Issues
- 0
- 10
- 1
- 0
- 4
Anyone please share their model ?
#77 opened by kenkit - 2
Train with error
#79 opened by wilddylan - 2
vocab.t7 not found
#72 opened by Achilles-96 - 3
- 32
Is there any pre-trained model?
#59 opened by GZJackCai - 0
Initialising pre-trained model
#78 opened by bienbinod - 1
online learning for the model
#69 opened by kenyeung128 - 1
- 38
- 8
Multiple GPU support
#26 opened by vikram-gupta - 5
the result is not like what u said
#58 opened by csrgxtu - 3
The memory usage skyrocket each time it saves
#70 opened by ljyloo - 7
- 1
[Discuss:] how to improve the performance?
#71 opened by SeekPoint - 1
- 1
- 2
The lines are shortened to the first sentence
#68 opened by kenyeung128 - 0
PANIC: unprotected error in call to Lua API (not enough memory)----but 'top' show the memory are still avaialbe
#66 opened by SeekPoint - 0
Perplexity calculation
#67 opened by BranaHi - 0
- 3
reversing the input sequence
#54 opened by nabihach - 0
- 0
attempt to call method 'topk' (a nil value)
#61 opened by sivagnanamn - 0
Unable to convert argument 3 from cdata
#60 opened by tebdrepo - 0
model:getParameters() used multiple times
#57 opened by nabihach - 0
Interpretation of 'decoderInputs' in dataset.lua
#56 opened by nabihach - 2
Resume training from a saved model
#55 opened by nabihach - 4
Train in another language
#50 opened by rmazitov - 4
Getting <unknown> as result
#53 opened by Vincent717 - 1
Using a different criterion while testing
#51 opened by nabihach - 10
opencl training fail
#30 opened by SolarPeng - 3
Using LR decay with Adam
#40 opened by vikram-gupta - 1
Word embeddings?
#46 opened by nabihach - 3
Problems with running the code
#45 opened by nabihach - 1
train.lua:169 cutorch.synchronize()
#44 opened by csrgxtu - 3
Maximum Vocabulary Size
#42 opened by vikram-gupta - 1
- 6
Multiple layers support
#34 opened by vikram-gupta - 1
No CUDA capable device is detected
#37 opened by VibhuSrivastava - 1
'dpnn' update problem
#36 opened by tsaiJN - 2
Why do we append all the previous tokens of the decoder to generate next token?
#39 opened by vikram-gupta - 3
Mini-batch learning
#27 opened by chenb67 - 2
- 1
SequencerCriterion.lua:42: expecting target table
#32 opened by kenkit - 2
- 1