snapshot...

modules/deeplearning/cloud_opd_srcnn_abi.py

@@ -717,16 +717,16 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     refl = np.where(np.isnan(refl), 0, bt)
     refl = refl[slc_y, slc_x]
     refl = np.expand_dims(refl, axis=0)
-    refl = upsample_static(refl, x_2, y_2, t, s, None, None)
-    print(refl.shape)
-    refl = normalize(refl, 'refl_0_65um_nom', mean_std_dct)
+    refl_us = upsample_static(refl, x_2, y_2, t, s, None, None)
+    print(refl_us.shape)
+    refl_us = normalize(refl_us, 'refl_0_65um_nom', mean_std_dct)
     print('REFL done')
 
     bt = np.where(np.isnan(bt), 0, bt)
     bt = bt[slc_y, slc_x]
     bt = np.expand_dims(bt, axis=0)
-    bt = upsample_static(bt, x_2, y_2, t, s, None, None)
-    bt = normalize(bt, 'temp_11_0um_nom', mean_std_dct)
+    bt_us = upsample_static(bt, x_2, y_2, t, s, None, None)
+    bt_us = normalize(bt_us, 'temp_11_0um_nom', mean_std_dct)
     print('BT done')
 
     # refl = get_grid_values_all(h5f, 'super/refl_0_65um')
@@ -743,11 +743,11 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     cld_opd = np.where(np.isnan(cld_opd), 0, cld_opd)
     cld_opd = cld_opd[slc_y, slc_x]
     cld_opd = np.expand_dims(cld_opd, axis=0)
-    cld_opd = upsample_static(cld_opd, x_2, y_2, t, s, None, None)
-    cld_opd = normalize(cld_opd, label_param, mean_std_dct)
+    cld_opd_us = upsample_static(cld_opd, x_2, y_2, t, s, None, None)
+    cld_opd_us = normalize(cld_opd_us, label_param, mean_std_dct)
     print('OPD done')
 
-    data = np.stack([bt, refl, cld_opd], axis=3)
+    data = np.stack([bt_us, refl_us, cld_opd_us], axis=3)
 
     h5f.close()
 
@@ -765,8 +765,8 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
     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, :, :]
 
-    refl_out = denormalize(refl_out, 'refl_0_65um_nom', mean_std_dct)
-    cld_opd_out = denormalize(cld_opd_out, label_param, mean_std_dct)
+    # refl_out = denormalize(refl_out, 'refl_0_65um_nom', mean_std_dct)
+    # cld_opd_out = denormalize(cld_opd_out, label_param, mean_std_dct)
 
     if out_file is not None:
         np.save(out_file, (cld_opd_sres_out, refl_out, cld_opd_out, cld_opd_hres))