jiyanbio

no 'GraphAttention' function implementation

1

class SequenceModel(nn.Module): def __init__(self, num_letters, hidden_dim, num_layers=3, vocab=20, top_k=30, num_positional_embeddings=16): """ Graph labeling network """ super(SequenceModel, self).__init__() # Hyperparameters self.top_k = top_k self.hidden_dim = hidden_dim self.positional_embeddings = PositionalEmbeddings(num_positional_embeddings) # Embedding...

loading h5 embeding file in train.py is killed due to large memory requirement

8

in train.py: print(f"# Loading embeddings", file=output) tensors = {} all_proteins = set(train_n0).union(set(train_n1)).union(set(test_n0)).union(set(test_n1)) for prot_name in tqdm(all_proteins): **tensors[prot_name] = torch.from_numpy(h5fi[prot_name][:, :])** Can it be modified with pytorch dataloader?