Merge pull request #1787 from amcadmus/master

Merge devel into master

.github/labeler.yml

@@ -0,0 +1,13 @@
+Python:
+- deepmd/**/*
+- source/tests/**/*
+Docs: doc/**/*
+Examples: examples/**/*
+Core: source/lib/**/*
+CUDA: source/lib/src/cuda/**/*
+ROCM: source/lib/src/rocm/**/*
+OP: source/op/**/*
+C++: source/api_cc/**/*
+LAMMPS: source/lmp/**/*
+Gromacs: source/gmx/**/*
+i-Pi: source/ipi/**/*

.github/workflows/build_cc.yml

@@ -12,6 +12,8 @@ jobs:
         - variant: cpu
         - variant: cuda
     steps:
+    - name: work around permission issue
+      run: git config --global --add safe.directory /__w/deepmd-kit/deepmd-kit
     - uses: actions/checkout@master
       with:
         submodules: true

.github/workflows/build_wheel.yml

@@ -13,6 +13,8 @@ jobs:
         os: [ubuntu-18.04]  #, windows-latest, macos-latest]
 
     steps:
+      - name: work around permission issue
+        run: git config --global --add safe.directory /__w/deepmd-kit/deepmd-kit
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
         name: Install Python
@@ -26,7 +28,7 @@ jobs:
       - name: Build wheels
         env:
           CIBW_BUILD: "cp36-* cp37-* cp38-* cp39-* cp310-*"
-          CIBW_MANYLINUX_X86_64_IMAGE: ghcr.io/deepmodeling/manylinux2010_x86_64_tensorflow
+          CIBW_MANYLINUX_X86_64_IMAGE: ghcr.io/deepmodeling/manylinux2014_x86_64_tensorflow
           CIBW_BEFORE_BUILD: pip install tensorflow
           CIBW_SKIP: "*-win32 *-manylinux_i686 *-musllinux*"
         run: |

.github/workflows/labeler.yml

@@ -0,0 +1,14 @@
+name: "Pull Request Labeler"
+on:
+- pull_request_target
+
+jobs:
+  triage:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/labeler@v4
+      with:
+        repo-token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/lint_python.yml

@@ -11,6 +11,8 @@ jobs:
         python-version: [3.8]
 
     steps:
+    - name: work around permission issue
+      run: git config --global --add safe.directory /__w/deepmd-kit/deepmd-kit
     - uses: actions/checkout@v1
     - uses: actions/setup-python@v2
       with:

.github/workflows/test_cc.yml

@@ -6,6 +6,12 @@ jobs:
   testpython:
     name: Test C++
     runs-on: ubuntu-latest
+    container: ghcr.io/deepmodeling/deepmd-kit-test-cc:latest
     steps:
+    - name: work around permission issue
+      run: git config --global --add safe.directory /__w/deepmd-kit/deepmd-kit
     - uses: actions/checkout@master
-    - run: source/install/test_cc.sh
+    - run: source/install/test_cc_local.sh
+      env:
+        tensorflow_root: /usr/local
+    - run: source/install/codecov.sh

.github/workflows/test_python.yml

@@ -51,6 +51,8 @@ jobs:
 
     container: ghcr.io/deepmodeling/deepmd-kit-test-environment:py${{ matrix.python }}-gcc${{ matrix.gcc }}-tf${{ matrix.tf }}
     steps:
+    - name: work around permission issue
+      run: git config --global --add safe.directory /__w/deepmd-kit/deepmd-kit
     - uses: actions/checkout@master
     - name: pip cache
       uses: actions/cache@v2

