atulkum pointer_summarizer issues

atulkum / pointer_summarizer

pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"

Apache License 2.0

904 stars 243 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Duplicated computation with LSTM?

#63 zhujiangang opened 3 years ago
0
How to choose the best training model

#62 Sixy1204 opened 3 years ago
0
Retraining model cause optimizer duplicate parameter error

#61 Sixy1204 closed 3 years ago
3
Discrepancy with implementation and the paper

#60 AetherPrior opened 3 years ago
0
Can the code here be trained with multiple GPUs

#59 gaozhiguang closed 3 years ago
1
What is the specific implementation of pointer network

#58 gaozhiguang closed 3 years ago
1
'Encoder' object has no attribute 'tx_proj'

#57 jivatneet opened 3 years ago
3
How to train with Coverage?

#56 XuemingQiu closed 3 years ago
1
how to use valid dataset to select a bestmodel to test?

#55 XuemingQiu closed 3 years ago
1
when i train it with coverage ,the loss is nan when i get 250k iter?

#54 XuemingQiu closed 3 years ago
1
eval.py decode.py

#53 superxaiole closed 3 years ago
2
question about eval

#52 superxaiole closed 3 years ago
1
what's function of the eval.py when i check the train.py ,it does't call the eval.py , save the model directly?

#51 XuemingQiu closed 3 years ago
1
Vector encode input extend vocab

#50 binhna closed 3 years ago
3
Fully automate dev setup with Gitpod

#49 WONIO opened 4 years ago
0
Training saturates early?

#48 ajoshi80 opened 4 years ago
3
Test time custom decoding!!

#47 rajeshsahu09 opened 4 years ago
0
What is the version of tensorflow？

#46 niuweicai closed 4 years ago
1
url correction

#45 TalSchuster closed 4 years ago
1
During the training and verification process, when "step = 0", the "coverage" is initialized differently. During training, the coverage is an all-zero tensor, but this is not the case during prediction.

#44 997261095 closed 4 years ago
1
Python3 support?

#43 johntiger1 closed 4 years ago
13
How to train the model from last checkpoint saved

#42 rajeshsahu09 closed 4 years ago
2
Illegal division by zero at /My-path-to-RELEASE-1.5.5/ROUGE-1.5.5.pl line 2450.

#41 Lanme opened 4 years ago
1
how to predict single line after training

#40 Lanme opened 4 years ago
3
When training around 8400 iters, got loss=nan

#39 buptorange closed 4 years ago
1
Decode custom texts with a pretrained model

#38 timoderbeste opened 5 years ago
0
Single word is repeated in entire summary while coverage is enable

#37 shubham3195 opened 5 years ago
1
Out of Memory error when trying to load the model

#36 Shashi456 opened 5 years ago
0
pre-trained word embedding

#35 TianlinZhang668 opened 5 years ago
1
Training time

#34 f550c opened 5 years ago
3
Adam optimiser starts giving NaN after few epochs after turning on coverage.

#33 karansaxena closed 5 years ago
5
Why is the model outputting UNK tokens? Shouldn't it be able to point to unkown words from the input?

#32 Rhuax opened 5 years ago
3
how to use the 'model_transformer'?

#31 zh215021 opened 5 years ago
1
Meaning of "iterations" in readme

#30 Rhuax closed 5 years ago
2
Ask about loading data

#29 realjoenguyen closed 5 years ago
2
pointer generator model starts overfitting

#28 priyanks179 closed 5 years ago
6
The low rouge scole

#27 jiangix01 opened 5 years ago
3
beam search log prob

#26 seanie12 closed 5 years ago
2
RAM issue

#25 karansaxena closed 5 years ago
0
transformer_pointer

#24 JoyeeL opened 5 years ago
0
Can I modify the "num_layers" parameter?

#23 lzw-pku closed 5 years ago
1
transfomer_model

#22 dajuzi123 closed 5 years ago
3
run the train

#21 BigwhiteRookie closed 4 years ago
4
What does the variable (training) mean?

#20 qlwang25 closed 5 years ago
1
what is '$MODEL' in 'start_decode.sh'?

#19 NinaTian98369 closed 5 years ago
2
Need help for retraining and cross validation

#18 atulkum opened 5 years ago
12
setup conda env

#17 yichern closed 5 years ago
0
why using 2*hidden_dim x 2*hidden_dim linear layer in encoder?

#16 ziliwang closed 5 years ago
0
TypeError: __init__() got an unexpected keyword argument 'initial_accumulator_value'

#15 pengzhi123 closed 5 years ago
2
Training on prefixes

#14 manishmotwani3 closed 5 years ago
1