snapshot..

modules/deeplearning/srcnn_l1b_l2.py

@@ -89,8 +89,8 @@ x_128 = slice(3, 131)
 y_128 = slice(3, 131)
 
 # Kernel size: 3, target size: (128, 128)
-x_130 = slice(2, 132)
-y_130 = slice(2, 132)
+slc_x = slice(2, 132)
+slc_y = slice(2, 132)
 slc_x_2 = x_134_2
 slc_y_2 = y_134_2
 x_128 = slice(3, 131)
@@ -102,13 +102,12 @@ y_2 = y_67
 # ----------------------------------------
 
 # Kernel size: 5, target_size: (128, 128)
-# x_132 = slice(3, 135)
-# y_132 = slice(3, 135)
+# slc_x = slice(3, 135)
+# slc_y = slice(3, 135)
 # slc_x_2 = slice(2, 137, 2)
 # slc_y_2 = slice(2, 137, 2)
 # x_128 = slice(5, 133)
 # y_128 = slice(5, 133)
-#
 # t = np.arange(1, 67, 0.5)
 # s = np.arange(1, 67, 0.5)
 # x_2 = np.arange(68)
@@ -271,7 +270,7 @@ class SRCNN:
         for param in data_params:
             idx = params.index(param)
             # tmp = input_data[:, idx, slc_y_2, slc_x_2]
-            tmp = input_data[:, idx, y_130, x_130]
+            tmp = input_data[:, idx, slc_y, slc_x]
             tmp = normalize(tmp, param, mean_std_dct)
             if DO_ADD_NOISE:
                 tmp = add_noise(tmp, noise_scale=NOISE_STDDEV)
@@ -281,7 +280,7 @@ class SRCNN:
         param = 'refl_0_65um_nom'
         idx = params.index(param)
         # tmp = input_data[:, idx, slc_y_2, slc_x_2]
-        tmp = input_data[:, idx, y_130, x_130]
+        tmp = input_data[:, idx, slc_y, slc_x]
         tmp = normalize(tmp, param, mean_std_dct)
         if DO_ADD_NOISE:
             tmp = add_noise(tmp, noise_scale=NOISE_STDDEV)