snapshot...

modules/deeplearning/cloud_opd_srcnn_abi.py

@@ -727,7 +727,7 @@ class SRCNN:
         t1 = time.time()
         print('read data time: ', (t1 - t0))
 
-        cld_opd_sres = self.run_inference_(bt, refl_sub_lo, refl_sub_hi, refl_sub_std, cld_opd, 2*LEN_Y, 2*LEN_X)
+        cld_opd_sres = self.run_inference_(bt, refl, refl_sub_lo, refl_sub_hi, refl_sub_std, cld_opd, 2*LEN_Y, 2*LEN_X)
 
         cld_opd_sres_out = np.zeros((LEN_Y, LEN_X), dtype=np.int8)
         border = int((KERNEL_SIZE - 1) / 2)
@@ -740,7 +740,7 @@ class SRCNN:
         else:
             return cld_opd_sres
 
-    def run_inference_(self, bt, refl_sub_lo, refl_sub_hi, refl_sub_std, cld_opd, LEN_Y, LEN_X):
+    def run_inference_(self, bt, refl, refl_sub_lo, refl_sub_hi, refl_sub_std, cld_opd, LEN_Y, LEN_X):
 
         self.slc_x_m = slice(1, int(LEN_X / 2) + 4)
         self.slc_y_m = slice(1, int(LEN_Y / 2) + 4)
@@ -772,6 +772,14 @@ class SRCNN:
         bt_us = smooth_2d(bt_us)
         bt_us = normalize(bt_us, 'temp_11_0um_nom', mean_std_dct)
 
+        refl = np.where(np.isnan(refl), 0, refl)
+        refl = refl[self.slc_y_m, self.slc_x_m]
+        bt = np.expand_dims(refl, axis=0)
+        # bt_us = upsample_static(bt, x_2, y_2, t, s, None, None)
+        refl_us = self.upsample(refl)
+        refl_us = smooth_2d(refl_us)
+        refl_us = normalize(refl_us, 'refl_0_65um_nom', mean_std_dct)
+
         cld_opd = np.where(np.isnan(cld_opd), 0, cld_opd)
         cld_opd = cld_opd[self.slc_y_m, self.slc_x_m]
         cld_opd = np.expand_dims(cld_opd, axis=0)
@@ -797,7 +805,7 @@ class SRCNN:
         t1 = time.time()
         print('upsample/normalize time: ', (t1 - t0))
 
-        data = np.stack([bt_us, refl_sub_lo, refl_sub_hi, refl_sub_std, cld_opd_us], axis=3)
+        data = np.stack([bt_us, refl_us, refl_sub_lo, refl_sub_hi, refl_sub_std, cld_opd_us], axis=3)
 
         cld_opd_sres = self.do_inference(data)
         cld_opd_sres = denormalize(cld_opd_sres, label_param, mean_std_dct)