snapshot...

modules/deeplearning/srcnn_l1b_l2.py

@@ -65,6 +65,8 @@ x_134 = np.arange(134)
 y_134 = np.arange(134)
 x_64 = np.arange(64)
 y_64 = np.arange(64)
+x_67 = np.arange(67)
+y_67 = np.arange(67)
 
 # x_134_2 = slice(3, 131, 2)
 # y_134_2 = slice(3, 131, 2)
@@ -88,6 +90,8 @@ y_134_2 = slice(1, 134, 2)
 # slc_y = y_128
 # t = np.arange(0, 64, 0.5)
 # s = np.arange(0, 64, 0.5)
+# x_2 = x_64
+# y_2 = y_64
 
 slc_x_2 = x_134_2
 slc_y_2 = y_134_2
@@ -95,6 +99,8 @@ slc_x = x_128
 slc_y = y_128
 t = np.arange(1, 66, 0.5)
 s = np.arange(1, 66, 0.5)
+x_2 = x_67
+y_2 = y_67
 
 
 def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.relu, padding='SAME',
@@ -251,14 +257,14 @@ class SRCNN:
             idx = params.index(param)
             tmp = input_data[:, idx, slc_y_2, slc_x_2]
             tmp = normalize(tmp, param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
-            tmp = resample_2d_linear(x_64, y_64, tmp, t, s)
+            tmp = resample_2d_linear(x_2, y_2, tmp, t, s)
             data_norm.append(tmp)
         # --------------------------
         param = 'refl_0_65um_nom'
         idx = params.index(param)
         tmp = input_data[:, idx, slc_y_2, slc_x_2]
         tmp = normalize(tmp, param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
-        tmp = resample_2d_linear(x_64, y_64, tmp, t, s)
+        tmp = resample_2d_linear(x_2, y_2, tmp, t, s)
         data_norm.append(tmp)
         # --------
         tmp = input_data[:, label_idx, slc_y_2, slc_x_2]
@@ -266,7 +272,7 @@ class SRCNN:
             tmp = normalize(tmp, label_param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
         else:
             tmp = np.where(np.isnan(tmp), 0, tmp)
-        tmp = resample_2d_linear(x_64, y_64, tmp, t, s)
+        tmp = resample_2d_linear(x_2, y_2, tmp, t, s)
         data_norm.append(tmp)
         # ---------
         data = np.stack(data_norm, axis=3)