-
## textsum
When I re-config textsum module (seq2seq_attention.py) to run with several servers, memory in chief computer exceed 12GB (8GB RAM + 4GB SWAP).
The main change like:
```
if FLAGS.job_nam…
-
## Please let us know which model this issue is about (specify the top-level directory)
# textsum#
when decode mode and set --beam_size=1, happen "ValueError: Cannot feed value of shape (512, 0) for …
-
This is about the textsum model.
I ran the model in train mode with about 80k articles (vocabulary ~40k) but after about a week still no training loss had been reported and no files have been writt…
-
I want to use the textsum model for tagging named entities. Hence the target size vocab is very small. While training there doesn't seem to be an option to provide different vocabs on the encoder an…
-
## Please let us know which model this issue is about (specify the top-level directory)
`textsum`
I get this error while doing the training
``` shell
Exception in thread Thread-152:
Traceback (most…
-
Can you please guide what went wrong? Also Can I run this only with CPU or is the following GPU capable of the textsum computations? It wasn't working for Caffe because it has --mode=train \
> --…
-
Sorry, this is not an issue but I would need to know what is the miminum RAM requirement for GPUs to be able to handle textsum computation? One of my GPUs listed below was not able to handle Caffe bec…
-
Hi guys,
I tried to play toy example of textsum.
I trained with toy dataset.
When I try to test as following,
following memory bug was occured.
have any idea?
there was no problem when I tried wit…
-
I would first like to know if anyone has successfully been able to run the textsum model recently against their own dataset. I seem to be hitting wall after wall, and after a week of training I get d…
-
# Textsum preprocess data
Could please tell me how to preprocess the DUC data to the required data format?
As the paper "Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond" men…