README.md

@@ -86,7 +86,8 @@ A full [document](doc/train/train-input-auto.rst) on options in the training inp
     - [Install GROMACS](doc/install/install-gromacs.md)
     - [Building conda packages](doc/install/build-conda.md)
 - [Data](doc/data/index.md)
-    - [Data conversion](doc/data/data-conv.md)
+    - [System](doc/data/system.md)
+    - [Formats of a system](doc/data/data-conv.md)
     - [Prepare data with dpdata](doc/data/dpdata.md)
 - [Model](doc/model/index.md)
     - [Overall](doc/model/overall.md)
@@ -99,6 +100,7 @@ A full [document](doc/train/train-input-auto.rst) on options in the training inp
     - [Fit `tensor` like `Dipole` and `Polarizability`](doc/model/train-fitting-tensor.md)
     - [Train a Deep Potential model using `type embedding` approach](doc/model/train-se-e2-a-tebd.md)
     - [Deep potential long-range](doc/model/dplr.md)
+    - [Deep Potential - Range Correction (DPRc)](doc/model/dprc.md)
 - [Training](doc/train/index.md)
     - [Training a model](doc/train/training.md)
     - [Advanced options](doc/train/training-advanced.md)
@@ -121,37 +123,31 @@ A full [document](doc/train/train-input-auto.rst) on options in the training inp
     - [LAMMPS commands](doc/third-party/lammps-command.md)
     - [Run path-integral MD with i-PI](doc/third-party/ipi.md)
     - [Run MD with GROMACS](doc/third-party/gromacs.md)
+    - [Interfaces out of DeePMD-kit](doc/third-party/out-of-deepmd-kit.md)
 
 # Code structure
+
 The code is organized as follows:
 
 * `data/raw`: tools manipulating the raw data files.
-
 * `examples`: examples.
-
 * `deepmd`: DeePMD-kit python modules.
-
 * `source/api_cc`: source code of DeePMD-kit C++ API.
-
 * `source/ipi`: source code of i-PI client.
-
 * `source/lib`: source code of DeePMD-kit library.
-
 * `source/lmp`: source code of Lammps module.
-
 * `source/gmx`: source code of Gromacs plugin.
-
 * `source/op`: tensorflow op implementation. working with library.
 
 
 # Troubleshooting
 
-- [Model compatibility](doc/troubleshooting/model-compatability.md)
+- [Model compatibility](doc/troubleshooting/model_compatability.md)
 - [Installation](doc/troubleshooting/installation.md)
-- [The temperature undulates violently during early stages of MD](doc/troubleshooting/md-energy-undulation.md)
-- [MD: cannot run LAMMPS after installing a new version of DeePMD-kit](doc/troubleshooting/md-version-compatibility.md)
-- [Do we need to set rcut < half boxsize?](doc/troubleshooting/howtoset-rcut.md)
-- [How to set sel?](doc/troubleshooting/howtoset-sel.md)
+- [The temperature undulates violently during early stages of MD](doc/troubleshooting/md_energy_undulation.md)
+- [MD: cannot run LAMMPS after installing a new version of DeePMD-kit](doc/troubleshooting/md_version_compatibility.md)
+- [Do we need to set rcut < half boxsize?](doc/troubleshooting/howtoset_rcut.md)
+- [How to set sel?](doc/troubleshooting/howtoset_sel.md)
 - [How to control the number of nodes used by a job?](doc/troubleshooting/howtoset_num_nodes.md)
 - [How to tune Fitting/embedding-net size?](doc/troubleshooting/howtoset_netsize.md)
 

deepmd/calculator.py

@@ -54,7 +54,7 @@ class DP(Calculator):
     """
 
     name = "DP"
-    implemented_properties = ["energy", "forces", "virial", "stress"]
+    implemented_properties = ["energy", "free_energy", "forces", "virial", "stress"]
 
     def __init__(
         self,
@@ -102,6 +102,8 @@ def calculate(
         atype = [self.type_dict[k] for k in symbols]
         e, f, v = self.dp.eval(coords=coord, cells=cell, atom_types=atype)
         self.results['energy'] = e[0][0]
+        # see https://gitlab.com/ase/ase/-/merge_requests/2485
+        self.results['free_energy'] = e[0][0]
         self.results['forces'] = f[0]
         self.results['virial'] = v[0].reshape(3, 3)
 

deepmd/common.py

@@ -95,6 +95,7 @@ def add_data_requirement(
     high_prec: bool = False,
     type_sel: bool = None,
     repeat: int = 1,
+    default: float = 0.,
 ):
     """Specify data requirements for training.
 
