paraphrase-id-tensorflow

paraphrase-id-tensorflow copied to clipboard

Prediction stuck at 65%

1

I met this error when trying to run the code (only change Glove to 840B.300d but remain filename as 6B.300d) Does anybody know how to fix this? File "scripts/run_model/run_bimpm.py", line...

tamio96

Several questions about the code

4

Hi, I appreciate your sharing this project! It is a very thoughtful work and friendly to newers! I have some questions when reading the code. 1. In dataset.py Instead of...

p-null

RuntimeError: Unrecognized line format

2

Hi, i am running the biMPM model to predict, getting the following result: ``` Traceback (most recent call last): File "run_bimpm.py", line 267, in 66%|███████████████████████████████████████████████████████████████▊ | 2345735/3563475 [09:22

p-null

Add MultiGPU (Data Parallelism)

2

Looks like the train time is pretty long on AWS instances with K80s. Adding MultiGPU data parallelism would be a good way to mitigate this (as done in https://www.tensorflow.org/tutorials/using_gpu#using_multiple_gpus)

nelson-liu

remove the overrides , otherwise it reports error

5

Traceback (most recent call last): File "scripts/run_model/run_siamese_matching_bilstm.py", line 16, in from duplicate_questions.data.instances.sts_instance import STSInstance File "scripts/run_model/../../duplicate_questions/data/instances/sts_instance.py", line 13, in class STSInstance(TextInstance): File "scripts/run_model/../../duplicate_questions/data/instances/sts_instance.py", line 69, in STSInstance @overrides File "/home//f.local/lib/python3.6/site-packages/overrides/overrides.py",...

SeekPoint

in most cases, skip-gram works better than GLOVE and using skip-gram vectors can improve the performance. Also, there are much more open source libraries to work with skip-gram.

r-y-zadeh

This would make our model training a lot faster.

nelson-liu

right now, the data pipeline will tokenize the input into both words / characters, even if you only want words. This is fine for now since character tokenization isn't that...

nelson-liu

Right now, the model can "train" (training on train data / periodically measure validation accuracy / loss) and it can "predict" (given an unlabeled test set, make predictions). It would...

nelson-liu

SwitchableDropoutWrapper currently has to run the LSTM cell twice, one to get the dropped out inputs and one to get the un-dropped out inputs (and then use `tf.cond` to output...

nelson-liu