nlp


Topic Replies Activity
Char RNN Not Outputting EOS Tokens 2 July 2, 2019
How to use nn.TransformerDecoder() at inference time 1 July 2, 2019
Embeddings shows index out of range if `padding_id` is -1 5 July 2, 2019
Any idea on how to slice an (N,D) tensor with minibatches? 2 July 1, 2019
Symmetric Relu stle activation function 1 June 28, 2019
Using Dataset to iterate over lines of large files 3 June 27, 2019
K-fold cross validation 1 June 26, 2019
When I try to rebuild a Transformer model, got 'Expected tensor for argument #1 'indices' to have scalar type Long, but got torch.IntTensor instead' 4 June 26, 2019
Issues after implementing minibatching 2 June 26, 2019
Convert caffe lstm to pytorch 1 June 25, 2019
Faster way to do multiple embeddings? 1 June 24, 2019
RuntimeError: Expected hidden[0] size (2, 20, 256), got (2, 50, 256) 11 June 21, 2019
Create a customised recurrent neural network 1 June 21, 2019
[solved] Expected tensor for argument #1 'indices' to have scalar type Long; but got CPUDoubleTensor instead (while checking arguments for embedding) 3 June 20, 2019
Using softmax causes out of memory error for CUDA 1 June 19, 2019
Simple RNN stuck around the mean 3 June 19, 2019
How to write resnet block for 1 dimensional data 1 June 19, 2019
Libtorch c++ tensor mismatch error 2 June 19, 2019
Pytorch model not utilizing all the cores of cpu 1 June 18, 2019
Error: Expected object of scalar type Long but got scalar type Float for argument #2 'mat2' 7 June 18, 2019
TF LayerNormalization vs PyTorch LayerNorm 1 June 18, 2019
Seq2seq for NMT why the decoder keeps predicting repeated tokens? 1 June 18, 2019
Efficient metrics evaluation in Training and Validation Loop 1 June 18, 2019
Loss is between 4 and 3'5 and never close to 0 2 June 17, 2019
Implement dataparallel on big vocab is much slower than single gpu 5 June 17, 2019
Accuracy is not calculated? 13 June 17, 2019
How to implement nested transformers: a character-level transformer for words and a word-level transformer for sentences? 1 June 14, 2019
Why isn't pad_packed_sequence sufficient ? Why do we need to pad by ourselves when we supply the sequence lengths? 2 June 14, 2019
How to change the output dimension of nn.Linear according to the batch data? 1 June 14, 2019
Masking operation on specific dimension 1 June 13, 2019