Merge pull request #24 from deepmodeling/master

master update

Author: denghuilu

.travis.yml

@@ -14,9 +14,10 @@ addons:
     - g++-7
     - gcc-8
     - g++-8
-matrix:
+jobs:
   include:
-    - python: 3.6
+    - stage: unit tests
+      python: 3.6
       env: 
       - CC=gcc-4.8
       - CXX=g++-4.8
@@ -65,14 +66,31 @@ matrix:
       env:
       - CC=gcc-5
       - CXX=g++-5
-      - TENSORFLOW_VERSION=2.0
+      - TENSORFLOW_VERSION=2.1
     - python: 3.7
       env:
       - CC=gcc-8
       - CXX=g++-8
-      - TENSORFLOW_VERSION=2.0
+      - TENSORFLOW_VERSION=2.1
+    - stage: build whls
+      services: docker
+      env:
+        - TWINE_USERNAME=__token__
+        - CIBW_BUILD="cp36-* cp37-*"
+        - CIBW_BEFORE_BUILD="pip install tensorflow && sed -i 's/libresolv.so.2\"/libresolv.so.2\", \"libtensorflow_framework.so.2\"/g' \$(find / -name policy.json)"
+        - CIBW_SKIP="*-win32 *-manylinux_i686"
+        - CC=gcc-7
+        - CXX=g++-7
+        - TENSORFLOW_VERSION=2.1
+      install:
+        - python -m pip install twine cibuildwheel==1.1.0 scikit-build setuptools_scm
+      script:
+        - python -m cibuildwheel --output-dir wheelhouse
+        - python setup.py sdist
+      after_success:
+        - if [[ $TRAVIS_TAG ]]; then python -m twine upload wheelhouse/*; python -m twine upload dist/*.tar.gz;  fi
 before_install:
-#  - pip install --upgrade pip
+  #- pip install --upgrade pip
   - pip install --upgrade setuptools
   - pip install tensorflow==$TENSORFLOW_VERSION
 install:

README.md

@@ -10,9 +10,9 @@
  	- [Deep Potential in a nutshell](#deep-potential-in-a-nutshell)
 - [Download and install](#download-and-install)
     - [Easy installation methods](#easy-installation-methods)
+      - [Offline packages](#offline-packages)
       - [With Docker](#with-docker)
       - [With conda](#with-conda)
-      - [Offline packages](#offline-packages)
     - [Install the python interaction](#install-the-python-interface)
       - [Install the Tensorflow's python interface](#install-the-tensorflows-python-interface)
       - [Install the DeePMD-kit's python interface](#install-the-deepmd-kits-python-interface)
@@ -90,8 +90,10 @@ Please follow our [github](https://github.com/deepmodeling/deepmd-kit) webpage t
 ## Easy installation methods
 There various easy methods to install DeePMD-kit. Choose one that you prefer. If you want to build by yourself, jump to the next two sections.
 
-### With Docker
-A docker for installing the DeePMD-kit on CentOS 7 is available [here](https://github.com/frankhan91/deepmd-kit_docker).
+After your easy installation, DeePMD-kit (`dp`) and LAMMPS (`lmp`) will be available to execute. You can try `dp -h` and `lmp -h` to see the help. `mpirun` is also available considering you may want to run LAMMPS in parallel.
+
+### Offline packages
+Both CPU and GPU version offline packages are avaiable in [the Releases page](https://github.com/deepmodeling/deepmd-kit/releases).
 
