EmbeddingSimilarityTransformer using too much GPU memory

[pseudotensor]

Can lead to:

self.doc_embedding = DocumentPoolEmbeddings([self.embedding])
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/flair/embeddings.py", line 1532, in __init__
    self.to(flair.device)
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 386, in to
    return self._apply(convert)
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
    module._apply(fn)
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
    module._apply(fn)
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
    module._apply(fn)
  [Previous line repeated 1 more times]
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 199, in _apply
    param.data = fn(param.data)
  File "/home/jon/h2oai/tmp/contrib5/env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 384, in convert
    return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
RuntimeError: CUDA out of memory. Tried to allocate 90.00 MiB (GPU 0; 7.76 GiB total capacity; 837.44 MiB already allocated; 65.50 MiB free; 84.56 MiB cached)

[pseudotensor]

pytorch/pytorch#18626