deepmd.tf.env

Module that sets tensorflow working environment and exports inportant constants.

Module Contents

Functions

reset_default_tf_session_config(cpu_only)	Limit tensorflow session to CPU or not.
global_cvt_2_tf_float(→ tensorflow.compat.v1.Tensor)	Cast tensor to globally set TF precision.
global_cvt_2_ener_float(→ tensorflow.compat.v1.Tensor)	Cast tensor to globally set energy precision.

Attributes

GLOBAL_CONFIG
GLOBAL_NP_FLOAT_PRECISION
SHARED_LIB_DIR
SHARED_LIB_MODULE
tf_py_version
EMBEDDING_NET_PATTERN
FITTING_NET_PATTERN
TYPE_EMBEDDING_PATTERN
ATTENTION_LAYER_PATTERN
TRANSFER_PATTERN
REMOVE_SUFFIX_DICT
default_tf_session_config
MODEL_VERSION
TF_VERSION
op_module
op_grads_module
GLOBAL_TF_FLOAT_PRECISION

deepmd.tf.env.GLOBAL_CONFIG

deepmd.tf.env.GLOBAL_NP_FLOAT_PRECISION

deepmd.tf.env.SHARED_LIB_DIR

deepmd.tf.env.SHARED_LIB_MODULE = 'lib'

deepmd.tf.env.tf_py_version

deepmd.tf.env.EMBEDDING_NET_PATTERN

deepmd.tf.env.FITTING_NET_PATTERN

deepmd.tf.env.TYPE_EMBEDDING_PATTERN

deepmd.tf.env.ATTENTION_LAYER_PATTERN

deepmd.tf.env.TRANSFER_PATTERN

deepmd.tf.env.REMOVE_SUFFIX_DICT

deepmd.tf.env.default_tf_session_config

deepmd.tf.env.reset_default_tf_session_config(cpu_only: bool)

Limit tensorflow session to CPU or not.

Parameters:

cpu_onlybool

If enabled, no GPU device is visible to the TensorFlow Session.

deepmd.tf.env.MODEL_VERSION

deepmd.tf.env.TF_VERSION

deepmd.tf.env.op_module

deepmd.tf.env.op_grads_module

deepmd.tf.env.GLOBAL_TF_FLOAT_PRECISION

deepmd.tf.env.global_cvt_2_tf_float(xx: tensorflow.compat.v1.Tensor) → tensorflow.compat.v1.Tensor

Cast tensor to globally set TF precision.

Parameters:

xxtf.Tensor

input tensor

Returns:

tf.Tensor

output tensor cast to GLOBAL_TF_FLOAT_PRECISION

deepmd.tf.env.global_cvt_2_ener_float(xx: tensorflow.compat.v1.Tensor) → tensorflow.compat.v1.Tensor

Cast tensor to globally set energy precision.

Parameters:

xxtf.Tensor

input tensor

Returns:

tf.Tensor

output tensor cast to GLOBAL_ENER_FLOAT_PRECISION