snapshot...

modules/deeplearning/icing_cnn.py

 import tensorflow as tf
 from util.setup import logdir, modeldir, cachepath, now, ancillary_path
 from util.util import EarlyStop, normalize, make_for_full_domain_predict
-from util.geos_nav import get_navigation
+from util.geos_nav import get_navigation, get_lon_lat_2d_mesh
 
 import os, datetime
 import numpy as np
@@ -1034,8 +1034,7 @@ def run_restore_static(filename_l1b, filename_l2, ckpt_dir_s_path):
     return labels, prob_avg, cm_avg
 
 
-def run_evaluate_static(h5f, ckpt_dir_s_path, flight_level=4, prob_thresh=0.5, satellite='GOES16', domain='FD'):
-    data_dct, ll, cc = make_for_full_domain_predict(h5f, name_list=train_params, domain=domain)
+def run_evaluate_static(data_dct, ll, cc, ckpt_dir_s_path, flight_level=4, prob_thresh=0.5, satellite='GOES16', domain='FD'):
     num_elems = len(cc)
     num_lines = len(ll)
 
@@ -1068,18 +1067,7 @@ def run_evaluate_static(h5f, ckpt_dir_s_path, flight_level=4, prob_thresh=0.5, s
         preds = np.where(probs > prob_thresh, 1, 0)
     else:
         preds = np.argmax(probs, axis=1)
-    preds_2d = preds.reshape((len(ll), len(cc)))
-    cc = np.array(cc)
-    ll = np.array(ll)
-    x_rad = cc * nav.CFAC + nav.COFF
-    y_rad = ll * nav.LFAC + nav.LOFF
-
-    ll, cc = np.meshgrid(ll, cc, indexing='ij')
-    cc = cc.flatten()
-    ll = ll.flatten()
-    lon_s, lat_s = nav.lc_to_earth(cc, ll)
-    lons_2d = lon_s.reshape((num_lines, num_elems))
-    lats_2d = lat_s.reshape((num_lines, num_elems))
+    preds_2d = preds.reshape((num_lines, num_elems))
 
     ice_mask = preds == 1
     ice_cc = cc[ice_mask]
@@ -1087,7 +1075,7 @@ def run_evaluate_static(h5f, ckpt_dir_s_path, flight_level=4, prob_thresh=0.5, s
 
     ice_lons, ice_lats = nav.lc_to_earth(ice_cc, ice_ll)
 
-    return ice_lons, ice_lats, preds_2d, lons_2d, lats_2d, x_rad, y_rad
+    return ice_lons, ice_lats, preds_2d
 
 
 def run_evaluate_static_new(data_dct, num_lines, num_elems, ckpt_dir_s_path, day_night='DAY', flight_levels=[0, 1, 2, 3, 4], prob_thresh=0.5):