minor

modules/deeplearning/icing_cnn.py

@@ -39,7 +39,7 @@ NOISE_STDDEV = 0.01
 img_width = 16
 
 mean_std_dct = {}
-mean_std_file = homedir+'data/icing/mean_std_lo_hi_l1b.pkl'
+mean_std_file = homedir+'data/icing/mean_std_lo_hi_l2.pkl'
 f = open(mean_std_file, 'rb')
 mean_std_dct_l2 = pickle.load(f)
 f.close()
@@ -60,12 +60,12 @@ train_params_l2 = ['cld_height_acha', 'cld_geo_thick', 'cld_temp_acha', 'cld_pre
 ##                'cld_emiss_acha', 'conv_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp', 'cld_cwp_dcomp', 'iwc_dcomp', 'lwc_dcomp']
                   'cld_emiss_acha', 'conv_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp', 'iwc_dcomp', 'lwc_dcomp']
 # -- DAY L1B --------------------------------
-train_params_l1b = ['temp_10_4um_nom', 'temp_11_0um_nom', 'temp_12_0um_nom', 'temp_13_3um_nom', 'temp_3_75um_nom',
-                    'temp_6_2um_nom', 'temp_6_7um_nom', 'temp_7_3um_nom', 'temp_8_5um_nom', 'temp_9_7um_nom',
-                    'refl_0_47um_nom', 'refl_0_65um_nom', 'refl_0_86um_nom', 'refl_1_38um_nom', 'refl_1_60um_nom']
-# -- NIGHT L1B -------------------------------
 # train_params_l1b = ['temp_10_4um_nom', 'temp_11_0um_nom', 'temp_12_0um_nom', 'temp_13_3um_nom', 'temp_3_75um_nom',
-#                    'temp_6_2um_nom', 'temp_6_7um_nom', 'temp_7_3um_nom', 'temp_8_5um_nom', 'temp_9_7um_nom']
+#                     'temp_6_2um_nom', 'temp_6_7um_nom', 'temp_7_3um_nom', 'temp_8_5um_nom', 'temp_9_7um_nom',
+#                     'refl_0_47um_nom', 'refl_0_65um_nom', 'refl_0_86um_nom', 'refl_1_38um_nom', 'refl_1_60um_nom']
+# -- NIGHT L1B -------------------------------
+train_params_l1b = ['temp_10_4um_nom', 'temp_11_0um_nom', 'temp_12_0um_nom', 'temp_13_3um_nom', 'temp_3_75um_nom',
+                    'temp_6_2um_nom', 'temp_6_7um_nom', 'temp_7_3um_nom', 'temp_8_5um_nom', 'temp_9_7um_nom']
 # -- DAY LUNAR ---------------------
 # train_params_l1b = ['cld_height_acha', 'cld_geo_thick', 'cld_temp_acha', 'cld_press_acha', 'supercooled_cloud_fraction',
 #                     'cld_emiss_acha', 'conv_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp', 'iwc_dcomp', 'lwc_dcomp']
@@ -495,8 +495,8 @@ class IcingIntensityNN:
         activation = tf.nn.leaky_relu
         momentum = 0.99
 
-        # num_filters = 16
-        num_filters = 30
+        num_filters = 16
+        # num_filters = 30
 
         conv = tf.keras.layers.Conv2D(num_filters, 5, strides=[1, 1], padding=padding, activation=activation)(self.inputs[0])
         conv = tf.keras.layers.MaxPool2D(padding=padding)(conv)