def test_cast_precision(self):
x = tf.zeros(1, dtype=GLOBAL_TF_FLOAT_PRECISION)
y = tf.zeros(1, dtype=tf.int64)
self.assertEqual(x.dtype, GLOBAL_TF_FLOAT_PRECISION)
self.assertEqual(y.dtype, tf.int64)
x, y, z = self._inner_method(x, y)
self.assertEqual(x.dtype, GLOBAL_TF_FLOAT_PRECISION)
self.assertEqual(y.dtype, tf.int64)
self.assertIsInstance(z, bool)
def _enrich(self, dipole, dof=3):
coll = []
sel_start_idx = 0
for type_i in range(self.ntypes):
if type_i in self.sel_type:
di = tf.slice(dipole, [0, sel_start_idx * dof],
[-1, self.t_natoms[2 + type_i] * dof])
sel_start_idx += self.t_natoms[2 + type_i]
else:
di = tf.zeros(
[tf.shape(dipole)[0], self.t_natoms[2 + type_i] * dof],
dtype=GLOBAL_TF_FLOAT_PRECISION)
coll.append(di)
return tf.concat(coll, axis=1)
def _enrich(self, dipole, dof = 3):
coll = []
sel_start_idx = 0
for type_i in range(self.ntypes):
if type_i in self.sel_type:
di = tf.slice(dipole,
[ 0, sel_start_idx * dof],
[-1, self.t_natoms[2+type_i] * dof])
sel_start_idx += self.t_natoms[2+type_i]
else:
di = tf.zeros([tf.shape(dipole)[0], self.t_natoms[2+type_i] * dof],
dtype = global_tf_float_precision)
coll.append(di)
return tf.concat(coll, axis = 1)
def _filter(self,
inputs,
type_input,
natoms,
activation_fn=tf.nn.tanh,
stddev=1.0,
bavg=0.0,
name='linear',
reuse=None,
seed=None,
trainable=True):
# natom x (nei x 4)
shape = inputs.get_shape().as_list()
outputs_size = [1] + self.filter_neuron
outputs_size_2 = self.n_axis_neuron
with tf.variable_scope(name, reuse=reuse):
start_index = 0
xyz_scatter_total = []
for type_i in range(self.ntypes):
# cut-out inputs
# with natom x (nei_type_i x 4)
inputs_i = tf.slice(inputs, [0, start_index * 4],
[-1, self.sel_a[type_i] * 4])
start_index += self.sel_a[type_i]
shape_i = inputs_i.get_shape().as_list()
# with (natom x nei_type_i) x 4
inputs_reshape = tf.reshape(inputs_i, [-1, 4])
xyz_scatter = tf.reshape(
tf.slice(inputs_reshape, [0, 0], [-1, 1]), [-1, 1])
if (type_input, type_i) not in self.exclude_types:
for ii in range(1, len(outputs_size)):
w = tf.get_variable(
'matrix_' + str(ii) + '_' + str(type_i),
[outputs_size[ii - 1], outputs_size[ii]],
self.filter_precision,
tf.random_normal_initializer(
stddev=stddev / np.sqrt(outputs_size[ii] +
outputs_size[ii - 1]),
seed=seed),
trainable=trainable)
b = tf.get_variable(
'bias_' + str(ii) + '_' + str(type_i),
[1, outputs_size[ii]],
self.filter_precision,
tf.random_normal_initializer(stddev=stddev,
mean=bavg,
seed=seed),
trainable=trainable)
if self.filter_resnet_dt:
idt = tf.get_variable(
'idt_' + str(ii) + '_' + str(type_i),
[1, outputs_size[ii]],
self.filter_precision,
tf.random_normal_initializer(stddev=0.001,
mean=1.0,
seed=seed),
trainable=trainable)
if outputs_size[ii] == outputs_size[ii - 1]:
if self.filter_resnet_dt:
xyz_scatter += activation_fn(
tf.matmul(xyz_scatter, w) + b) * idt
else:
xyz_scatter += activation_fn(
tf.matmul(xyz_scatter, w) + b)
elif outputs_size[ii] == outputs_size[ii - 1] * 2:
if self.filter_resnet_dt:
xyz_scatter = tf.concat(
[xyz_scatter, xyz_scatter],
1) + activation_fn(
tf.matmul(xyz_scatter, w) + b) * idt
else:
xyz_scatter = tf.concat(
[xyz_scatter, xyz_scatter],
1) + activation_fn(
tf.matmul(xyz_scatter, w) + b)
else:
xyz_scatter = activation_fn(
tf.matmul(xyz_scatter, w) + b)
else:
w = tf.zeros((outputs_size[0], outputs_size[-1]),
dtype=global_tf_float_precision)
xyz_scatter = tf.matmul(xyz_scatter, w)
