Merge devel into master#1787
Merged
amcadmus merged 62 commits intodeepmodeling:masterfrom Jun 26, 2022
Merged
Conversation
Merge master into devel
…#1644) * change default NN precision from `float64` to `default` Fix deepmodeling#1643. * update type embedding * remove extra . * remove extra .
* update TF installation doc * Revert "update TF installation doc" This reverts commit 4d24036. * add a seperated doc * fix typo
* migrate test_cc from conda to docker * change image * update image * set CXX_STANDARD before add_library * use bash instead of sh
* use float constant for float functions * kk * kk * we have cmath in c++ 11 * use float functions * revert changes to legacy codes * fix typo in ewald.cc * fix lib/tests CUDA installation * use tanh for float Co-authored-by: Denghui Lu <denghuilu@pku.edu.cn> Co-authored-by: Denghui Lu <denghuilu@pku.edu.cn>
Co-authored-by: Han Wang <wang_han@iapcm.ac.cn>
A tensor can be reused in a graph but a numpy array can't. This avoids saving duplicated constants in the case deepmodeling#1423.
A graph has a size limitation of 2 GB, so if we do not clean the graph, the limitation will be indeed 1GB...
* fix rcut in hybrid model compression
The current way `self.graph.get_operation_by_name('ProdEnvMatA')` to get `rcut` is incorrect for hybrid models. There may be several ProdEnvMatA ops in a graph.
(cherry picked from commit 34a4e9b)
* fix se_r attr
* rewrite data doc Current data doc was wrttien in the inital version. It's out-of-date. * provide the name of raw file * add raw file to input properties and labeled properties
jsdelivr, which is the default mathjax path in the sphinx, has been blocked in China. See jsdelivr/jsdelivr#18392. Of course, we hope our rendered equations can be shown in China.
* Update training.md * Fix typo * Update overall.md * Update overall.md * Update train-energy.md * Update train-fitting-tensor.md * Update train-fitting-tensor.md * Update train-fitting-tensor.md * Update README.md * Update README.md
Fix deepmodeling#1679. The bug was introduced in deepmodeling#1610.
…eepmodeling#1686) * fix bug of model compression training with se_e2_r type descriptor * Update source/op/tabulate_multi_device.cc Co-authored-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu> Co-authored-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
* Change Typo "short" --> "shot" * Update index.md
…ng#1695) * set default fparam and aparam stat and recover from graph fix deepmodeling#1692 * check avg and std separately
1. Compare square value instead of square root value. Square root is expensive. 2. Compare float instead of double, considering rcut is provided as float. `ProdEnvMatA` (CPU) is observed to improve over 5%.
* implement parallelism for neighbor stat * bugfix * fix typo in docstring
* render equations in markdown files * enable dollarmath in the sphinx * fix Angstrom sybol; it's not supported by mathjax * fix equations of the learning rate * fix equations * fix equations * fix equations * fix equations * Update lammps-command.md * use \cdots for ... * add the detailed keys
Follow up deepmodeling#1723. It's quite confusing that no `version_info.h` is generated when building TF 2.9 C++ library only (but Python library has). So the definition is copied here..
* using int64 within the memory allocation operations * reduce temp memory allocation * change the related python implementations * fix UT error * fix reset error
* support atom_ener_coeff * bugfix; add option * reshape atom_ener_coeff before multiply * add UT for "default" * fix typo
* replace 1./sqrt with rsqrt Per NVIDIA doc: > 11.1.3. Reciprocal Square Root > The reciprocal square root should always be invoked explicitly as rsqrtf() for single precision and rsqrt() for double precision. The compiler optimizes 1.0f/sqrtf(x) into rsqrtf() only when this does not violate IEEE-754 semantics. See https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html#reciprocal-square-root * remove FPTYPE as it has been FPTYPE * apply the same opt for ROCM
* add DPRc doc * fix json * add links
by changing the main font to Symbola. This font has been installed in the RTD image. But if one wants build locally, first install the font: apt-get install fonts-symbola
* add a script to build TF from source * remove todo
* add auto cli docs This commit adds the automatic documentation for command line interface, generated by a sphinx extension. * move cli out of inference it should be not related to inference..
Before this commit, only global site-packages directory was searched.
1e-2 is too small making the compression table have a large upper.
So one can click the link to learn more about a key (like type, default value, etc.). Note: links are only available in the sphinx-generated HTML or PDF. It will be not shown on the GitHub. This commit also fixes two typos.
... and update some examples with depracated parameters.
From the perspective of unit tests, there is no differece between testing 1 step and 100 steps.
... it looks that `gprcio` (dependency of TF) has dropped the manylinux2010 wheels
exhale will run doxygen automatically, so there is no need to manually run it.
* bump LAMMPS version to stable_23Jun2022 * update conda package name
Codecov Report
@@ Coverage Diff @@
## master #1787 +/- ##
==========================================
- Coverage 76.15% 76.08% -0.08%
==========================================
Files 94 96 +2
Lines 7850 7927 +77
==========================================
+ Hits 5978 6031 +53
- Misses 1872 1896 +24
Continue to review full report at Codecov.
|
njzjz
approved these changes
Jun 26, 2022
Member
njzjz
left a comment
njzjz
left a comment
There was a problem hiding this comment.
It looks like I contribute too many commits LOL
Member
Author
which is definitely welcome |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
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.
No description provided.