snapshot...

modules/deeplearning/cloud_opd_srcnn_abi.py

@@ -54,7 +54,7 @@ label_param = 'cld_opd_dcomp'
 
 params = ['temp_11_0um_nom', 'refl_0_65um_nom', label_param]
 params_i = ['temp_11_0um_nom', 'refl_0_65um_nom', label_param]
-data_params_half = ['temp_11_0um_nom']
+data_params_half = ['temp_11_0um_nom', 'refl_0_65um_nom']
 data_params_full = ['refl_0_65um_nom']
 
 label_idx_i = params_i.index(label_param)
@@ -142,7 +142,7 @@ def get_min_max_std(grd_k):
 
 class SRCNN:
     
-    def __init__(self, LEN_Y=128, LEN_X=128):
+    def __init__(self, LEN_Y=32, LEN_X=32):
 
         self.train_data = None
         self.train_label = None
@@ -258,13 +258,13 @@ class SRCNN:
             tmp = normalize(tmp, param, mean_std_dct)
             data_norm.append(tmp)
 
-        for param in data_params_full:
-            idx = params_i.index(param)
-            tmp = input_label[:, idx, :, :]
-            tmp = np.where(np.isnan(tmp), 0, tmp)
-
-            tmp = normalize(tmp, param, mean_std_dct)
-            data_norm.append(tmp[:, self.slc_y, self.slc_x])
+        # for param in data_params_full:
+        #     idx = params_i.index(param)
+        #     tmp = input_label[:, idx, :, :]
+        #     tmp = np.where(np.isnan(tmp), 0, tmp)
+        #
+        #     tmp = normalize(tmp, param, mean_std_dct)
+        #     data_norm.append(tmp[:, self.slc_y, self.slc_x])
         # ---------------------------------------------------
         tmp = input_label[:, label_idx_i, :, :]
         tmp = np.where(np.isnan(tmp), 0, tmp)