Merge pull request #327 from amcadmus/master

Bug fixings and add notice for the consistency of TF versions.

Author: amcadmus

doc/install.md

@@ -63,7 +63,8 @@ source $tensorflow_venv/bin/activate
 pip install --upgrade pip
 pip install --upgrade tensorflow==2.3.0
 ```
-It is notice that everytime a new shell is started and one wants to use `DeePMD-kit`, the virtual environment should be activated by 
+It is highly recommanded to keep the consistency of the TensorFlow version for the python and C++ interfaces. 
+Everytime a new shell is started and one wants to use `DeePMD-kit`, the virtual environment should be activated by 
 ```bash
 source $tensorflow_venv/bin/activate
 ```

source/train/Loss.py

@@ -38,11 +38,11 @@ def __init__ (self, jdata, **kwarg) :
         self.has_ae = (self.start_pref_ae != 0 or self.limit_pref_ae != 0)
         self.has_pf = (self.start_pref_pf != 0 or self.limit_pref_pf != 0)
         # data required
-        add_data_requirement('energy', 1, atomic=False, must=self.has_e, high_prec=True)
-        add_data_requirement('force',  3, atomic=True,  must=self.has_f, high_prec=False)
-        add_data_requirement('virial', 9, atomic=False, must=self.has_v, high_prec=False)
-        add_data_requirement('atom_ener', 1, atomic=True, must=self.has_ae, high_prec=False)
-        add_data_requirement('atom_pref', 1, atomic=True, must=self.has_pf, high_prec=False, repeat=3)
+        add_data_requirement('energy', 1, atomic=False, must=False, high_prec=True)
+        add_data_requirement('force',  3, atomic=True,  must=False, high_prec=False)
+        add_data_requirement('virial', 9, atomic=False, must=False, high_prec=False)
+        add_data_requirement('atom_ener', 1, atomic=True, must=False, high_prec=False)
+        add_data_requirement('atom_pref', 1, atomic=True, must=False, high_prec=False, repeat=3)
 
     def build (self, 
                learning_rate,

source/train/argcheck.py

@@ -299,6 +299,7 @@ def loss_args():
     doc_loss = 'The definition of loss function. The type of the loss depends on the type of the fitting. For fitting type `ener`, the prefactors before energy, force, virial and atomic energy losses may be provided. For fitting type `dipole`, `polar` and `global_polar`, the loss may be an empty `dict` or unset.' 
     ca = Argument('loss', dict, [], 
                   [loss_variant_type_args()],
+                  optional = True,
                   doc = doc_loss)
     return ca