld_opd = smooth_2d(cld_opd)
     # cld_opd = normalize(cld_opd, label_param, mean_std_dct)
 
+    cld_opd = np.where(np.isnan(cld_opd_orig), 0, cld_opd_orig)
+    cld_opd = cld_opd[nn.slc_y_m, nn.slc_x_m]
+    cld_opd = np.expand_dims(cld_opd, axis=0)
+    cld_opd = nn.upsample(cld_opd)
+    cld_opd = smooth_2d(cld_opd)
+    cld_opd = normalize(cld_opd, label_param, mean_std_dct)
+
     data = np.stack([bt, refl, cld_opd], axis=3)
     print('input data shape: ', data.shape)
 
@@ -765,19 +765,19 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     # cld_opd_sres = descale(cld_opd_sres, label_param, mean_std_dct)
     _, ylen, xlen, _ = cld_opd_sres.shape
 
-    # cld_opd_sres_out = np.zeros((LEN_Y, LEN_X), dtype=np.float32)
-    # refl_out = np.zeros((LEN_Y, LEN_X), dtype=np.float32)
-    # cld_opd_out = np.zeros((LEN_Y, LEN_X), dtype=np.float32)
-    #
-    # cld_opd_sres_out[border:(border+ylen), border:(border+xlen)] = cld_opd_sres[0, :, :, 0]
-    # refl_out[0:(ylen+2*border), 0:(xlen+2*border)] = refl[0, :, :]
-    # cld_opd_out[0:(ylen+2*border), 0:(xlen+2*border)] = cld_opd[0, :, :]
-
-    cld_opd_sres_out = cld_opd_sres[0, :, :, 0]
-    refl_out = refl[0, :, :]
-    cld_opd_out = cld_opd[0, :, :]
-    cld_opd_hres = cld_opd_hres
-    print(cld_opd_sres_out.shape, refl_out.shape, cld_opd_out.shape, cld_opd_hres.shape)
+    cld_opd_sres_out = np.zeros((LEN_Y, LEN_X), dtype=np.float32)
+    refl_out = np.zeros((LEN_Y, LEN_X), dtype=np.float32)
+    cld_opd_out = np.zeros((LEN_Y, LEN_X), dtype=np.float32)
+
+    cld_opd_sres_out[border:(border+ylen), border:(border+xlen)] = cld_opd_sres[0, :, :, 0]
+    refl_out[0:(ylen+2*border), 0:(xlen+2*border)] = refl[0, :, :]
+    cld_opd_out[0:(ylen+2*border), 0:(xlen+2*border)] = cld_opd[0, :, :]
+
+    # cld_opd_sres_out = cld_opd_sres[0, :, :, 0]
+    # refl_out = refl[0, :, :]
+    # cld_opd_out = cld_opd[0, :, :]
+    # cld_opd_hres = cld_opd_hres
+    # print(cld_opd_sres_out.shape, refl_out.shape, cld_opd_out.shape, cld_opd_hres.shape)
 
     refl_out = denormalize(refl_out, 'refl_0_65um_nom', mean_std_dct)
     cld_opd_out = denormalize(cld_opd_out, label_param, mean_std_dct)