AttributeError: 'numpy.ndarray' object has no attribute 'device'

[zyrlia1018]

Using backend: pytorch
0%| | 0/1 [00:00<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 105, in
main()
File "main.py", line 101, in main
train(max_epochs, model, optimizer, scheduler, train_loader, valid_loader, project_name)
File "F:\zouyr\pythonProject\CIGIN-master\CIGIN_V2\train.py", line 40, in train
for samples in tq_loader:
File "D:\ANACONDA\envs\onionnet\lib\site-packages\tqdm\std.py", line 1178, in iter
for obj in iterable:
File "D:\ANACONDA\envs\onionnet\lib\site-packages\torch\utils\data\dataloader.py", line 517, in next
data = self._next_data()
File "D:\ANACONDA\envs\onionnet\lib\site-packages\torch\utils\data\dataloader.py", line 557, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "D:\ANACONDA\envs\onionnet\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\ANACONDA\envs\onionnet\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "main.py", line 74, in getitem
solute_graph = get_graph_from_smile(solute)
File "F:\zouyr\pythonProject\CIGIN-master\CIGIN_V2\molecular_graph.py", line 95, in get_graph_from_smile
G.ndata['x'] = np.array(node_features)
File "D:\ANACONDA\envs\onionnet\lib\site-packages\dgl\view.py", line 81, in setitem
self._graph._set_n_repr(self._ntid, self._nodes, {key : val})
File "D:\ANACONDA\envs\onionnet\lib\site-packages\dgl\heterograph.py", line 3994, in _set_n_repr
if F.context(val) != self.device:
File "D:\ANACONDA\envs\onionnet\lib\site-packages\dgl\backend\pytorch\tensor.py", line 76, in context
return input.device
AttributeError: 'numpy.ndarray' object has no attribute 'device'

[harrypotty18]

I have the same problem, did you solve it?

[harrypotty18]

I have fixed it!

1. G.ndata['x'] = np.array(node_features) should be:
   G.ndata['x'] = torch.from_numpy(np.array(node_features))
   G.edata['w'] = torch.from_numpy(np.array(edge_features))

2. solute_len_matrix = get_len_matrix(solute_graphs.batch_num_nodes), and
   solvent_len_matrix = get_len_matrix(solvent_graphs.batch_num_nodes should be like this:
   solute_len_matrix = get_len_matrix(solute_graphs.batch_num_nodes().numpy())
   solvent_len_matrix = get_len_matrix(solvent_graphs.batch_num_nodes().numpy())
   (File unity.py, line 58,59 in collate function)

[colour307]

hi,bro!
I have a question, when the model has been trained and save in "bese_model.tar", how to load and use the mode?

[zyrlia1018]

hi,bro! I have a question, when the model has been trained and save in "bese_model.tar", how to load and use the mode?
This project doesn't have an application file like eval.py, so you can write your own from train.py.

[colour307]

hi,bro! I have a question, when the model has been trained and save in "bese_model.tar", how to load and use the mode?
This project doesn't have an application file like eval.py, so you can write your own from train.py.

ok，i get it. I have already load the model. but I have another question. I use my dataset to predict the properties of energetic materials.the code is follow:
import dgl
import matplotlib.pyplot as plt
from torch.utils.data import DataLoader, Dataset
from GNNmodel import GNNModel
from GNNmolecular_graph import get_graph_from_smile
from rdkit import Chem

model = GNNModel()
model.load_state_dict(torch.load("runs/run-gnn/models/best_model.tar"))
#model=(torch.load("runs/run-gnn/models/best_model.tar"))
print(model)

use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")

def get_len_matrix(len_list):
len_list = np.array(len_list)
max_nodes = np.sum(len_list)
curr_sum = 0
len_matrix = []
for l in len_list:
curr = np.zeros(max_nodes)
curr[curr_sum:curr_sum + l] = 1
len_matrix.append(curr)
curr_sum += l
return np.array(len_matrix)

def collate(samples):
density_graphs, labels = map(list, zip(*samples))
density_graphs = dgl.batch(density_graphs)
density_len_matrix = get_len_matrix(density_graphs.batch_num_nodes().numpy())
return density_graphs, density_len_matrix, labels

class Dataclass(Dataset):
def init(self, dataset):
self.dataset = dataset

def __len__(self):
    return len(self.dataset)

def __getitem__(self, idx):

    density = self.dataset.iloc[idx]['SMILES']
    mol = Chem.MolFromSmiles(density)
    mol = Chem.AddHs(mol)
    density = Chem.MolToSmiles(mol)
    density_graph = get_graph_from_smile(density)

    delta_density = self.dataset.iloc[idx]['Delta_Density']
    return [density_graph, [delta_density]]

Data_df = pd.read_csv('data/Nitro aromatic 1.csv', encoding='ANSI', skipinitialspace=True)
test_df = Data_df.sample(frac=0.8)
test_dataset = Dataclass(test_df)
test_loader = DataLoader(test_dataset, collate_fn=collate, batch_size=128, shuffle=True)

test_batch = next(iter(test_loader))
model.to(device)
with torch.no_grad():
test_batch.to(device)

and the AttributeError: 'tuple' object has no attribute 'to', how to resolve the error? Thank you very much