snapshot...

modules/deeplearning/icing_fcn.py

@@ -397,9 +397,8 @@ class IcingIntensityFCN:
         data = np.transpose(data, axes=(1, 2, 0))
         data = np.expand_dims(data, axis=0)
 
-        # TODO: altitude data will be specified by user at run-time
-        nda = np.zeros([data.shape[1]*data.shape[2]])
-        nda[:] = self.flight_level
+        nda = np.zeros([1])
+        nda[0] = self.flight_level
         nda = tf.one_hot(nda, 5).numpy()
 
         return data, nda
@@ -445,9 +444,7 @@ class IcingIntensityFCN:
         indexes = list(indexes)
 
         dataset = tf.data.Dataset.from_tensor_slices(indexes)
-        # dataset = dataset.batch(PROC_BATCH_SIZE)
         dataset = dataset.map(self.data_function_evaluate, num_parallel_calls=8)
-        # dataset = dataset.cache()
         self.eval_dataset = dataset
 
     def setup_pipeline(self, filename_l1b_trn, filename_l1b_tst, filename_l2_trn, filename_l2_tst, trn_idxs=None, tst_idxs=None, seed=None):
@@ -990,12 +987,7 @@ class IcingIntensityFCN:
         self.reset_test_metrics()
 
         pred_s = []
-        # for data in self.eval_dataset:
-        #     ds = tf.data.Dataset.from_tensor_slices(data)
-        #     ds = ds.batch(BATCH_SIZE)
-        #     for mini_batch in ds:
-        #         pred = self.model([mini_batch], training=False)
-        #         pred_s.append(pred)
+
         for data in self.eval_dataset:
             print(data[0].shape, data[1].shape)
             pred = self.model([data])