snapshot...

modules/deeplearning/cloud_fraction_fcn.py

@@ -781,29 +781,22 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
 
     grd_a = get_grid_values_all(h5f, 'orig/temp_11_0um')
     grd_a = np.where(np.isnan(grd_a), 0, grd_a)
-    # grd_a = grd_a[y_0:y_0+sub_y, x_0:x_0+sub_x]
     grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
-    #grd_a = grd_a[slc_y, slc_x]
     grd_a = grd_a[2:3230, 2:1098]
 
     grd_b = get_grid_values_all(h5f, 'super/refl_0_65um')
     grd_b = np.where(np.isnan(grd_b), 0, grd_b)
-    #grd_b = grd_b[y_0:y_0+sub_y, x_0:x_0+sub_x]
     grd_b = np.expand_dims(grd_b, axis=0)
     lo, hi, std, avg = get_min_max_std(grd_b)
     lo = normalize(lo, 'refl_0_65um_nom', mean_std_dct)
     hi = normalize(hi, 'refl_0_65um_nom', mean_std_dct)
     avg = normalize(avg, 'refl_0_65um_nom', mean_std_dct)
-    #lo = lo[0, slc_y, slc_x]
-    #hi = hi[0, slc_y, slc_x]
-    #avg = avg[0, slc_y, slc_x]
     lo = lo[0, 2:3230, 2:1098]
     hi = hi[0, 2:3230, 2:1098]
     avg = avg[0, 2:3230, 2:1098]
 
     grd_c = get_grid_values_all(h5f, 'orig/'+label_param)
     grd_c = np.where(np.isnan(grd_c), 0, grd_c)
-    #grd_c = grd_c[y_0:y_0+sub_y, x_0:x_0+sub_x]
     grd_c = grd_c[2:3230, 2:1098]
 
     data = np.stack([grd_a, lo, hi, avg, grd_c], axis=2)