-
We need a common ground to compare LSTM with BioWordVec embeddings and Arnold's strategy with character trigrams. Either:
- LSTM with character trigrams (#110)
- Arnold's strategy with BioWordVec …
-
Hello,
Guys, this looks like an amazing work! I want to use this library for my on-going research project in which I need to "test" a BLSTM on android device. I've a trained BLSTM model and I need to…
-
This program is amazing!
I am reproducing the stocks-blstm.ipynb example - as a beginner I would be interested to train and test a model with data up to now and then make predictions directly after…
-
Would it be possible for you to provide a pre-trained model? Additionally, does the model support real-time streaming inference?
-
Hi! I've been using the library for a few days now, particularly the deep learning API and I'm very impressed by its ease of use, documentation and performance.
However I couldn't find support for BLS…
-
Should the "nnet-train-blstm-streams" be included as a train-tool in local/run_blstm.sh ? Because we face error with nnet-train-lstm-streams tool
-
@eragonruan hi
有个疑问就是，得到VGG16的卷基层（Conv5）后，是怎么把数据丢入到BLSTM的？
TensorFlow的实现，对这个Conv5又做了一次卷积，
而论文coffee版本实现，只用了img2col+Transpose, 这是我不能理解的。
根据我对论文的理解，是直接从Conv5截取大小为3x3xC(这里C是512)的数据 然后再做img2col+Transp…
-
We implement the BLSTM layer for caffe. We realise that incorporating BLSTM layer in models for activity recognition can improve the accuracy rate. So we want to share the code in caffe. Does this hel…
-
The line 6 has to be changed from `from blstm_sw import BLSTM` to `from blstm_sw import BLSTM`. It is just a simple import error.
-
你好，请问直接densnet连接ctc和加上lstm再连ctc哪个效果会比较好，作者有试过吗？
如果想加lstm的话，训练代码需要做什么改变吗