v1.2.3

New feature:

• added tool to convert a v1.2 compatible model to v1.3 compatible model.

Bug fixing:

• neighbor list bug in the GPU implementation.

v1.3.1

Bug fixing:

• Compulsory label requirement if the corresponding prefactor is set to non-zero. The current behavior is when then label is missing, the corresponding term does not appear in the loss function
• Optional requirement of loss in dipole and polarizability training

Improvement:

• Recommend consistent TensorFlow versions for python and C++ interfaces.

v1.3.0

New features:

• Support input script in yaml format #271
• Enable setting test size individually for each system #267

Improvements:

• Support building with TF2.3
• Improved documentation. Automatically generated doc page. Explained keys in the training input script. #297
• Compile with latest stable release of lammps (stable_29Oct2020). Old releases are not supported anymore. #302
• Multi-device and multi-implementation support for OPs. #254

Bug fixings:

• Allow ntypes_model > ntypes_data (fix #261) #296
• Bug in setting coeff_ener when coeff_atom_ener is given #290

v1.2.2

New features:

• fast gelu implementation
• relax the restriction on the maximal number of neighbors to 4096
• one-sided embedding net

Bug fixings:

• check if the cell volume is positive.
• bugs of dplr
• loading coord when data has only one frame
• ase calculator None-PBC system
• details printing when testing on multiple systems.
• bugs in transform

v1.1.5

Bug fixing:

• GPU implementation: stop the program when the number of neighbors is larger than the limit.

v1.2.0

New features of dp train:

• Polarizability and dipole fitting
• If provided with stop_lr, the decay_rate will be computed automatically
• Support non-pbc system: add an empty file named nopbc to the data system.
• Use envs TF_INTRA_OP_PARALLELISM_THREADS and TF_INTER_OP_PARALLELISM_THREADS to control the multi-threading of tf, clean up command line options.
• When the key systems is provided with a string, all possible systems will be recursively searched within the dir given by systems
• User specific atomic energy.
• Exclude types when building descriptors.
• User specific activation function and network precision.
• Transform neural network parameters.

New features of dp test:

• Recursively search all possible systems in a directory.
• Weighted average of test results

Bug fixings:

• Cuda version compatibility
• raw_to_set when nframe == 1
• Slow test when testing multiple systems
• Potentially wrong neighbor list when number of neighbors is larger than 256.
• Fix bug #163 : broken lib link of dp_ipi
• Infering number of types from data

v1.1.4

Big fixings:

• KeyError in dp test (#165 )
• Protect the std calculation

v1.1.3

Bug fixings:

• raw_to_set.sh does not work for data system that has only one frame.
• dp test ignores type_map.raw
• cannot compile lammps with deepmd-kit that does not use GPU
• compiling problems in debug mode
• GPU kernel threading bug that leads to wrong model deviation

v1.1.2

New features:

• GPU supported descriptor computation
• Support ASE evaluation of deep potential
• Trainable (true/false) descriptors

Bug fixings:

• import warnings in common.py
• relative force model deviation
• freezing bug in se_ar

v1.1.1

Bug fixing:

• pass the warning of upper/lower index bound but do not correct the index.