snapshot...

modules/deeplearning/cloud_opd_srcnn_abi.py

@@ -52,10 +52,11 @@ IMG_DEPTH = 1
 
 label_param = 'cld_opd_dcomp'
 
-params = ['temp_11_0um_nom', 'refl_0_65um_nom', label_param]
+params = ['temp_11_0um_nom', 'refl_0_65um_nom', 'refl_submin_ch01', 'refl_submax_ch01', 'refl_substddev_ch01', label_param]
 params_i = ['temp_11_0um_nom', 'refl_0_65um_nom', label_param]
 data_params_half = ['temp_11_0um_nom', 'refl_0_65um_nom']
 data_params_full = ['refl_0_65um_nom']
+sub_fields = ['refl_submin_ch01', 'refl_submax_ch01', 'refl_substddev_ch01']
 
 label_idx_i = params_i.index(label_param)
 label_idx = params.index(label_param)
@@ -199,7 +200,7 @@ class SRCNN:
         self.test_label_files = None
 
         # self.n_chans = len(data_params_half) + len(data_params_full) + 1
-        self.n_chans = 3
+        self.n_chans = 6
 
         self.X_img = tf.keras.Input(shape=(None, None, self.n_chans))
 
@@ -258,6 +259,17 @@ class SRCNN:
             tmp = normalize(tmp, param, mean_std_dct)
             data_norm.append(tmp)
 
+        for param in sub_fields:
+            idx = params.index(param)
+            tmp = input_data[:, idx, :, :]
+            tmp = tmp[:, self.slc_y_m, self.slc_x_m]
+            tmp = self.upsample_nearest(tmp)
+            if param != 'refl_substddev_ch01':
+                tmp = normalize(tmp, 'refl_0_65um_nom', mean_std_dct)
+            else:
+                tmp = np.where(np.isnan(tmp), 0, tmp)
+            data_norm.append(tmp)
+
         # for param in data_params_full:
         #     idx = params_i.index(param)
         #     tmp = input_label[:, idx, :, :]