# natom x nei_type_i x out_size
xyz_scatter = tf.reshape(
xyz_scatter, (-1, shape_i[1] // 4, outputs_size[-1]))
xyz_scatter_total.append(xyz_scatter)
# natom x nei x outputs_size
xyz_scatter = tf.concat(xyz_scatter_total, axis=1)
# natom x nei x 4
inputs_reshape = tf.reshape(inputs, [-1, shape[1] // 4, 4])
# natom x 4 x outputs_size
xyz_scatter_1 = tf.matmul(inputs_reshape,
xyz_scatter,
transpose_a=True)
xyz_scatter_1 = xyz_scatter_1 * (4.0 / shape[1])
# natom x 4 x outputs_size_2
xyz_scatter_2 = tf.slice(xyz_scatter_1, [0, 0, 0],
[-1, -1, outputs_size_2])
# # natom x 3 x outputs_size_2
# qmat = tf.slice(xyz_scatter_2, [0,1,0], [-1, 3, -1])
# natom x 3 x outputs_size_1
qmat = tf.slice(xyz_scatter_1, [0, 1, 0], [-1, 3, -1])
# natom x outputs_size_2 x 3
qmat = tf.transpose(qmat, perm=[0, 2, 1])
# natom x outputs_size x outputs_size_2
result = tf.matmul(xyz_scatter_1, xyz_scatter_2, transpose_a=True)
# natom x (outputs_size x outputs_size_2)
result = tf.reshape(result,
[-1, outputs_size_2 * outputs_size[-1]])
return result, qmat
def _filter_r(self,
inputs,
type_input,
natoms,
activation_fn=tf.nn.tanh,
stddev=1.0,
bavg=0.0,
name='linear',
reuse=None,
seed=None,
trainable=True):
# natom x nei
outputs_size = [1] + self.filter_neuron
with tf.variable_scope(name, reuse=reuse):
start_index = 0
xyz_scatter_total = []
for type_i in range(self.ntypes):
# cut-out inputs
# with natom x nei_type_i
inputs_i = tf.slice(inputs, [0, start_index],
[-1, self.sel_r[type_i]])
start_index += self.sel_r[type_i]
shape_i = inputs_i.get_shape().as_list()
# with (natom x nei_type_i) x 1
xyz_scatter = tf.reshape(inputs_i, [-1, 1])
if (type_input, type_i) not in self.exclude_types:
for ii in range(1, len(outputs_size)):
w = tf.get_variable(
'matrix_' + str(ii) + '_' + str(type_i),
[outputs_size[ii - 1], outputs_size[ii]],
self.filter_precision,
tf.random_normal_initializer(
stddev=stddev / np.sqrt(outputs_size[ii] +
outputs_size[ii - 1]),
seed=seed),
trainable=trainable)
b = tf.get_variable(
'bias_' + str(ii) + '_' + str(type_i),
[1, outputs_size[ii]],
self.filter_precision,
tf.random_normal_initializer(stddev=stddev,
mean=bavg,
seed=seed),
trainable=trainable)
if self.filter_resnet_dt:
idt = tf.get_variable(
'idt_' + str(ii) + '_' + str(type_i),
[1, outputs_size[ii]],
self.filter_precision,
tf.random_normal_initializer(stddev=0.001,
mean=1.0,
seed=seed),
trainable=trainable)
if outputs_size[ii] == outputs_size[ii - 1]:
if self.filter_resnet_dt:
xyz_scatter += activation_fn(
tf.matmul(xyz_scatter, w) + b) * idt
else:
xyz_scatter += activation_fn(
tf.matmul(xyz_scatter, w) + b)
elif outputs_size[ii] == outputs_size[ii - 1] * 2:
if self.filter_resnet_dt:
xyz_scatter = tf.concat(
[xyz_scatter, xyz_scatter],
1) + activation_fn(
tf.matmul(xyz_scatter, w) + b) * idt
else:
xyz_scatter = tf.concat(
[xyz_scatter, xyz_scatter],
1) + activation_fn(
tf.matmul(xyz_scatter, w) + b)
else:
xyz_scatter = activation_fn(
tf.matmul(xyz_scatter, w) + b)
else:
w = tf.zeros((outputs_size[0], outputs_size[-1]),
dtype=global_tf_float_precision)
xyz_scatter = tf.matmul(xyz_scatter, w)
# natom x nei_type_i x out_size
xyz_scatter = tf.reshape(xyz_scatter,
(-1, shape_i[1], outputs_size[-1]))
xyz_scatter_total.append(xyz_scatter)
# natom x nei x outputs_size
xyz_scatter = tf.concat(xyz_scatter_total, axis=1)
# natom x outputs_size
#
res_rescale = 1. / 5.
