bentrevett/pytorch-seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Jupyter NotebookMIT
Issues
- 0
Incorrect German Translation
#206 opened by timothy-geiger - 6
Tutorial 3: failed to run in google colab
#159 opened by YiyiAm - 0
RuntimeError: Expected hidden[0] size (2, 1, 512), got [2, 128, 512] - Seq2Seq Model with PreTrained BERT Model
#162 opened by Ninja16180 - 0
how to use BPTTIterator for Language Modeling
#163 opened by StephennFernandes - 1
Adding layers to the encoder and decoder of seq2seq
#154 opened by dopu2k16 - 0
Blank Outputs
#155 opened by abdullahkhilji - 1
- 2
- 2
Why the batch size is misplaced in the tensor?
#153 opened by abdullahkhilji - 0
How to change seq2seq to graph2seq
#203 opened by nhjclxc - 0
Seq2seq: Input not matching Output (and big thanks)
#202 opened by s2458588 - 2
no module named 'torchtext.legacy'
#198 opened by Hzzhang-nlp - 0
import
#199 opened by bouchalhakim - 0
- 3
Why using tanh function
#194 opened by karimmahalian - 0
How do you make this work on android?
#196 opened by Lambdacreator - 2
Notebook 1 <eos> problem.
#197 opened by yusufsali61 - 0
Tutorial 6: [Attention is All You need] Different output at different batch size during Inference
#189 opened by rajeevbaalwan - 0
- 0
Using pretrained BERT embedding
#192 opened by dhurba-baral - 0
- 4
- 0
Question about how to resolve the out of vocabulary problem during encoding and decoding in tutorial 1
#186 opened by liaomuquan - 0
Possible Inaccuracies in training script
#187 opened by rrmina - 1
Thank you!
#181 opened by asigalov61 - 3
- 6
Custom Text Dataset
#183 opened by moodhiaj - 1
using CTC loss instead of Cross Entropy loss:
#177 opened by kerolos - 1
spacy load not loading
#179 opened by neqkir - 0
Custom dataset: using Tabular dataset
#172 opened by CrispenGari - 1
Question about tutorial 1 and 2 Decoder
#168 opened by djaekim - 3
- 3
Tutorial 6: Attention is all you need
#170 opened by Hannibal046 - 3
Suggest ask the users (whoever is using this tutorial) to update their spaCy to 3.0 as 2.0 is suddenly very slow today
#165 opened by cestwc - 3
- 0
why this
#178 opened by zhiqiangohuo - 2
[Bug] Tranformer Seq2Seq Have Wrong Inputs!
#182 opened by bot66 - 1
Tut 6: TypeError with calculate_bleu_alt
#175 opened by yuvaraj91 - 0
Tutorial 6: Regarding attention plots
#176 opened by yuvaraj91 - 7
Tutorial 4 : AssertionError during the trainning
#173 opened by WendkuuniArzouma - 0
How easy can those models be converted into production TorchScript (PyTorch model inference pipeline)
#174 opened by kerolos - 1
Tutorial 4: Why not set the padding_idx of nn.Embedding's to src_pad_token_idx or tgt_pad_token_idx respectively?
#167 opened by yipliu - 3
Tutorial 3: The input of Attention
#149 opened by yipliu - 1
Tutorial 6: Question to CrossEntropyLoss
#166 opened by bpaulwitz - 4
Lesson 1, decoder to linear batch position
#164 opened by marcpaga - 2
- 4
Conversational Model Created Using Pre-Trained BERT Model is Throwing Error During Training
#160 opened by Ninja16180 - 3
Tutorial 4: RuntimeError: 'lengths' argument should be a 1D CPU int64 tensor, but got 1D cuda:0 Long tensor
#156 opened by STRZGR - 3
Tutorial 1: understanding LSTM
#151 opened by harshraj22 - 0
Tutorial 6: Multihead Attention
#152 opened by hartrials