snapshot...

modules/deeplearning/cloud_fraction_fcn_abi.py

@@ -790,15 +790,12 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     refl = np.where(np.isnan(refl), 0, refl)
     refl = normalize(refl, 'refl_0_65um_nom', mean_std_dct)
 
-    # refl_lo = get_grid_values_all(h5f, 'refl_submin_ch01')
     refl_lo = get_grid_values_all(h5f, 'refl_0_65um_nom_min_sub')
     refl_lo = refl_lo[0:2500, :]
     refl_lo = normalize(refl_lo, 'refl_0_65um_nom', mean_std_dct)
-    # refl_hi = get_grid_values_all(h5f, 'refl_submax_ch01')
     refl_hi = get_grid_values_all(h5f, 'refl_0_65um_nom_max_sub')
     refl_hi = refl_hi[0:2500, :]
     refl_hi = normalize(refl_hi, 'refl_0_65um_nom', mean_std_dct)
-    # refl_std = get_grid_values_all(h5f, 'refl_substdev_ch01')
     refl_std = get_grid_values_all(h5f, 'refl_0_65um_nom_stddev_sub')
     refl_std = refl_std[0:2500, :]
     refl_std = np.where(np.isnan(refl_std), 0, refl_std)
@@ -807,7 +804,6 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     cp = cp[0:2500, :]
     cp = np.where(np.isnan(cp), 0, cp)
 
-    # data = np.stack([bt, refl_lo, refl_hi, refl_std, cp], axis=2)
     data = np.stack([bt, refl, refl_lo, refl_hi, refl_std, cp], axis=2)
     data = np.expand_dims(data, axis=0)