解决报错 RuntimeError: one of the variables needed for gradient computation has been modified by an inpl

解决报错 RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [16, 50]] is at version 3; expected version 2 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

self.ent_embeddings = nn.Embedding(self.params.total_ent, self.params.embedding_dim, max_norm=1)

改为

self.ent_embeddings = nn.Embedding(self.params.total_ent, self.params.embedding_dim)

！！！！ 调了40分钟