snapshot...

modules/deeplearning/cloud_fraction_fcn_abi.py

@@ -3,7 +3,7 @@ import tensorflow as tf
 from util.plot_cm import confusion_matrix_values
 from util.augment import augment_image
 from util.setup_cloud_fraction import logdir, modeldir, now, ancillary_path
-from util.util import EarlyStop, normalize, denormalize, get_grid_values_all, make_tf_callable_generator
+from util.util import EarlyStop, normalize, denormalize, scale2, get_grid_values_all, make_tf_callable_generator
 import glob
 import os, datetime
 import numpy as np
@@ -289,8 +289,7 @@ class SRCNN:
         self.test_data_files = None
         self.test_label_files = None
 
-        # self.n_chans = len(data_params_half) + len(data_params_full) + 1
-        self.n_chans = 6
+        self.n_chans = 5
 
         self.X_img = tf.keras.Input(shape=(None, None, self.n_chans))
 
@@ -327,15 +326,30 @@ 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[:, slc_y, slc_x]
-            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 sub_fields:
+        #     idx = params.index(param)
+        #     tmp = input_data[:, idx, :, :]
+        #     tmp = tmp[:, slc_y, slc_x]
+        #     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)
+
+        rlo = input_data[:, params.index('refl_submin_ch01'), :, :]
+        rlo = rlo[:, slc_y, slc_x]
+        rlo = normalize(rlo, 'refl_0_65um_nom', mean_std_dct)
+
+        rhi = input_data[:, params.index('refl_submax_ch01'), :, :]
+        rhi = rhi[:, slc_y, slc_x]
+        rhi = normalize(rhi, 'refl_0_65um_nom', mean_std_dct)
+        refl_rng = rhi - rlo
+        data_norm.append(refl_rng)
+
+        rstd = input_data[:, params.index('refl_substddev_ch01'), :, :]
+        rstd = rstd[:, slc_y, slc_x]
+        rstd = scale2(rstd, 0.0, 20.0)
+        data_norm.append(rstd)
 
         tmp = input_label[:, label_idx_i, :, :]
         tmp = get_grid_cell_mean(tmp)