@@ -116,6 +117,8 @@ def add_data_requirement(
         select only certain type of atoms, by default None
     repeat : int, optional
         if specify repaeat data `repeat` times, by default 1
+    default : float, optional, default=0.
+        default value of data
     """
     data_requirement[key] = {
         "ndof": ndof,
@@ -124,6 +127,7 @@ def add_data_requirement(
         "high_prec": high_prec,
         "type_sel": type_sel,
         "repeat": repeat,
+        "default": default,
     }
 
 
@@ -444,28 +448,6 @@ def expand_sys_str(root_dir: Union[str, Path]) -> List[str]:
     return matches
 
 
-def docstring_parameter(*sub: Tuple[str, ...]):
-    """Add parameters to object docstring.
-
-    Parameters
-    ----------
-    sub: Tuple[str, ...]
-        list of strings that will be inserted into prepared locations in docstring.
-
-    Note
-    ----
-    Can be used on both object and classes.
-    """
-
-    @wraps
-    def dec(obj: "_OBJ") -> "_OBJ":
-        if obj.__doc__ is not None:
-            obj.__doc__ = obj.__doc__.format(*sub)
-        return obj
-
-    return dec
-
-
 def get_np_precision(precision: "_PRECISION") -> np.dtype:
     """Get numpy precision constant from string.
 

deepmd/descriptor/hybrid.py

@@ -189,7 +189,7 @@ def build (self,
             dout = tf.reshape(dout, [-1, ii.get_dim_out()])
             all_dout.append(dout)
         dout = tf.concat(all_dout, axis = 1)
-        dout = tf.reshape(dout, [-1, natoms[0] * self.get_dim_out()])
+        dout = tf.reshape(dout, [-1, natoms[0], self.get_dim_out()])
         return dout
 
 

deepmd/descriptor/loc_frame.py

@@ -305,7 +305,7 @@ def prod_force_virial(self,
         """
         [net_deriv] = tf.gradients (atom_ener, self.descrpt)
         tf.summary.histogram('net_derivative', net_deriv)
-        net_deriv_reshape = tf.reshape (net_deriv, [-1, natoms[0] * self.ndescrpt])
+        net_deriv_reshape = tf.reshape (net_deriv, [np.cast['int64'](-1), natoms[0] * np.cast['int64'](self.ndescrpt)])
         force = op_module.prod_force (net_deriv_reshape,
                                       self.descrpt_deriv,
                                       self.nlist,

deepmd/descriptor/se_a.py

@@ -3,8 +3,7 @@
 from typing import Tuple, List, Dict, Any
 
 from deepmd.env import tf
-from deepmd.common import get_activation_func, get_precision, ACTIVATION_FN_DICT, PRECISION_DICT, docstring_parameter, cast_precision
-from deepmd.utils.argcheck import list_to_doc
+from deepmd.common import get_activation_func, get_precision, cast_precision
 from deepmd.env import GLOBAL_TF_FLOAT_PRECISION
 from deepmd.env import GLOBAL_NP_FLOAT_PRECISION
 from deepmd.env import op_module
@@ -88,9 +87,9 @@ class DescrptSeA (DescrptSe):
     set_davg_zero
             Set the shift of embedding net input to zero.
     activation_function
-            The activation function in the embedding net. Supported options are {0}
+            The activation function in the embedding net. Supported options are |ACTIVATION_FN|
     precision
-            The precision of the embedding net parameters. Supported options are {1}
+            The precision of the embedding net parameters. Supported options are |PRECISION|
     uniform_seed
             Only for the purpose of backward compatibility, retrieves the old behavior of using the random seed
     
