snapshot...

modules/deeplearning/srcnn_l1b_l2.py

@@ -731,7 +731,7 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     grd_a = grd_a[y_0:y_0+sub_y, x_0:x_0+sub_x]
     hr_grd_a = grd_a.copy()
     grd_a = upsample_one(grd_a)
-    grd_a = normalize(grd_a, 'super/temp_11_0um', mean_std_dct)
+    grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
     hr_grd_a = hr_grd_a[y_128, x_128]
 
     # ------------------------------------------------------
@@ -741,7 +741,7 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     hr_grd_b = grd_b.copy()
     hr_grd_b = hr_grd_b[y_128, x_128]
     # Full res:
-    grd_b = normalize(grd_b, 'super/refl_0_65um', mean_std_dct)
+    grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
     grd_b = grd_b[slc_y, slc_x]
 
     grd_c = get_grid_values_all(h5f, 'super/'+label_param)
@@ -752,7 +752,7 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
 
     grd_c = upsample_one(grd_c)
     if label_param != 'cloud_probability':
-        grd_c = normalize(grd_c, 'super/'+label_param, mean_std_dct)
+        grd_c = normalize(grd_c, label_param, mean_std_dct)
 
     data = np.stack([grd_a, grd_b, grd_c], axis=2)
     data = np.expand_dims(data, axis=0)