 ### With conda
 DeePMD-kit is avaiable with [conda](https://github.com/conda/conda). Install [Anaconda](https://www.anaconda.com/distribution/#download-section) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html) first.
@@ -101,28 +103,37 @@ To install the CPU version:
 conda install deepmd-kit=*=*cpu lammps-dp=*=*cpu -c deepmodeling
 ```
 
-To install the GPU version containing [CUDA 10.0](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver):
+To install the GPU version containing [CUDA 10.1](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver):
 ```bash
 conda install deepmd-kit=*=*gpu lammps-dp=*=*gpu -c deepmodeling
 ```
 
-### Offline packages
-Both CPU and GPU version offline package are avaiable in [the Releases page](https://github.com/deepmodeling/deepmd-kit/releases).
+### With Docker
+A docker for installing the DeePMD-kit is available [here](https://github.com/orgs/deepmodeling/packages/container/deepmd-kit).
+
+To pull the CPU version:
+```bash
+docker pull ghcr.io/deepmodeling/deepmd-kit:1.2.0_cpu
+```
+
+To pull the GPU version:
+```bash
+docker pull ghcr.io/deepmodeling/deepmd-kit:1.2.0_cuda10.1_gpu
+```
 
 ## Install the python interface 
 ### Install the Tensorflow's python interface
-First, check the python version and compiler version on your machine 
+First, check the python version on your machine 
 ```bash
-python --version; gcc --version
+python --version
 ```
-If your python version is 3.7.x, it is highly recommended that the GNU C/C++ compiler is higher than or equal to 5.0.
 
 We follow the virtual environment approach to install the tensorflow's Python interface. The full instruction can be found on [the tensorflow's official website](https://www.tensorflow.org/install/pip). Now we assume that the Python interface will be installed to virtual environment directory `$tensorflow_venv`
 ```bash
 virtualenv -p python3 $tensorflow_venv
 source $tensorflow_venv/bin/activate
 pip install --upgrade pip
-pip install --upgrade tensorflow==1.14.0
+pip install --upgrade tensorflow==2.1.0
 ```
 It is notice that everytime a new shell is started and one wants to use `DeePMD-kit`, the virtual environment should be activated by 
 ```bash
@@ -136,31 +147,21 @@ If one has multiple python interpreters named like python3.x, it can be specifie
 ```bash
 virtualenv -p python3.7 $tensorflow_venv
 ```
-If one needs the GPU support of deepmd-kit, the GPU version of tensorflow should be installed by
-```bash
-pip install --upgrade tensorflow-gpu==1.14.0
+If one does not need the GPU support of deepmd-kit and is concerned about package size, the CPU-only version of tensorflow should be installed by	
+```bash	
+pip install --upgrade tensorflow-cpu==2.1.0	
 ```
 To verify the installation, run
 ```bash
-python -c "import tensorflow as tf; sess=tf.Session(); print(sess.run(tf.reduce_sum(tf.random_normal([1000, 1000]))))"
+python -c "import tensorflow as tf;print(tf.reduce_sum(tf.random.normal([1000, 1000])))"
 ```
 One should remember to activate the virtual environment every time he/she uses deepmd-kit.
 
 ### Install the DeePMD-kit's python interface
 
-Clone the DeePMD-kit source code
+Execute
 ```bash
-cd /some/workspace
-git clone --recursive https://github.com/deepmodeling/deepmd-kit.git deepmd-kit -b devel
-```
-If one downloads the .zip file from the github, then the default folder of source code would be `deepmd-kit-master` rather than `deepmd-kit`. For convenience, you may want to record the location of source to a variable, saying `deepmd_source_dir` by
-```bash
-cd deepmd-kit
-deepmd_source_dir=`pwd`
-```
-Then execute
-```bash
-pip install .
+pip install deepmd-kit
 ```
 To test the installation, one may execute
 ```bash
@@ -189,11 +190,30 @@ If one does not need to use DeePMD-kit with Lammps or I-Pi, then the python inte
 
 ### Install the Tensorflow's C++ interface
 
-It is highly recommended that one keeps the same C/C++ compiler as the python interface. The C++ interface of DeePMD-kit was tested with compiler gcc >= 4.8. It is noticed that the I-Pi support is only compiled with gcc >= 4.9.
+Check the compiler version on your machine
+
+```
+gcc --version
+```
+
+The C++ interface of DeePMD-kit was tested with compiler gcc >= 4.8. It is noticed that the I-Pi support is only compiled with gcc >= 4.9.
 
 First the C++ interface of Tensorflow should be installed. It is noted that the version of Tensorflow should be in consistent with the python interface. We assume that you have followed our instruction and installed tensorflow python interface 1.14.0 with, then you may follow [the instruction for CPU](doc/install-tf.1.14.md) to install the corresponding C++ interface (CPU only). If one wants GPU supports, he/she should follow [the instruction for GPU](doc/install-tf.1.14-gpu.md) to install the C++ interface.
 
 ### Install the DeePMD-kit's C++ interface
+
+Clone the DeePMD-kit source code
+```bash
+cd /some/workspace
+git clone --recursive https://github.com/deepmodeling/deepmd-kit.git deepmd-kit
+```
+
+For convenience, you may want to record the location of source to a variable, saying `deepmd_source_dir` by
+```bash
+cd deepmd-kit
+deepmd_source_dir=`pwd`
+```
+
 Now goto the source code directory of DeePMD-kit and make a build place.
 ```bash
 cd $deepmd_source_dir/source
@@ -437,8 +457,6 @@ positional arguments:
 
 optional arguments:
   -h, --help            show this help message and exit
-  -t INTER_THREADS, --inter-threads INTER_THREADS
-                        With default value 0. Setting the "inter_op_parallelism_threads" key for the tensorflow, the "intra_op_parallelism_threads" will be set by the env variable OMP_NUM_THREADS
   --init-model INIT_MODEL
                         Initialize a model by the provided checkpoint
   --restart RESTART     Restart the training from the provided checkpoint
@@ -449,6 +467,15 @@ The keys `intra_op_parallelism_threads` and `inter_op_parallelism_threads` are T
 
 **`--restart model.ckpt`**, continues the training from the checkpoint `model.ckpt`.
 
+On some resources limited machines, one may want to control the number of threads used by DeePMD-kit. This is achieved by three environmental variables: `OMP_NUM_THREADS`, `TF_INTRA_OP_PARALLELISM_THREADS` and `TF_INTER_OP_PARALLELISM_THREADS`. `OMP_NUM_THREADS` controls the multithreading of DeePMD-kit implemented operations. `TF_INTRA_OP_PARALLELISM_THREADS` and `TF_INTER_OP_PARALLELISM_THREADS` controls `intra_op_parallelism_threads` and `inter_op_parallelism_threads`, which are  Tensorflow configurations for multithreading. An explanation is found [here](https://stackoverflow.com/questions/41233635/meaning-of-inter-op-parallelism-threads-and-intra-op-parallelism-threads).
+
+For example if you wish to use 3 cores of 2 CPUs on one node, you may set the environmental variables and run DeePMD-kit as follows:
+```bash
+export OMP_NUM_THREADS=6
+export TF_INTRA_OP_PARALLELISM_THREADS=3
+export TF_INTER_OP_PARALLELISM_THREADS=2
+dp train input.json
+```
 
 ## Freeze a model
 
@@ -606,18 +633,6 @@ rm -r *
 ```
 and redo the `cmake` process.
 