result = tf.reduce_mean(xyz_scatter, axis=1) * res_rescale
return result
def build(
self,
inputs: tf.Tensor,
natoms: tf.Tensor,
input_dict: dict = None,
reuse: bool = None,
suffix: str = '',
) -> tf.Tensor:
"""
Build the computational graph for fitting net
Parameters
----------
inputs
The input descriptor
input_dict
Additional dict for inputs.
if numb_fparam > 0, should have input_dict['fparam']
if numb_aparam > 0, should have input_dict['aparam']
natoms
The number of atoms. This tensor has the length of Ntypes + 2
natoms[0]: number of local atoms
natoms[1]: total number of atoms held by this processor
natoms[i]: 2 <= i < Ntypes+2, number of type i atoms
reuse
The weights in the networks should be reused when get the variable.
suffix
Name suffix to identify this descriptor
Returns
-------
ener
The system energy
"""
if input_dict is None:
input_dict = {}
bias_atom_e = self.bias_atom_e
if self.numb_fparam > 0 and (self.fparam_avg is None
or self.fparam_inv_std is None):
raise RuntimeError(
'No data stat result. one should do data statisitic, before build'
)
if self.numb_aparam > 0 and (self.aparam_avg is None
or self.aparam_inv_std is None):
raise RuntimeError(
'No data stat result. one should do data statisitic, before build'
)
with tf.variable_scope('fitting_attr' + suffix, reuse=reuse):
t_dfparam = tf.constant(self.numb_fparam,
name='dfparam',
dtype=tf.int32)
t_daparam = tf.constant(self.numb_aparam,
name='daparam',
dtype=tf.int32)
if self.numb_fparam > 0:
t_fparam_avg = tf.get_variable(
't_fparam_avg',
self.numb_fparam,
dtype=GLOBAL_TF_FLOAT_PRECISION,
trainable=False,
initializer=tf.constant_initializer(self.fparam_avg))
t_fparam_istd = tf.get_variable(
't_fparam_istd',
self.numb_fparam,
dtype=GLOBAL_TF_FLOAT_PRECISION,
trainable=False,
initializer=tf.constant_initializer(self.fparam_inv_std))
if self.numb_aparam > 0:
t_aparam_avg = tf.get_variable(
't_aparam_avg',
self.numb_aparam,
dtype=GLOBAL_TF_FLOAT_PRECISION,
trainable=False,
initializer=tf.constant_initializer(self.aparam_avg))
t_aparam_istd = tf.get_variable(
't_aparam_istd',
self.numb_aparam,
dtype=GLOBAL_TF_FLOAT_PRECISION,
trainable=False,
initializer=tf.constant_initializer(self.aparam_inv_std))
inputs = tf.reshape(inputs, [-1, self.dim_descrpt * natoms[0]])
if len(self.atom_ener):
# only for atom_ener
nframes = input_dict.get('nframes')
if nframes is not None:
# like inputs, but we don't want to add a dependency on inputs
inputs_zero = tf.zeros((nframes, self.dim_descrpt * natoms[0]),
dtype=self.fitting_precision)
else:
inputs_zero = tf.zeros_like(inputs,
dtype=self.fitting_precision)
if bias_atom_e is not None:
assert (len(bias_atom_e) == self.ntypes)
fparam = None
aparam = None
if self.numb_fparam > 0:
fparam = input_dict['fparam']
fparam = tf.reshape(fparam, [-1, self.numb_fparam])
