Merge pull request #106 from mila-iqia/dev_atom_types_diffusion

Dev atom types diffusion

.gitignore

@@ -9,6 +9,12 @@ examples/data/
 examples/*/output/
 examples/*/lightning_logs/
 
+**/train_run*/
+**/valid_run*/
+**/processed/
+**/cache/
+**/output/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

data/SiGe_diffusion_1x1x1/config.yaml

@@ -0,0 +1,6 @@
+# Configuration for the dataloader
+batch_size: 1024
+num_workers: 0
+max_atom: 8
+spatial_dimension: 3
+elements: [Si, Ge]

data/SiGe_diffusion_1x1x1/create_data.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+source ../data_generation_functions.sh
+
+TEMPERATURE=300
+BOX_SIZE=1
+STEP=10000
+CROP=10000
+NTRAIN_RUN=10
+NVALID_RUN=5
+
+SW_PATH="../stillinger_weber_coefficients/SiGe.sw"
+IN_PATH="in.SiGe.lammps"
+CONFIG_PATH="config.yaml"
+
+create_data_function $TEMPERATURE $BOX_SIZE $STEP $CROP $NTRAIN_RUN $NVALID_RUN $SW_PATH $IN_PATH $CONFIG_PATH

data/SiGe_diffusion_1x1x1/in.SiGe.lammps

@@ -0,0 +1,34 @@
+log log.lammps
+
+units           metal
+atom_style      atomic
+atom_modify     map array
+
+lattice         diamond 5.5421217827
+region          box block 0 ${S} 0 ${S} 0 ${S}
+
+create_box      2 box 
+create_atoms    1 box basis 1 1 basis 2 1 basis 3 1 basis 4 1 basis 5 2 basis 6 2 basis 7 2 basis 8 2
+
+
+mass 1 28.0855
+mass 2 72.64
+
+group Si type 1
+group Ge type 2
+
+pair_style sw
+pair_coeff * * ${SW_PATH} Si Ge
+
+velocity all create ${T} ${SEED}
+
+dump dump_id all yaml 1 dump.${T}-${S}.yaml id element x y z fx fy fz
+dump_modify dump_id element Si Ge
+
+thermo_style yaml
+thermo 1
+#==========================Output files========================
+
+fix 1 all nvt temp ${T} ${T} 0.01
+run ${STEP}
+unfix 1

data/SiGe_diffusion_2x2x2/config.yaml

@@ -0,0 +1,6 @@
+# Configuration for the dataloader
+batch_size: 1024
+num_workers: 0
+max_atom: 64
+spatial_dimension: 3
+elements: [Si, Ge]

data/SiGe_diffusion_2x2x2/create_data.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+source ../data_generation_functions.sh
+
+TEMPERATURE=300
+BOX_SIZE=2
+STEP=10000
+CROP=10000
+NTRAIN_RUN=10
+NVALID_RUN=5
+
+SW_PATH="../stillinger_weber_coefficients/SiGe.sw"
+IN_PATH="in.SiGe.lammps"
+CONFIG_PATH="config.yaml"
+
+create_data_function $TEMPERATURE $BOX_SIZE $STEP $CROP $NTRAIN_RUN $NVALID_RUN $SW_PATH $IN_PATH $CONFIG_PATH

data/SiGe_diffusion_2x2x2/in.SiGe.lammps

@@ -0,0 +1,34 @@
+log log.lammps
+
+units           metal
+atom_style      atomic
+atom_modify     map array
+
+lattice         diamond 5.5421217827
+region          box block 0 ${S} 0 ${S} 0 ${S}
+
+create_box      2 box 
+create_atoms    1 box basis 1 1 basis 2 1 basis 3 1 basis 4 1 basis 5 2 basis 6 2 basis 7 2 basis 8 2
+
+
+mass 1 28.0855
+mass 2 72.64
+
+group Si type 1
+group Ge type 2
+
+pair_style sw
+pair_coeff * * ${SW_PATH} Si Ge
+
+velocity all create ${T} ${SEED}
+
+dump dump_id all yaml 1 dump.${T}-${S}.yaml id element x y z fx fy fz
+dump_modify dump_id element Si Ge
+
+thermo_style yaml
+thermo 1
+#==========================Output files========================
+
+fix 1 all nvt temp ${T} ${T} 0.01
+run ${STEP}
+unfix 1

data/SiGe_diffusion_3x3x3/config.yaml

@@ -0,0 +1,6 @@
+# Configuration for the dataloader
+batch_size: 1024
+num_workers: 0
+max_atom: 216
+spatial_dimension: 3
+elements: [Si, Ge]