-## Training: TensorFlow abi binary cannot be found when doing training
-If you confront such kind of error: 
-
-```
-$deepmd_root/lib/deepmd/libop_abi.so: undefined symbol:
-_ZN10tensorflow8internal21CheckOpMessageBuilder9NewStringB5cxx11Ev
-```
-
-This may happen if you are using a gcc >= 5.0, and tensorflow was compiled with gcc < 5.0. You may set `-DOP_CXX_ABI=0` in the process of `cmake`.
-
-Another possible reason might be the large gap between the python version of TensorFlow and the TensorFlow c++ interface.
-
 ## MD: cannot run LAMMPS after installing a new version of DeePMD-kit
 This typically happens when you install a new version of DeePMD-kit and copy directly the generated `USER-DEEPMD` to a LAMMPS source code folder and re-install LAMMPS.
 

doc/install-tf.1.14.md

@@ -42,6 +42,7 @@ Now, copy the libraries to the tensorflow's installation directory:
 mkdir $tensorflow_root/lib
 cp -d bazel-bin/tensorflow/libtensorflow_cc.so* $tensorflow_root/lib/
 cp -d bazel-bin/tensorflow/libtensorflow_framework.so* $tensorflow_root/lib/
+cp -d $tensorflow_root/lib/libtensorflow_framework.so.1 $tensorflow_root/lib/libtensorflow_framework.so
 ```
 Then copy the headers
 ```bash

examples/water/train/polar.json

@@ -31,9 +31,9 @@
 
     "learning_rate" :{
 	"type":		"exp",
-	"start_lr":	0.001,
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.001,	
+	"stop_lr":	3.51e-8,
 	"_comment":	"that's all"
     },
 

examples/water/train/polar_se_a.json

@@ -3,7 +3,7 @@
     "_comment": " model parameters",
     "model":{
 	"type_map":		["O", "H"],
-	"data_stat_nbatch":	1,
+	"data_stat_nbatch":	10,
 	"descriptor" :{
 	    "type":		"se_a",
 	    "sel":		[46, 92],
@@ -18,7 +18,7 @@
 	"fitting_net": {
 	    "type":		"polar",
 	    "sel_type":		[0],
-	    "fit_diag":		true,
+	    "fit_diag":		false,
 	    "neuron":		[100, 100, 100],
 	    "resnet_dt":	true,
 	    "seed":		1,
@@ -29,9 +29,9 @@
 
     "learning_rate" :{
 	"type":		"exp",
-	"start_lr":	0.01,
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.01,
+	"stop_lr":	3.51e-7,
 	"_comment":	"that's all"
     },
 

examples/water/train/wannier.json

@@ -32,9 +32,9 @@
 
     "learning_rate" :{
 	"type":		"exp",
-	"start_lr":	0.001,
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.001,	
+	"stop_lr":	3.51e-8,
 	"_comment":	"that's all"
     },
 

examples/water/train/water.json

@@ -3,6 +3,7 @@
     "_comment": " model parameters",
     "model":{
 	"type_map":		["O", "H"],
+	"data_stat_nbatch":	10,
 	"descriptor": {
 	    "type":		"loc_frame",
 	    "sel_a":		[16, 32],
@@ -28,9 +29,9 @@
 
     "learning_rate" :{
 	"type":		"exp",
-	"start_lr":	0.001,
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.001,
+	"stop_lr":	3.51e-8,
 	"_comment":	"that's all"
     },
 

examples/water/train/water_se_a.json

@@ -24,9 +24,9 @@
 
     "learning_rate" :{
 	"type":		"exp",
-	"start_lr":	0.001,
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.001,	
+	"stop_lr":	3.51e-8,
 	"_comment":	"that's all"
     },
 

examples/water/train/water_se_ar.json

@@ -35,9 +35,9 @@
 
     "learning_rate" :{
 	"type":		"exp",
-	"start_lr":	0.005,
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.005,
+	"stop_lr":	1.76e-7,
 	"_comment":	"that's all"
     },
 

examples/water/train/water_se_r.json

@@ -23,9 +23,10 @@
     },
 
     "learning_rate" : {
-	"start_lr":	0.005,
+	"type":		"exp",
 	"decay_steps":	5000,
-	"decay_rate":	0.95,
+	"start_lr":	0.005,	
+	"stop_lr":	1.76e-7,
 	"_comment":	" that's all"
     },