File size: 5,965 Bytes
a244197 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | # Script for evaluating configurations contained in an xyz file with a trained model
import time
import argparse
import ase.io
import numpy as np
import torch
from onescience.datapipes.materials.pyg_stack.core.utils import config_from_atoms
from onescience.datapipes.materials.pyg_stack.core.atomic_data import AtomicData
from onescience.datapipes.materials.tools import torch_geometric, torch_tools, utils
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument("--configs", help="path to XYZ configurations", required=True)
parser.add_argument("--model", help="path to model", required=True)
parser.add_argument("--output", help="output path", required=True)
parser.add_argument(
"--device",
help="select device",
type=str,
choices=["cpu", "cuda"],
default="cpu",
)
parser.add_argument(
"--default_dtype",
help="set default dtype",
type=str,
choices=["float32", "float64"],
default="float64",
)
parser.add_argument("--batch_size", help="batch size", type=int, default=64)
parser.add_argument(
"--compute_stress",
help="compute stress",
action="store_true",
default=False,
)
parser.add_argument(
"--return_contributions",
help="model outputs energy contributions for each body order, only supported for MACE, not ScaleShiftMACE",
action="store_true",
default=False,
)
parser.add_argument(
"--info_prefix",
help="prefix for energy, forces and stress keys",
type=str,
default="MACE_",
)
parser.add_argument(
"--head",
help="Model head used for evaluation",
type=str,
required=False,
default=None,
)
return parser.parse_args()
def main() -> None:
args = parse_args()
run(args)
def run(args: argparse.Namespace) -> None:
torch_tools.set_default_dtype(args.default_dtype)
device = torch_tools.init_device(args.device)
# Load model
model = torch.load(f=args.model, map_location=args.device)
model = model.to(args.device)
model.eval() # ✅ 保持 eval，不要关掉 requires_grad
# Load data and prepare input
atoms_list = ase.io.read(args.configs, index=":")
if args.head is not None:
for atoms in atoms_list:
atoms.info["head"] = args.head
configs = [config_from_atoms(atoms) for atoms in atoms_list]
z_table = utils.AtomicNumberTable([int(z) for z in model.atomic_numbers])
try:
heads = model.heads
except AttributeError:
heads = None
data_loader = torch_geometric.dataloader.DataLoader(
dataset=[
AtomicData.from_config(
config, z_table=z_table, cutoff=float(model.r_max), heads=heads
)
for config in configs
],
batch_size=args.batch_size,
shuffle=False,
drop_last=False,
)
# Collect data
energies_list = []
contributions_list = []
stresses_list = []
forces_collection = []
total_time = 0.0
num_batches = 0
total_cfgs = len(configs)
start_total = time.time()
for batch in data_loader:
batch = batch.to(device)
if args.device == "cuda":
torch.cuda.synchronize()
start = time.time()
output = model(batch.to_dict(), compute_stress=args.compute_stress)
if args.device == "cuda":
torch.cuda.synchronize()
end = time.time()
total_time += (end - start)
num_batches += 1
energies_list.append(torch_tools.to_numpy(output["energy"]))
if args.compute_stress:
stresses_list.append(torch_tools.to_numpy(output["stress"]))
if args.return_contributions:
contributions_list.append(torch_tools.to_numpy(output["contributions"]))
forces = np.split(
torch_tools.to_numpy(output["forces"]),
indices_or_sections=batch.ptr[1:],
axis=0,
)
forces_collection.append(forces[:-1]) # drop last as its empty
end_total = time.time()
# ✅ 打印时间
if num_batches > 0 and total_cfgs > 0:
avg_time_batch = total_time / num_batches
avg_time_cfg = total_time / total_cfgs
print(f"Average inference time per batch: {avg_time_batch:.6f} s")
print(f"Average inference time per configuration: {avg_time_cfg:.6f} s")
print(f"Total inference time (only forward): {total_time:.6f} s")
print(f"Wall clock time (data+forward): {end_total - start_total:.6f} s")
else:
print("No batches were processed.")
# Process outputs
energies = np.concatenate(energies_list, axis=0)
forces_list = [
forces for forces_list in forces_collection for forces in forces_list
]
assert len(atoms_list) == len(energies) == len(forces_list)
if args.compute_stress:
stresses = np.concatenate(stresses_list, axis=0)
assert len(atoms_list) == stresses.shape[0]
if args.return_contributions:
contributions = np.concatenate(contributions_list, axis=0)
assert len(atoms_list) == contributions.shape[0]
# Store data in atoms objects
for i, (atoms, energy, forces) in enumerate(zip(atoms_list, energies, forces_list)):
atoms.calc = None # crucial
atoms.info[args.info_prefix + "energy"] = energy
atoms.arrays[args.info_prefix + "forces"] = forces
if args.compute_stress:
atoms.info[args.info_prefix + "stress"] = stresses[i]
if args.return_contributions:
atoms.info[args.info_prefix + "BO_contributions"] = contributions[i]
# Write atoms to output path
ase.io.write(args.output, images=atoms_list, format="extxyz")
if __name__ == "__main__":
main()
|