-
The HAN paper considers only words that appears more than 5 times. I don't think it is implemented in the code. Also, does stop word removal take place in the paper? As I mentioned if stop words are r…
-
Thanks for your great job.I rewrite you program to make it run with tensorflow1.12 and python 3. I only use 2BLSTM not 4.At the begining of train stage ,the train loss is 3000k, after 66k steps ,the t…
-
You mentioned in your readme file that you achieved better accuracy with BILSTM attention instead of HAN. **What did you mean by BILSTM attention?** I want to know the architecture. Are you referring …
-
Many thanks for the the specAugment implementation.
The base2.conv2l.specaug.curric3 [here](https://github.com/rwth-i6/returnn-experiments/tree/master/2019-librispeech-system/attention), is my un…
-
[1D CNN with BLSTM for automated classification of fixations, saccades, and smooth pursuits](https://sci-hub.tw/https://link.springer.com/article/10.3758/s13428-018-1144-2)
Their [website](http://w…
-
## 🐛 Bug
Python's garbage collection invokes every 700 object creations (by default), so there should be a situation when the object is not referred but still occupies the CUDA memory (when referen…
-
@jpuigcerver Thanks for your answer. Actually, I build your model using pytorch and I try to extract the weights form your lua pretrained model and transfer them to my pytorch model. I do the convolut…
-
Epoch 1/20
2019-07-19 10:34:06.768267: I tensorflow/stream_executor/dso_loader.cc:152] successfully opened CUDA library libcublas.so.10.0 locally
2019-07-19 10:34:07.669769: E tensorflow/stream_exec…
-
Hi, I borrowed your functions, as below, for training CoNLL_2003 data only.
when CRF=True, result is ~ 95% for F1,
but when I changed to CRF=False, the accuracy reduced to almost 0, wondering if I …
-
@ngimel I have a *.t7 model that consists in few convolution layers and 1 block of cudnn.BLSTM(). To convert the model to pytorch, I create the same architecture with pytorch and try to get the weigh…