data/SiGe_diffusion_3x3x3/create_data.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+source ../data_generation_functions.sh
+
+TEMPERATURE=300
+BOX_SIZE=3
+STEP=10000
+CROP=10000
+NTRAIN_RUN=10
+NVALID_RUN=5
+
+SW_PATH="../stillinger_weber_coefficients/SiGe.sw"
+IN_PATH="in.SiGe.lammps"
+CONFIG_PATH="config.yaml"
+
+create_data_function $TEMPERATURE $BOX_SIZE $STEP $CROP $NTRAIN_RUN $NVALID_RUN $SW_PATH $IN_PATH $CONFIG_PATH

data/SiGe_diffusion_3x3x3/in.SiGe.lammps

@@ -0,0 +1,34 @@
+log log.lammps
+
+units           metal
+atom_style      atomic
+atom_modify     map array
+
+lattice         diamond 5.5421217827
+region          box block 0 ${S} 0 ${S} 0 ${S}
+
+create_box      2 box 
+create_atoms    1 box basis 1 1 basis 2 1 basis 3 1 basis 4 1 basis 5 2 basis 6 2 basis 7 2 basis 8 2
+
+
+mass 1 28.0855
+mass 2 72.64
+
+group Si type 1
+group Ge type 2
+
+pair_style sw
+pair_coeff * * ${SW_PATH} Si Ge
+
+velocity all create ${T} ${SEED}
+
+dump dump_id all yaml 1 dump.${T}-${S}.yaml id element x y z fx fy fz
+dump_modify dump_id element Si Ge
+
+thermo_style yaml
+thermo 1
+#==========================Output files========================
+
+fix 1 all nvt temp ${T} ${T} 0.01
+run ${STEP}
+unfix 1

data/Si_diffusion_1x1x1/config.yaml

@@ -0,0 +1,6 @@
+# Configuration for the dataloader
+batch_size: 1024
+num_workers: 0
+max_atom: 8
+spatial_dimension: 3
+elements: [Si]

data/Si_diffusion_1x1x1/create_data.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+source ../data_generation_functions.sh
+
+TEMPERATURE=300
+BOX_SIZE=1
+STEP=10000
+CROP=10000
+NTRAIN_RUN=10
+NVALID_RUN=5
+
+SW_PATH="../stillinger_weber_coefficients/Si.sw"
+IN_PATH="in.Si.lammps"
+CONFIG_PATH="config.yaml"
+
+create_data_function $TEMPERATURE $BOX_SIZE $STEP $CROP $NTRAIN_RUN $NVALID_RUN $SW_PATH $IN_PATH $CONFIG_PATH

data/si_diffusion_2x2x2/in.si.lammps → data/Si_diffusion_1x1x1/in.Si.lammps

@@ -14,11 +14,13 @@ mass 1 28.0855
 group Si type 1
 
 pair_style sw
-pair_coeff * * ../../si.sw Si
+pair_coeff * * ${SW_PATH} Si
+
 
 velocity all create ${T} ${SEED}
 
-dump 1 all yaml 1 dump.si-${T}-${S}.yaml id type x y z fx fy fz
+dump dump_id all yaml 1 dump.${T}-${S}.yaml id element x y z fx fy fz
+dump_modify dump_id element Si
 
 thermo_style yaml
 thermo 1

data/Si_diffusion_2x2x2/config.yaml

@@ -0,0 +1,6 @@
+# Configuration for the dataloader
+batch_size: 1024
+num_workers: 0
+max_atom: 64
+spatial_dimension: 3
+elements: [Si]

data/Si_diffusion_2x2x2/create_data.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+source ../data_generation_functions.sh
+
+TEMPERATURE=300
+BOX_SIZE=2
+STEP=10000
+CROP=10000
+NTRAIN_RUN=10
+NVALID_RUN=5
+
+SW_PATH="../stillinger_weber_coefficients/Si.sw"
+IN_PATH="in.Si.lammps"
+CONFIG_PATH="config.yaml"
+
+create_data_function $TEMPERATURE $BOX_SIZE $STEP $CROP $NTRAIN_RUN $NVALID_RUN $SW_PATH $IN_PATH $CONFIG_PATH

data/si_diffusion_1x1x1_large/in.si.lammps → data/Si_diffusion_2x2x2/in.Si.lammps

