NTU ML2023Spring Part3.8 Auto encoder

ml2023 作业的模板代码链接挂了，因此做的是 ml2022 的相关作业．

发现没有标 todo，于是随机找了几个 fc 层把参数改大点，再按照 这里 的做法加了点 data augmentation．

在 Kaggle 上跑了几个小时，训练完之后报错：

UnpicklingError                           Traceback (most recent call last)
/tmp/ipykernel_19/897056216.py in <cell line: 0>()
     10 # load trained model
     11 checkpoint_path = f'last_model_{model_type}.pt'
---> 12 model = torch.load(checkpoint_path)
     13 model.eval()
     14 

/usr/local/lib/python3.11/dist-packages/torch/serialization.py in load(f, map_location, pickle_module, weights_only, mmap, **pickle_load_args)
   1468                         )
   1469                     except pickle.UnpicklingError as e:
-> 1470                         raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
   1471                 return _load(
   1472                     opened_zipfile,

UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint. 
 (1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
 (2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
 WeightsUnpickler error: Unsupported global: GLOBAL __main__.VAE was not an allowed global by default. Please use `torch.serialization.add_safe_globals([VAE])` or the `torch.serialization.safe_globals([VAE])` context manager to allowlist this global if you trust this class/function.

Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.

简单粗暴地在 torch.load 里加了个 weights_only=False，重新跑．

最后结果 0.57，过 simple baseline．