diff --git a/modules/deeplearning/srcnn_l1b_l2.py b/modules/deeplearning/srcnn_l1b_l2.py
index b7d5153109efbab582b92e6ebeb0946c5cb493fd..560e9f61dc68481084c040fb7f1dff62399cd491 100644
--- a/modules/deeplearning/srcnn_l1b_l2.py
+++ b/modules/deeplearning/srcnn_l1b_l2.py
@@ -672,7 +672,7 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
 
     nn = SRCNN()
     out_sr = nn.run_evaluate(data, ckpt_dir)
-    #out_sr = denormalize(out_sr, label_params[0], mean_std_dct)
+    # out_sr = denormalize(out_sr, label_params[0], mean_std_dct)
     if out_file is not None:
         np.save(out_file, out_sr)
     else:
@@ -682,19 +682,26 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
 def analyze():
     h5f = h5py.File('/Users/tomrink/clavrx_snpp_viirs.A2019071.0000.001.2019071061610.uwssec_B00038187.level2.h5', 'r')
     grd = get_grid_values_all(h5f, 'cloud_fraction')
-    grd = grd[::2, ::2]
+    grd = np.where(np.isnan(grd), 0, grd)
+    grd = grd[1600:, 400:1200]
     print(grd.shape)
-    leny, lenx = grd.shape
+
+    grd_lr = grd[::2, ::2]
+    print(grd_lr.shape)
+    leny, lenx = grd_lr.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 = resample_2d_linear_one(x, y, grd, x_up, y_up)
-    print(grd_a.shape)
+    grd_hr = resample_2d_linear_one(x, y, grd_lr, x_up, y_up)
+    print(grd_hr.shape)
 
     h5f.close()
 
+    return grd, grd_hr
+
 
 if __name__ == "__main__":
     nn = SRCNN()