Hi,
I am facing a problem with Embeddings: IndexError: index out of range in self as shown bellow:
y = self.ensemble(x, mask)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/lucasgongora/Documents/KTH/Courses/Thesis/tracab-masters-ball-from-context/model/networks.py", line 33, in forward
src = self.encoder(src) * math.sqrt(self.ninp)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/sparse.py", line 145, in forward
return F.embedding(
File "/usr/local/lib/python3.8/dist-packages/torch/nn/functional.py", line 1913, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self
For context, I am running a database x with dimensions (batch_size x 50 x 48). And I need to input with this configuration. I am training it on The transformer network
class TransformerModel(nn.Module):
def __init__(self, ntoken, ninp, nhead, nhid, nlayers, dropout=0.5):
super(TransformerModel, self).__init__()
from torch.nn import TransformerEncoder, TransformerEncoderLayer
self.model_type = 'Transformer'
self.pos_encoder = PositionalEncoding(ninp, dropout)
encoder_layers = TransformerEncoderLayer(ninp, nhead, nhid, dropout)
self.transformer_encoder = TransformerEncoder(encoder_layers, nlayers)
self.encoder = nn.Embedding(ntoken, ninp)
self.ninp = ninp
self.decoder = nn.Linear(ninp, ntoken)
self.init_weights()
def generate_square_subsequent_mask(self, sz):
mask = (torch.triu(torch.ones(sz, sz)) == 1).transpose(0, 1)
mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
return mask
def init_weights(self):
initrange = 0.1
self.encoder.weight.data.uniform_(-initrange, initrange)
self.decoder.bias.data.zero_()
self.decoder.weight.data.uniform_(-initrange, initrange)
def forward(self, src, src_mask):
src = self.encoder(src) * math.sqrt(self.ninp)
src = self.pos_encoder(src)
output = self.transformer_encoder(src, src_mask)
output = self.decoder(output)
return output
class PositionalEncoding(nn.Module):
def __init__(self, d_model, dropout=0.1, max_len=5000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = torch.zeros(max_len, d_model)
position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
pe[:, 0::2] = torch.sin(position * div_term)
pe[:, 1::2] = torch.cos(position * div_term)
pe = pe.unsqueeze(0).transpose(0, 1)
self.register_buffer('pe', pe)
def forward(self, x):
x = x + self.pe[:x.size(0), :]
return self.dropout(x)
class Ensemble_Networks(nn.Module):
def __init__(self, num_output_target, num_in_players, num_output_players, dim_output_players, num_features,
num_inds_players=64, dim_hidden_players=128, num_heads_players=4):
super(Ensemble_Networks, self).__init__()
self.ensemble = TransformerModel(ntoken=48, ninp=50, nhead=1, nhid=200, nlayers=2, dropout=0.5)
def forward(self, x, mask):
y = self.ensemble(x, mask)
return y
I believe the error is at: self.ensemble = TransformerModel(ntoken=48, ninp=50, nhead=1, nhid=200, nlayers=2, dropout=0.5) where i cannot find the proper dimensions of the variables of the function.
I am running something like:
mask = self.generate_square_subsequent_mask(50)
for Epochs in trange(self.n_epochs, desc='Epoch'):
for step in range(iter_size):
x, y = data_import.create_batches(x_train, y_train)
y_pred = self.model(x, mask)