snapshot...

modules/deeplearning/icing_cnn.py

@@ -1063,58 +1063,6 @@ def run_restore_static(filename_l1b, filename_l2, ckpt_dir_s_path, day_night='DA
     return labels, prob_avg, cm_avg
 
 
-def run_evaluate_static_avg(data_dct, ll, cc, ckpt_dir_s_path, day_night='DAY', flight_level=4,
-                        use_flight_altitude=False, prob_thresh=0.5,
-                        satellite='GOES16', domain='FD'):
-    num_elems = len(cc)
-    num_lines = len(ll)
-    cc = np.array(cc)
-    ll = np.array(ll)
-
-    ckpt_dir_s = os.listdir(ckpt_dir_s_path)
-
-    nav = get_navigation(satellite, domain)
-
-    prob_s = []
-    for ckpt in ckpt_dir_s:
-        ckpt_dir = ckpt_dir_s_path + ckpt
-        if not os.path.isdir(ckpt_dir):
-            continue
-        nn = IcingIntensityNN(day_night=day_night, use_flight_altitude=use_flight_altitude)
-        nn.flight_level = flight_level
-        nn.setup_eval_pipeline(data_dct, num_lines * num_elems)
-        nn.build_model()
-        nn.build_training()
-        nn.build_evaluation()
-        nn.do_evaluate(ckpt_dir)
-        prob_s.append(nn.test_probs)
-
-    num = len(prob_s)
-    prob_avg = prob_s[0]
-    for k in range(num-1):
-        prob_avg += prob_s[k+1]
-    prob_avg /= num
-    probs = prob_avg
-
-    if NumClasses == 2:
-        preds = np.where(probs > prob_thresh, 1, 0)
-    else:
-        preds = np.argmax(probs, axis=1)
-    preds_2d = preds.reshape((num_lines, num_elems))
-
-    ll, cc = np.meshgrid(ll, cc, indexing='ij')
-    cc = cc.flatten()
-    ll = ll.flatten()
-
-    ice_mask = preds == 1
-    ice_cc = cc[ice_mask]
-    ice_ll = ll[ice_mask]
-
-    ice_lons, ice_lats = nav.lc_to_earth(ice_cc, ice_ll)
-
-    return ice_lons, ice_lats, preds_2d
-
-
 def run_evaluate_static(data_dct, num_tiles, ckpt_dir_s_path, day_night='DAY', l1b_or_l2='both', prob_thresh=0.5,
                         flight_levels=[0, 1, 2, 3, 4], use_flight_altitude=False):