snapshot...

modules/deeplearning/srcnn_l1b_l2.py

@@ -752,30 +752,22 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
 
 def run_evaluate_static_2(in_file, out_file, ckpt_dir):
     nda = np.load(in_file)
-    grd_a = nda[:, 0, :, :]
-    grd_a = grd_a[:, 3:131:2, 3:131:2]
-
-    grd_b = nda[:, 2, 3:131, 3:131]
-
-    grd_c = nda[:, 3, :, :]
-    grd_c = grd_c[:, 3:131:2, 3:131:2]
-
-    num, leny, lenx = grd_a.shape
-    x = np.arange(lenx)
-    y = np.arange(leny)
-    x_up = np.arange(0, lenx, 0.5)
-    y_up = np.arange(0, leny, 0.5)
 
+    grd_a = nda[:, 0, :, :]
+    grd_a = grd_a[:, slc_y_2, slc_x_2]
     grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
-    grd_a = resample_2d_linear(x, y, grd_a, x_up, y_up)
+    grd_a = resample_2d_linear(x_2, y_2, grd_a, t, s)
 
+    grd_b = nda[:, 2, :, :]
+    grd_b = grd_b[:, slc_y_2, slc_x_2]
     grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
+    grd_b = resample_2d_linear(x_2, y_2, grd_b, t, s)
 
-    if label_param == 'cloud_fraction':
-        grd_c = np.where(np.isnan(grd_c), 0, grd_c)
-    else:
+    grd_c = nda[:, 3, :, :]
+    grd_c = grd_c[:, slc_y_2, slc_x_2]
+    if label_param != 'cloud_fraction':
         grd_c = normalize(grd_c, label_param, mean_std_dct)
-    grd_c = resample_2d_linear(x, y, grd_c, x_up, y_up)
+    grd_c = resample_2d_linear(x_2, y_2, grd_c, t, s)
 
     data = np.stack([grd_a, grd_b, grd_c], axis=3)
     print(data.shape)
@@ -783,7 +775,7 @@ def run_evaluate_static_2(in_file, out_file, ckpt_dir):
     nn = SRCNN()
     out_sr = nn.run_evaluate(data, ckpt_dir)
     if label_param != 'cloud_fraction':
-        # out_sr = denormalize(out_sr, label_param, mean_std_dct)
+        out_sr = denormalize(out_sr, label_param, mean_std_dct)
         pass
     if out_file is not None:
         np.save(out_file, out_sr)