fparam = (fparam - t_fparam_avg) * t_fparam_istd
if self.numb_aparam > 0:
aparam = input_dict['aparam']
aparam = tf.reshape(aparam, [-1, self.numb_aparam])
aparam = (aparam - t_aparam_avg) * t_aparam_istd
aparam = tf.reshape(aparam, [-1, self.numb_aparam * natoms[0]])
type_embedding = input_dict.get('type_embedding', None)
if type_embedding is not None:
atype_embed = embed_atom_type(self.ntypes, natoms, type_embedding)
atype_embed = tf.tile(atype_embed, [tf.shape(inputs)[0], 1])
else:
atype_embed = None
if atype_embed is None:
start_index = 0
outs_list = []
for type_i in range(self.ntypes):
if bias_atom_e is None:
type_bias_ae = 0.0
else:
type_bias_ae = bias_atom_e[type_i]
final_layer = self._build_lower(start_index,
natoms[2 + type_i],
inputs,
fparam,
aparam,
bias_atom_e=type_bias_ae,
suffix='_type_' + str(type_i) +
suffix,
reuse=reuse)
# concat the results
if type_i < len(
self.atom_ener) and self.atom_ener[type_i] is not None:
zero_layer = self._build_lower(start_index,
natoms[2 + type_i],
inputs_zero,
fparam,
aparam,
bias_atom_e=type_bias_ae,
suffix='_type_' +
str(type_i) + suffix,
reuse=True)
final_layer += self.atom_ener[type_i] - zero_layer
final_layer = tf.reshape(
final_layer, [tf.shape(inputs)[0], natoms[2 + type_i]])
outs_list.append(final_layer)
start_index += natoms[2 + type_i]
# concat the results
# concat once may be faster than multiple concat
outs = tf.concat(outs_list, axis=1)
# with type embedding
else:
if len(self.atom_ener) > 0:
raise RuntimeError(
"setting atom_ener is not supported by type embedding")
atype_embed = tf.cast(atype_embed, self.fitting_precision)
type_shape = atype_embed.get_shape().as_list()
inputs = tf.concat(
[tf.reshape(inputs, [-1, self.dim_descrpt]), atype_embed],
axis=1)
self.dim_descrpt = self.dim_descrpt + type_shape[1]
inputs = tf.reshape(inputs, [-1, self.dim_descrpt * natoms[0]])
final_layer = self._build_lower(0,
natoms[0],
inputs,
fparam,
aparam,
bias_atom_e=0.0,
suffix=suffix,
reuse=reuse)
outs = tf.reshape(final_layer, [tf.shape(inputs)[0], natoms[0]])
# add atom energy bias; TF will broadcast to all batches
# tf.repeat is avaiable in TF>=2.1 or TF 1.15
_TF_VERSION = Version(TF_VERSION)
if (Version('1.15') <= _TF_VERSION < Version('2') or _TF_VERSION >=
Version('2.1')) and self.bias_atom_e is not None:
outs += tf.repeat(
tf.Variable(self.bias_atom_e,
dtype=self.fitting_precision,
trainable=False,
name="bias_atom_ei"), natoms[2:])
if self.tot_ener_zero:
force_tot_ener = 0.0
outs = tf.reshape(outs, [-1, natoms[0]])
outs_mean = tf.reshape(tf.reduce_mean(outs, axis=1), [-1, 1])
outs_mean = outs_mean - tf.ones_like(
outs_mean, dtype=GLOBAL_TF_FLOAT_PRECISION) * (
force_tot_ener / global_cvt_2_tf_float(natoms[0]))
outs = outs - outs_mean
outs = tf.reshape(outs, [-1])
tf.summary.histogram('fitting_net_output', outs)
return tf.reshape(outs, [-1])
