Can you please update it for pytorch 0.3.0 as pytorch 0.2.0 is long gone and runs very

There are problems with pytorch 0.4 and cuda. <div class="snippet-clipboard-conten

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

is there a way to port it to 0.3.0? about torchnlp HOT 3 CLOSED

kolloldas commented on June 7, 2024

is there a way to port it to 0.3.0?

from torchnlp.

Comments (3)

kolloldas commented on June 7, 2024

Sorry missed this. Are you having trouble running it on PyTorch 0.3.0? Seems to work fine on my system. The minimum required version is 0.2.0 but should run fine on the latest version. I'll check on 0.4.0 and update this thread.

from torchnlp.

djstrong commented on June 7, 2024

There are problems with pytorch 0.4 and cuda.

_________________________________________________________________________________________ test_softmax_output_layer _________________________________________________________________________________________

    def test_softmax_output_layer():
        hidden = Variable(torch.randn(2, 3, 4))
        labels = Variable(torch.ones(2, 3).long())
        softmax = SoftmaxOutputLayer(4, 8)
        loss = softmax.loss(hidden, labels)
>       assert loss.shape[0] == 1
E       IndexError: tuple index out of range

../../../../../../repos/torchnlp/tests/modules/test_outputs.py:12: IndexError
___________________________________________________________________________________________ test_crf_output_layer ___________________________________________________________________________________________

    def test_crf_output_layer():
        hidden = Variable(torch.randn(2, 3, 4))
        labels = Variable(torch.ones(2, 3).long())
        crf = CRFOutputLayer(4, 8)
        loss = crf.loss(hidden, labels)
>       assert loss.shape[0] == 1
E       IndexError: tuple index out of range

../../../../../../repos/torchnlp/tests/modules/test_outputs.py:21: IndexError

from torchnlp.

kolloldas commented on June 7, 2024

@djstrong Thanks for pointing that out! I have just migrated the library to use Pytorch 0.4.0. All tests are passing now and I was able to train the CoNLL2000 dataset on a GPU without issues. Please give it a try and let me know if you still find problems.

from torchnlp.

Related Issues (15)

Recommend Projects