Issues
- 2
- 0
About section
#197 opened by faizannazir - 1
Teacher forcing per timestep?
#195 opened by Aligholami - 8
Error for cuda and cpu
#185 opened by lucasjinreal - 6
Backtracking in beam search
#151 opened by shubhamagarwal92 - 2
NLL & Perplexity Loss
#144 opened by lethienhoa - 8
Attention type
#165 opened by ratis86 - 0
Out of memory for NLLLoss even the batch size is small
#194 opened by serenayj - 6
TopKDecoder
#177 opened by Hongzl1996 - 0
The dimension of predicted_softmax in DecoderRNN.py
#193 opened by tk1363704 - 0
Teacher forcing during beam decoding
#192 opened by iamsimha - 1
pre-trained word embedding
#187 opened by TianlinZhang668 - 0
- 2
Memory leak
#183 opened by amjltc295 - 10
Copy attention based decoder
#153 opened by AtmaHou - 4
GPU error when run sample code
#180 opened by vachelch - 2
RuntimeError when running Samplescript without attention in the develop branch
#181 opened by amjltc295 - 2
Decode function in decoder
#179 opened by ihungalexhsu - 1
Main advantages of develop branch?
#175 opened by me2beats - 2
Dev branch: toy training stops after 2 epochs
#174 opened by me2beats - 5
Cuda.LongTensor instead of LongTensor on GPU
#156 opened by ShilinHe - 0
beam search
#176 opened by asmartsnail - 3
Dropout error using external embeddings
#171 opened by rrkarim - 1
How is the memory optimized when using pre-trained embeddings like FastText and etc?
#170 opened by rrkarim - 1
RuntimeError occurs running integration_test.py
#169 opened by jhyun0919 - 2
- 0
How to train models with GPU?
#164 opened by Runingtime - 2
Hi! When I use examples.py for lannguage translation, an error occured in def len_filter if I use all train_datasets. But when I use part of train_datasets, it works well. Could you please tell me why?
#162 opened by Decalogue - 5
- 1
Multi-GPU Support
#145 opened by calperk - 2
Bug with get the embedding from pre-trained model
#147 opened by enferas - 1
UserWarning: volatile was removed
#149 opened by amrsharaf - 7
Scheduled Sampling
#152 opened by umgupta - 2
- 4
Masked attention
#141 opened by lethienhoa - 0
Incorrect Version Requirement
#140 opened by JakeStevens - 1
some question about embedding matrix in v0.1.4
#155 opened by reeuq - 1
Integration test fails on GPU
#160 opened by pskrunner14 - 1
can I use pytorch-seq2seq implement this model
#157 opened by gaikin - 1
What rnn.output_size is referring to exactly?
#158 opened by katyakuda - 0
some question about embedding matrix in v0.1.4
#154 opened by reeuq - 0
A question about predict
#148 opened by Glilei - 0
Dimension Error with LSTM
#146 opened by zeyofu - 2
Use pretrained embeddings
#132 opened by femoiseev - 0
most of the testunit in tests package can't pass
#143 opened by gameking157 - 0
run test_topkdecoder.py error
#142 opened by gameking157 - 2
sample.py doesnt seem to run with torch 0.4
#136 opened by yucongo - 0
Update to pytorch 0.4
#133 opened by kylegao91 - 1
Questioning the teacher forcing implementation
#129 opened by erogol - 0