@@ -14,11 +14,13 @@ mass 1 28.0855
 group Si type 1
 
 pair_style sw
-pair_coeff * * ../../si.sw Si
+pair_coeff * * ${SW_PATH} Si
+
 
 velocity all create ${T} ${SEED}
 
-dump 1 all yaml 1 dump.si-${T}-${S}.yaml id type x y z fx fy fz
+dump dump_id all yaml 1 dump.${T}-${S}.yaml id element x y z fx fy fz
+dump_modify dump_id element Si
 
 thermo_style yaml
 thermo 1

data/Si_diffusion_3x3x3/config.yaml

@@ -0,0 +1,6 @@
+# Configuration for the dataloader
+batch_size: 1024
+num_workers: 0
+max_atom: 216
+spatial_dimension: 3
+elements: [Si]

data/Si_diffusion_3x3x3/create_data.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+source ../data_generation_functions.sh
+
+TEMPERATURE=300
+BOX_SIZE=3
+STEP=10000
+CROP=10000
+NTRAIN_RUN=10
+NVALID_RUN=5
+
+SW_PATH="../stillinger_weber_coefficients/Si.sw"
+IN_PATH="in.Si.lammps"
+CONFIG_PATH="config.yaml"
+
+create_data_function $TEMPERATURE $BOX_SIZE $STEP $CROP $NTRAIN_RUN $NVALID_RUN $SW_PATH $IN_PATH $CONFIG_PATH

data/si_diffusion_1x1x1/in.si.lammps → data/Si_diffusion_3x3x3/in.Si.lammps

@@ -14,11 +14,13 @@ mass 1 28.0855
 group Si type 1
 
 pair_style sw
-pair_coeff * * ../../si.sw Si
+pair_coeff * * ${SW_PATH} Si
+
 
 velocity all create ${T} ${SEED}
 
-dump 1 all yaml 1 dump.si-${T}-${S}.yaml id type x y z fx fy fz
+dump dump_id all yaml 1 dump.${T}-${S}.yaml id element x y z fx fy fz
+dump_modify dump_id element Si
 
 thermo_style yaml
 thermo 1

data/data_generation_functions.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+
+function create_data_function() {
+    # this function drives the creation training and validation data with LAMMPS.
+    # It assumes :
+    #   - the function is sourced in a bash script (the "calling script") within the folder where the data is to be created.
+    #   - the calling script is invoked in a shell with the correct python environment.
+    #   - the LAMMPS input file follows a template and has all the passed variables defined.
+    #   - the paths are defined with respect to the folder where the generation script is called.
+
+    TEMPERATURE="$1"
+    BOX_SIZE="$2"
+    STEP="$3"
+    CROP="$4"
+    NTRAIN_RUN="$5"
+    NVALID_RUN="$6"
+    SW_PATH="$7"
+    IN_PATH="$8"
+    CONFIG_PATH="$9"
+
+    NRUN=$(($NTRAIN_RUN + $NVALID_RUN))
+
+    # Generate the data
+    for SEED in $(seq 1 $NRUN); do
+      if [ "$SEED" -le $NTRAIN_RUN ]; then
+        MODE="train"
+      else
+        MODE="valid"
+      fi
+      echo "Creating LAMMPS data for ${MODE}_run_${SEED}..."
+      mkdir -p "${MODE}_run_${SEED}"
+      cd "${MODE}_run_${SEED}"
+
+      # Calling LAMMPS with various arguments to keep it quiet. Also, the current location is "${MODE}_run_${SEED}", which is one
+      # folder away from the location of the calling script.
+      lmp  -echo none -screen none < ../$IN_PATH -v STEP $(($STEP + $CROP)) -v T $TEMPERATURE -v S $BOX_SIZE -v SEED $SEED -v SW_PATH ../$SW_PATH
+
+      # extract the thermodynamic outputs in a yaml file
+      egrep  '^(keywords:|data:$|---$|\.\.\.$|  - \[)' log.lammps > thermo_log.yaml
+
+      mkdir -p "uncropped_outputs"
+      mv "dump.${TEMPERATURE}-${BOX_SIZE}.yaml" uncropped_outputs/
+      mv thermo_log.yaml uncropped_outputs/
+
+      python ../../crop_lammps_outputs.py \
+          --lammps_yaml "uncropped_outputs/dump.${TEMPERATURE}-${BOX_SIZE}.yaml" \
+          --lammps_thermo "uncropped_outputs/thermo_log.yaml" \
+          --crop $CROP \
+          --output_dir ./
+
+      cd ..
+    done
+
+    # process the data
+    python ../process_lammps_data.py --data "./" --processed_datadir "./processed/" --config ${CONFIG_PATH}
+}