snaphot...

modules/deeplearning/srcnn.py

 import glob
 import tensorflow as tf
 from util.setup import logdir, modeldir, cachepath, now, ancillary_path
-from util.util import EarlyStop, normalize, denormalize, resample
+from util.util import EarlyStop, normalize, denormalize, resample, get_grid_values_all
 import os, datetime
 import numpy as np
 import pickle
@@ -49,13 +49,13 @@ mean_std_dct.update(mean_std_dct_l2)
 
 # emis_params = ['temp_10_4um_nom', 'temp_11_0um_nom', 'temp_12_0um_nom', 'temp_13_3um_nom', 'temp_3_75um_nom',
 #                'temp_6_7um_nom', 'temp_6_2um_nom', 'temp_7_3um_nom', 'temp_8_5um_nom', 'temp_9_7um_nom']
-data_params = ['refl_0_65um_nom', 'temp_11_0um_nom', 'cld_temp_acha', 'cld_press_acha', 'cloud_fraction']
-label_params = ['refl_0_65um_nom', 'temp_11_0um_nom', 'cld_temp_acha', 'cld_press_acha', 'cloud_fraction']
+data_params = ['temp_11_0um_nom', 'temp_12_0um_nom', 'cld_temp_acha', 'cld_press_acha']
+label_params = ['temp_11_0um_nom', 'temp_12_0um_nom', 'cld_temp_acha', 'cld_press_acha']
 
 
 DO_ZERO_OUT = False
 
-data_idx, label_idx = 4, 4
+data_idx, label_idx = 0, 0
 data_param = data_params[data_idx]
 label_param = label_params[label_idx]
 print(data_param+', '+label_param)
@@ -603,8 +603,8 @@ class SRCNN:
         ckpt.restore(ckpt_manager.latest_checkpoint)
 
         data = normalize(nda_lr, param, mean_std_dct)
-        #data = np.expand_dims(data, axis=0)
-        #data = np.expand_dims(data, axis=3)
+        data = np.expand_dims(data, axis=0)
+        data = np.expand_dims(data, axis=3)
 
         self.reset_test_metrics()
 
@@ -668,6 +668,24 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
         return out_sr
 
 
+def run_evaluate_static_new(in_file, out_file, ckpt_dir):
+    nda = np.load(in_file)
+
+    nda = nda[:, data_idx, 3:131:2, 3:131:2]
+    nda = resample(x_64, y_64, nda, t, s)
+    nda = np.expand_dims(nda, axis=3)
+
+    h5f = h5py.File(in_file, 'r')
+    grd = get_grid_values_all(h5f, data_param)
+
+    nn = SRCNN()
+    out_sr = nn.run_evaluate(grd, data_param, ckpt_dir)
+    if out_file is not None:
+        np.save(out_file, out_sr)
+    else:
+        return out_sr
+
+
 if __name__ == "__main__":
     nn = SRCNN()
     nn.run('matchup_filename')