@@ -101,7 +100,6 @@ class DescrptSeA (DescrptSe):
        systems. In Proceedings of the 32nd International Conference on Neural Information Processing
        Systems (NIPS'18). Curran Associates Inc., Red Hook, NY, USA, 4441–4451.
     """
-    @docstring_parameter(list_to_doc(ACTIVATION_FN_DICT.keys()), list_to_doc(PRECISION_DICT.keys()))
     def __init__ (self, 
                   rcut: float,
                   rcut_smth: float,
@@ -517,7 +515,7 @@ def prod_force_virial(self,
         """
         [net_deriv] = tf.gradients (atom_ener, self.descrpt_reshape)
         tf.summary.histogram('net_derivative', net_deriv)
-        net_deriv_reshape = tf.reshape (net_deriv, [-1, natoms[0] * self.ndescrpt])        
+        net_deriv_reshape = tf.reshape (net_deriv, [np.cast['int64'](-1), natoms[0] * np.cast['int64'](self.ndescrpt)])        
         force \
             = op_module.prod_force_se_a (net_deriv_reshape,
                                           self.descrpt_deriv,
@@ -553,14 +551,14 @@ def _pass_filter(self,
         else:
             type_embedding = None
         start_index = 0
-        inputs = tf.reshape(inputs, [-1, self.ndescrpt * natoms[0]])
+        inputs = tf.reshape(inputs, [-1, natoms[0], self.ndescrpt])
         output = []
         output_qmat = []
         if not (self.type_one_side and len(self.exclude_types) == 0) and type_embedding is None:
             for type_i in range(self.ntypes):
                 inputs_i = tf.slice (inputs,
-                                     [ 0, start_index*      self.ndescrpt],
-                                     [-1, natoms[2+type_i]* self.ndescrpt] )
+                                     [ 0, start_index, 0],
+                                     [-1, natoms[2+type_i], -1] )
                 inputs_i = tf.reshape(inputs_i, [-1, self.ndescrpt])
                 if self.type_one_side:
                     # reuse NN parameters for all types to support type_one_side along with exclude_types
@@ -569,8 +567,8 @@ def _pass_filter(self,
                 else:
                     filter_name = 'filter_type_'+str(type_i)+suffix
                 layer, qmat = self._filter(inputs_i, type_i, name=filter_name, natoms=natoms, reuse=reuse, trainable = trainable, activation_fn = self.filter_activation_fn)
-                layer = tf.reshape(layer, [tf.shape(inputs)[0], natoms[2+type_i] * self.get_dim_out()])
-                qmat  = tf.reshape(qmat,  [tf.shape(inputs)[0], natoms[2+type_i] * self.get_dim_rot_mat_1() * 3])
+                layer = tf.reshape(layer, [tf.shape(inputs)[0], natoms[2+type_i], self.get_dim_out()])
+                qmat  = tf.reshape(qmat,  [tf.shape(inputs)[0], natoms[2+type_i], self.get_dim_rot_mat_1() * 3])
                 output.append(layer)
                 output_qmat.append(qmat)
                 start_index += natoms[2+type_i]
@@ -579,8 +577,8 @@ def _pass_filter(self,
             inputs_i = tf.reshape(inputs_i, [-1, self.ndescrpt])
             type_i = -1
             layer, qmat = self._filter(inputs_i, type_i, name='filter_type_all'+suffix, natoms=natoms, reuse=reuse, trainable = trainable, activation_fn = self.filter_activation_fn, type_embedding=type_embedding)
-            layer = tf.reshape(layer, [tf.shape(inputs)[0], natoms[0] * self.get_dim_out()])
-            qmat  = tf.reshape(qmat,  [tf.shape(inputs)[0], natoms[0] * self.get_dim_rot_mat_1() * 3])
+            layer = tf.reshape(layer, [tf.shape(inputs)[0], natoms[0], self.get_dim_out()])
+            qmat  = tf.reshape(qmat,  [tf.shape(inputs)[0], natoms[0], self.get_dim_rot_mat_1() * 3])
             output.append(layer)
             output_qmat.append(qmat)
         output = tf.concat(output, axis = 1)
@@ -635,7 +633,7 @@ def _compute_dstats_sys_smth (self,
 
