我试图通过嵌入在计算机上重新执行GitHub项目以进行推荐，目的是首先嵌入在movieLens数据集中存在的用户和项目，然后使用内部产品预测收视率。完成所有组件的集成后，我在培训中遇到了错误。
代码：
from lightfm.datasets import fetch_movielens
movielens = fetch_movielens()
ratings_train, ratings_test = movielens['train'], movielens['test']
def _binarize(dataset):
dataset = dataset.copy()
dataset.data = (dataset.data >= 0.0).astype(np.float32)
dataset = dataset.tocsr()
dataset.eliminate_zeros()
return dataset.tocoo()
train, test = _binarize(movielens['train']), _binarize(movielens['test'])
class ScaledEmbedding(nn.Embedding):
""" Change the scale from normal to [0,1/embedding_dim] """
def reset_parameters(self):
self.weight.data.normal_(0, 1.0 / self.embedding_dim)
if self.padding_idx is not None:
self.weight.data[self.padding_idx].fill_(0)
class ZeroEmbedding(nn.Embedding):
def reset_parameters(self):
self.weight.data.zero_()
if self.padding_idx is not None:
self.weight.data[self.padding_idx].fill_(0)
class BilinearNet(nn.Module):
def __init__(self, num_users, num_items, embedding_dim, sparse=False):
super().__init__()
self.embedding_dim = embedding_dim
self.user_embeddings = ScaledEmbedding(num_users, embedding_dim,
sparse=sparse)
self.item_embeddings = ScaledEmbedding(num_items, embedding_dim,
sparse=sparse)
self.user_biases = ZeroEmbedding(num_users, 1, sparse=sparse)
self.item_biases = ZeroEmbedding(num_items, 1, sparse=sparse)
def forward(self, user_ids, item_ids):
user_embedding = self.user_embeddings(user_ids)
item_embedding = self.item_embeddings(item_ids)
user_embedding = user_embedding.view(-1, self.embedding_dim)
item_embedding = item_embedding.view(-1, self.embedding_dim)
user_bias = self.user_biases(user_ids).view(-1, 1)
item_bias = self.item_biases(item_ids).view(-1, 1)
dot = (user_embedding * item_embedding).sum(1)
return dot + user_bias + item_bias
def pointwise_loss(net,users, items, ratings, num_items):
negatives = Variable(
torch.from_numpy(np.random.randint(0,
num_items,
len(users))).cuda()
)
positives_loss = (1.0 - torch.sigmoid(net(users, items)))
negatives_loss = torch.sigmoid(net(users, negatives))
return torch.cat([positives_loss, negatives_loss]).mean()
embedding_dim = 128
minibatch_size = 1024
n_iter = 10
l2=0.0
sparse = True
num_users, num_items = train.shape
net = BilinearNet(num_users,
num_items,
embedding_dim,
sparse=sparse).cuda()
optimizer = optim.Adagrad(net.parameters(),
weight_decay=l2)
for epoch_num in range(n_iter):
users, items, ratings = shuffle(train)
user_ids_tensor = torch.from_numpy(users).cuda()
item_ids_tensor = torch.from_numpy(items).cuda()
ratings_tensor = torch.from_numpy(ratings).cuda()
epoch_loss = 0.0
for (batch_user,
batch_item,
batch_ratings) in zip(_minibatch(user_ids_tensor,
minibatch_size),
_minibatch(item_ids_tensor,
minibatch_size),
_minibatch(ratings_tensor,
minibatch_size)):
user_var = Variable(batch_user)
item_var = Variable(batch_item)
ratings_var = Variable(batch_ratings)
optimizer.zero_grad()
loss = pointwise_loss(net,user_var, item_var, ratings_var, num_items)
epoch_loss += loss.data[0]
loss.backward()
optimizer.step()
print('Epoch {}: loss {}'.format(epoch_num, epoch_loss))
错误：
RuntimeError Traceback (most recent call last) <ipython-input-87-dcd04440363f> in <module>()
22 ratings_var = Variable(batch_ratings)
23 optimizer.zero_grad()
---> 24 loss = pointwise_loss(net,user_var, item_var, ratings_var, num_items)
25 epoch_loss += loss.data[0]
26 loss.backward()
<ipython-input-86-679e10f637a5> in pointwise_loss(net, users, items, ratings, num_items)
8
9 positives_loss = (1.0 - torch.sigmoid(net(users, items)))
---> 10 negatives_loss = torch.sigmoid(net(users, negatives))
11
12 return torch.cat([positives_loss, negatives_loss]).mean()
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in
__call__(self, *input, **kwargs)
491 result = self._slow_forward(*input, **kwargs)
492 else:
--> 493 result = self.forward(*input, **kwargs)
494 for hook in self._forward_hooks.values():
495 hook_result = hook(self, input, result)
<ipython-input-58-3946abf81d81> in forward(self, user_ids, item_ids)
16
17 user_embedding = self.user_embeddings(user_ids)
---> 18 item_embedding = self.item_embeddings(item_ids)
19
20 user_embedding = user_embedding.view(-1, self.embedding_dim)
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in
__call__(self, *input, **kwargs)
491 result = self._slow_forward(*input, **kwargs)
492 else:
--> 493 result = self.forward(*input, **kwargs)
494 for hook in self._forward_hooks.values():
495 hook_result = hook(self, input, result)
~\Anaconda3\lib\site-packages\torch\nn\modules\sparse.py in forward(self, input)
115 return F.embedding(
116 input, self.weight, self.padding_idx, self.max_norm,
--> 117 self.norm_type, self.scale_grad_by_freq, self.sparse)
118
119 def extra_repr(self):
~\Anaconda3\lib\site-packages\torch\nn\functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse) 1504 # remove once script supports set_grad_enabled 1505
_no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 1506 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) 1507 1508
RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got CUDAType instead (while checking arguments for embedding)
有人可以帮我吗？
答案 0 :(得分：2)
我建议您检查输入类型 我有同样的问题，可以通过将输入类型从int32转换为int64来解决。（在win10上运行） 例如：
x = torch.tensor(train).to(torch.int64)
答案 1 :(得分：2)
对于类似错误：
运行时错误：参数＃1'indices'的预期张量具有标量类型Long；但是却改为CUDAType（在检查嵌入参数时）
b_input_ids = torch.tensor(b_input_ids).to(device).long()
以上转换在Oses上完美无缺
答案 2 :(得分：0)
对我来说，错误是由 type_as 引起的。
将 .type_as(z) 更改为 .to(self.device) 解决了问题。