1

如何将流引导视频完成 (FGVC) 用于个人文件？对于那些想从 Google Colab 平台免费使用 FGVC 的人来说，各种官方来源没有指定操作（https://colab.research.google.com/drive/1pb6FjWdwq_q445rG2NP0dubw7LKNUkqc?usp=sharing）。作为测试，我将视频上传到 Google Drive（与我运行 Google Colab 脚本的帐户相同），该视频分为多个帧，位于名为“demo1.zip”的 .zip 文件夹中。然后我运行序列中的第一个脚本，称为“准备环境”，我通过公共链接激活视频共享，并复制了第二个脚本中的链接（紧跟第一个单词“wget ​​​-quiet”）和第一个条目“rm”我输入了“demo1.zip”，与我的视频文件的名称有关。在阅读了第二个脚本的运行按钮上方的说明后，我继续这样做：“我们展示了一个 15 帧序列的演示。要处理您自己的数据，只需上传序列并指定路径。” 也运行第二个脚本，这是成功的，我的视频文件已加载。然后我转到第四个（也是最后一个）脚本，该脚本包括通过 AI 处理内容以获得具有扩大视野（FOV => 更大纵横比）的最终产品。运行几秒钟后，该过程以错误结束：

  File "video_completion.py", line 613, in <module>
    main (args)
  File "video_completion.py", line 576, in main
    video_completion_sphere (args)
  File "video_completion.py", line 383, in video_completion_sphere
    RAFT_model = initialize_RAFT (args)
  File "video_completion.py", line 78, in initialize_RAFT
    model.load_state_dict (torch.load (args.model))
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 594, in load
    return _load (opened_zipfile, map_location, pickle_module, ** pickle_load_args)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 853, in _load
    result = unpickler.load ()
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 845, in persistent_load
    load_tensor (data_type, size, key, _maybe_decode_ascii (location))
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 834, in load_tensor
    loaded_storages [key] = restore_location (storage, location)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 175, in default_restore_location
    result = fn (storage, location)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 151, in _cuda_deserialize
    device = validate_cuda_device (location)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 135, in validate_cuda_device
    raise RuntimeError ('Attempting to deserialize object on a CUDA'
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available () is False. If you are running on a CPU-only machine, please use torch.load with map_location = torch.device ('cpu') to map your storages to the CPU.

执行有什么问题？有没有办法修复并允许使用 Google Colab 完成该过程？让我知道！

4

0 回答 0