Python 无法运行Poincare嵌入示例以获取层次表示

我正试图复制Facebook Research发布的“现在”。但是我无法运行

example.sh

在重建设置中嵌入哺乳动物子树

OS：Ubuntu 16.04，使用Anaconda4.3.30、Python3.6.5、Pytorch0.4.0

命令：

NHTHREDS=2./example.sh

错误日志：

Using 2 threads
slurp: objects=1181, edges=6541
Indexing data
json_conf: {"distfn": "poincare", "dim": 5, "lr": 0.3, "batchsize": 10, "negs": 50}
Burnin: lr=0.003
'Traceback (most recent call last):\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in <listcomp>\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/harman_workspace/poincare-embeddings/model.py", line 185, in __getitem__\n    if n not in self._weights[t]:\nKeyError: tensor(491)\n'
Traceback (most recent call last):
  File "/home/harman/harman_workspace/poincare-embeddings/train.py", line 19, in train_mp
    train(model, data, optimizer, opt, log, rank, queue)
  File "/home/harman/harman_workspace/poincare-embeddings/train.py", line 46, in train
    for inputs, targets in loader:
  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 286, in __next__
    return self._process_next_batch(batch)
  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
KeyError: 'Traceback (most recent call last):\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in <listcomp>\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/harman_workspace/poincare-embeddings/model.py", line 185, in __getitem__\n    if n not in self._weights[t]:\nKeyError: tensor(491)\n'
'Traceback (most recent call last):\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in <listcomp>\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/harman_workspace/poincare-embeddings/model.py", line 185, in __getitem__\n    if n not in self._weights[t]:\nKeyError: tensor(491)\n'
Traceback (most recent call last):
  File "/home/harman/harman_workspace/poincare-embeddings/train.py", line 19, in train_mp
    train(model, data, optimizer, opt, log, rank, queue)
  File "/home/harman/harman_workspace/poincare-embeddings/train.py", line 46, in train
    for inputs, targets in loader:
  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 286, in __next__
    return self._process_next_batch(batch)
  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
KeyError: 'Traceback (most recent call last):\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in <listcomp>\n    samples = collate_fn([dataset[i] for i in batch_indices])\n  File "/home/harman/harman_workspace/poincare-embeddings/model.py", line 185, in __getitem__\n    if n not in self._weights[t]:\nKeyError: tensor(491)\n'

使用两个线程
slurp:objects=1181，edges=6541
索引数据
json_conf:{“distfn”：“庞加莱”，“dim”：5，“lr”：0.3，“batchsize”：10，“negs”：50}
磨合：lr=0.003
“回溯（最近一次调用）：\n文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第57行，在\u-worker\u-loop\n-samples=collate\u-fn（[dataset[i]表示批次索引中的i]）\n文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第57行，in\n samples=collate\u fn（[dataset[i]表示批次索引中的i]）\n文件“/home/harman/harman\u workspace/poincare embeddengs/model.py”，第185行，in\uu getitem\uu\n如果n不在self中。\u权重[t]：\nKeyError:tensor（491）\n
回溯（最近一次呼叫最后一次）：
文件“/home/harman/harman_workspace/poincare embeddings/train.py”，第19行，列车mp中
培训（模型、数据、优化器、opt、日志、排名、队列）
文件“/home/harman/harman_workspace/poincare embeddings/train.py”，第46行，列车中
对于输入，加载器中的目标：
文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第286行，下一页__
返回自。\处理\下一批\批次（批次）
文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第307行，在下一批处理中
raise batch.exc_类型（batch.exc_msg）
KeyError:“Traceback（最近一次调用）：\n File”/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site packages/torch/utils/data/dataloader.py”，第57行，在\u worker\u循环中\n samples=collate\u fn（[dataset[i]表示批索引中的i]）\n文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第57行，in\n samples=collate\u fn（[dataset[i]for i in batch\u index]）\n文件“/home/harman/harman\u workspace/poincare embeddings/model.py”，第185行，in\u getitem\n如果n不在self中。\权重[t]：\nKeyError:tensor（491）\n”
“Traceback（最近一次调用）：\n File”/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第57行，在\u-worker\u循环\n samples=collate\u fn（[dataset[i]表示批索引中的i]）\n File”/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py“，第57行，in\n samples=collate\u fn（[dataset[i]表示批次索引中的i]）\n File”/home/harman/harman\u workspace/poincare embeddings/model.py”，第185行，in\uu getitem\uuuuu\n如果n不在self中。\u权重[t]：\nKeyError:tensor（491）\n”
回溯（最近一次呼叫最后一次）：
文件“/home/harman/harman_workspace/poincare embeddings/train.py”，第19行，列车mp中
培训（模型、数据、优化器、opt、日志、排名、队列）
文件“/home/harman/harman_workspace/poincare embeddings/train.py”，第46行，列车中
对于输入，加载器中的目标：
文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第286行，下一页__
返回自。\处理\下一批\批次（批次）
文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第307行，在下一批处理中
raise batch.exc_类型（batch.exc_msg）
KeyError:“Traceback（最近一次调用）：\n File”/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site packages/torch/utils/data/dataloader.py”，第57行，在\u worker\u循环中\n samples=collate\u fn（[dataset[i]表示批索引中的i]）\n文件“/home/harman/anaconda3/envs/pytorch-venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py”，第57行，in\n samples=collate\u fn（[dataset[i]for i in batch\u index]）\n文件“/home/harman/harman\u workspace/poincare embeddings/model.py”，第185行，in\u getitem\n如果n不在self中。\权重[t]：\nKeyError:tensor（491）\n”

---

任何帮助都将不胜感激。

我也有同样的错误。这与它的版本有关。

这是解决方案，他们回答了关于h，w，t的int的变化 我试过了，但是失败了，我试过了torch 1.0.0到0.3.1的版本。它成功了

希望能解决问题