schnet from_pretrained crashed

[FUVHasagi]

🐛 Describe the bug

the pretrained function returns ModuleNotFoundError: No module named 'schnetpack.atomistic.model'
Due to the changes in the schnetpack library, the model now belong to schnet.model instead of atomistic.model
Is there anything I can do with it, thank you
`import argparse
import os.path as osp

import torch
from tqdm import tqdm

from torch_geometric.datasets import QM9
from torch_geometric.loader import DataLoader
from torch_geometric.nn import SchNet

parser = argparse.ArgumentParser()
parser.add_argument('--cutoff', type=float, default=10.0,
help='Cutoff distance for interatomic interactions')
args = parser.parse_args()

path = osp.join(osp.dirname(osp.realpath(file)), '..', 'data', 'QM9')
dataset = QM9(path)

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

for target in range(12):
model, datasets = SchNet.from_qm9_pretrained(path, dataset, target)
train_dataset, val_dataset, test_dataset = datasets

model = model.to(device)
loader = DataLoader(test_dataset, batch_size=256)

maes = []
for data in tqdm(loader):
    data = data.to(device)
    with torch.no_grad():
        pred = model(data.z, data.pos, data.batch)
    mae = (pred.view(-1) - data.y[:, target]).abs()
    maes.append(mae)

mae = torch.cat(maes, dim=0)

# Report meV instead of eV.
mae = 1000 * mae if target in [2, 3, 4, 6, 7, 8, 9, 10] else mae

print(f'Target: {target:02d}, MAE: {mae.mean():.5f} ± {mae.std():.5f}')`

Versions

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] pytorch-lightning==2.2.1
[pip3] torch==2.2.1
[pip3] torch-ema==0.3
[pip3] torch_geometric==2.5.2
[pip3] torchaudio==2.2.1
[pip3] torchmetrics==1.3.2
[pip3] torchvision==0.17.1
[pip3] triton==2.2.0
[conda] blas 2.116 mkl conda-forge
[conda] blas-devel 3.9.0 16_linux64_mkl conda-forge
[conda] ffmpeg 4.3 hf484d3e_0 pytorch
[conda] libblas 3.9.0 16_linux64_mkl conda-forge
[conda] libcblas 3.9.0 16_linux64_mkl conda-forge
[conda] libjpeg-turbo 2.0.0 h9bf148f_0 pytorch
[conda] liblapack 3.9.0 16_linux64_mkl conda-forge
[conda] liblapacke 3.9.0 16_linux64_mkl conda-forge
[conda] mkl 2022.1.0 h84fe81f_915 conda-forge
[conda] mkl-devel 2022.1.0 ha770c72_916 conda-forge
[conda] mkl-include 2022.1.0 h84fe81f_915 conda-forge
[conda] numpy 1.26.4 py310hb13e2d6_0 conda-forge
[conda] pyg 2.5.2 py310_torch_2.2.0_cu118 pyg
[conda] pytorch 2.2.1 py3.10_cuda11.8_cudnn8.7.0_0 pytorch
[conda] pytorch-cuda 11.8 h7e8668a_5 pytorch
[conda] pytorch-lightning 2.2.1 pyhd8ed1ab_0 conda-forge
[conda] pytorch-mutex 1.0 cuda pytorch
[conda] torch-ema 0.3 pyhd8ed1ab_0 conda-forge
[conda] torchaudio 2.2.1 py310_cu118 pytorch
[conda] torchmetrics 1.3.2 pyhd8ed1ab_0 conda-forge
[conda] torchtriton 2.2.0 py310 pytorch
[conda] torchvision 0.17.1 py310_cu118 pytorch

[cycal1020]

Hello, I also encountered some problems while training SchNet. Can I communicate with you? Could you please provide a contact information, such as email?

[dbehera-zenon]

I have also encountered same problem, please provide us some solution.

Thanks

[rusty1s]

I'll take a look.