     def _compute_std (self,sumv2, sumv, sumn) :
         if sumn == 0:
-            return 1e-2
+            return 1. / self.rcut_r
         val = np.sqrt(sumv2/sumn - np.multiply(sumv/sumn, sumv/sumn))
         if np.abs(val) < 1e-2:
             val = 1e-2
@@ -720,12 +718,12 @@ def _filter_lower(
                 raise RuntimeError('compression of type embedded descriptor is not supported at the moment')
         # natom x 4 x outputs_size
         if self.compress and (not is_exclude):
-          info = [self.lower, self.upper, self.upper * self.table_config[0], self.table_config[1], self.table_config[2], self.table_config[3]]
-          if self.type_one_side:
-            net = 'filter_-1_net_' + str(type_i)
-          else:
-            net = 'filter_' + str(type_input) + '_net_' + str(type_i)
-          return op_module.tabulate_fusion_se_a(tf.cast(self.table.data[net], self.filter_precision), info, xyz_scatter, tf.reshape(inputs_i, [natom, shape_i[1]//4, 4]), last_layer_size = outputs_size[-1])  
+            if self.type_one_side:
+                net = 'filter_-1_net_' + str(type_i)
+            else:
+                net = 'filter_' + str(type_input) + '_net_' + str(type_i)
+            info = [self.lower[net], self.upper[net], self.upper[net] * self.table_config[0], self.table_config[1], self.table_config[2], self.table_config[3]]
+            return op_module.tabulate_fusion_se_a(tf.cast(self.table.data[net], self.filter_precision), info, xyz_scatter, tf.reshape(inputs_i, [natom, shape_i[1]//4, 4]), last_layer_size = outputs_size[-1])  
         else:
           if (not is_exclude):
               # with (natom x nei_type_i) x out_size

deepmd/descriptor/se_a_ebd.py

@@ -433,8 +433,8 @@ def _pass_filter(self,
                                        seed = self.seed, 
                                        trainable = trainable, 
                                        activation_fn = self.filter_activation_fn)
-        output      = tf.reshape(layer, [tf.shape(inputs)[0], natoms[0] * self.get_dim_out()])
-        output_qmat = tf.reshape(qmat,  [tf.shape(inputs)[0], natoms[0] * self.get_dim_rot_mat_1() * 3])
+        output      = tf.reshape(layer, [tf.shape(inputs)[0], natoms[0], self.get_dim_out()])
+        output_qmat = tf.reshape(qmat,  [tf.shape(inputs)[0], natoms[0], self.get_dim_rot_mat_1() * 3])
         return output, output_qmat
 
 

deepmd/descriptor/se_a_ef.py

@@ -2,8 +2,7 @@
 from typing import Tuple, List
 
 from deepmd.env import tf
-from deepmd.common import add_data_requirement,get_activation_func, get_precision, ACTIVATION_FN_DICT, PRECISION_DICT, docstring_parameter
-from deepmd.utils.argcheck import list_to_doc
+from deepmd.common import add_data_requirement
 from deepmd.utils.sess import run_sess
 from deepmd.env import GLOBAL_TF_FLOAT_PRECISION
 from deepmd.env import GLOBAL_NP_FLOAT_PRECISION
@@ -43,13 +42,12 @@ class DescrptSeAEf (Descriptor):
     set_davg_zero
             Set the shift of embedding net input to zero.
     activation_function
-            The activation function in the embedding net. Supported options are {0}
+            The activation function in the embedding net. Supported options are |ACTIVATION_FN|
     precision
-            The precision of the embedding net parameters. Supported options are {1}
+            The precision of the embedding net parameters. Supported options are |PRECISION|
     uniform_seed
             Only for the purpose of backward compatibility, retrieves the old behavior of using the random seed
     """
-    @docstring_parameter(list_to_doc(ACTIVATION_FN_DICT.keys()), list_to_doc(PRECISION_DICT.keys()))
     def __init__(self,
                  rcut: float,
                  rcut_smth: float,
@@ -230,7 +228,7 @@ def build (self,
         self.dout_vert = tf.reshape(self.dout_vert, [nframes * natoms[0], self.descrpt_vert.get_dim_out()])
         self.dout_para = tf.reshape(self.dout_para, [nframes * natoms[0], self.descrpt_para.get_dim_out()])
         self.dout = tf.concat([self.dout_vert, self.dout_para], axis = 1)
-        self.dout = tf.reshape(self.dout, [nframes, natoms[0] * self.get_dim_out()])
+        self.dout = tf.reshape(self.dout, [nframes, natoms[0], self.get_dim_out()])
         self.qmat = self.descrpt_vert.qmat + self.descrpt_para.qmat
 
         tf.summary.histogram('embedding_net_output', self.dout)