v1.3 compatibility #724
Closed
v1.3 compatibility #724
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
api branche update
fix bugs of single precision training and transfer
api update from amcadmus
@denghuilu fix bug of gpu namespace
add deepmd namespace for lib
better output format during training, testing and in lcurve.out
fix bugs of ase calculator and add tests
api update
prod_env_mat gpu update
refact model
add UUID support for DP
fix TB logdir remove bug
add coverage report for c/c++ api
check validity of data systems. print help message
* add Important hint for getting-started.md * add hint for some parameters * add Important hint for variables * Update argcheck.py * Update getting-started.md
Atention -> Attention
* Complete modification of tensor training, support combination of system with global/local label, and support polar label normalization to speed up training. Examples and documentation not added yet * modify dipole json to pass ut test * change json file (second time) to pass ut test * modify test_data_modifier_shuffle.py file to fit new args rule * modify data_modifier_shuffle: from dipole.npy to atomic_dipole.npy * modify the name of pref_weight to pref and pref_atomic_weight to pref_atomic, plus some implementation mentioned by Han Wang in May 7th's email * fix a bug occuring in ut test * fix args of polar_se_a.json, to pass ut test * change args: from loss_type to type, so that the args will be the same as ener mode, and will not cause conflict * add examples and readme for tensor fitting mode in May 14 * change readmd content of tensor fit * change the file name of readme file of tensor fitting * Update train-fitting-tensor.md * Update train-fitting-tensor.md * Update train-fitting-tensor.md * change the explanation of why some of lcurve.out is 0 * Update train-fitting-tensor.md * Update train-fitting-tensor.md
This ensures the out file will not be override when LAMMPS restarts. This commit may be conflicted with deepmodeling#392. Commit @5597ea2b49f96e99a52a9779b04b6c12e5a79a04 should be dropped.
* add an example of C++ inference to doc * fix broken link
* Add instructions for i-PI * Update doc/getting-started.md Co-authored-by: Jinzhe Zeng <[email protected]> Co-authored-by: tuoping <[email protected]> Co-authored-by: Jinzhe Zeng <[email protected]>
…ng in doc/troubleshooting/ (deepmodeling#657)
* fix bug of issue 668
…ing#685) * fix bug in op definition prod_virial_grad_multi_device.cc. This fixes 679 * fix bug in op definition prod_virial_grad_multi_device.cc. Co-authored-by: Han Wang <[email protected]>
* PR * modify CMakeLists.txt * modify CMakeLists.txt Fixed logic issues, but the absolute path has not yet been modified, leaving multiple errors thrown in the CMakeList * ADD FindROCM.cmake 1、ADD FindROCM.cmake 2、modify CMAKELISTS.TXT * modify FindROCM.cmake * modify FindROCM.cmake * Fixed issue * Update FindROCM.cmake * fix issue about wildcard * Modified duplicate * Use add_definitions to replace set(CMAKE_CXX_FLAGS) Co-authored-by: 李泽宇 <[email protected]> Co-authored-by: Han Wang <[email protected]>
* change default seed of constructors to `None` * initialize the parameters in different layers of the embedding net with different seeds * use different seeds for embedding net of different atom types * different seed for diffferent layers in the fitting nets. add UT for dipole model * support EF, fix bugs * fix bugs in wfc * fix bugs in tests * fig bug in test: duplicated model name * Fix typo in the type hint of `exclude_types` Co-authored-by: Han Wang <[email protected]>
* Doxyfile cannot be installed from pip, therefore I precompiled with doxyfile to generated xml/ from C++. And then api_cc.rst can be generated by breathe from xml/. * Edit conf.py to include doxygen * Edit conf.py to enable doxygen on readthedocs * Add specification in conf.py to refine the html layout of api_cc.rst * Included exhale to make prettier C++ API. * Update conf.py * add a function description to see if it works * it should be put into the header file? * add documents for DeepPot and DeepTensor * add documents for some common functions Co-authored-by: tuoping <[email protected]> Co-authored-by: Jinzhe Zeng <[email protected]>
Co-authored-by: Han Wang <[email protected]>
Co-authored-by: Han Wang <[email protected]>
|
created by mistake. See #725. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Created by mistake