bi-att-flow
bi-att-flow copied to clipboard
allenai
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to ach...
Hi! Which of the Glove pre-trained weights were used to train the model in "out/basic/00/save/basic-18000"? This is the model loaded when running the demo. Is it 6B, 42B, or 840...
Hello all, As I was going through the instructions, I found a very minor typo in the README and have fixed it. Hope it helps!
- Updated the demo branch so it's now a standalone module. It accepts new text and outputs answers and soft-maxed logits (confidence). - Added an inference module to predict answers...
Just curious, why use `BasicLSTMCell` instead of other "faster" LSTM cell in TF like: tf.contrib.rnn.LSTMBlockCell` or `tf.contrib.rnn.LSTMBlockFusedCell` ? I am not really a machine learning expert, just thought why not...
I've gone through the demo branch tutorial, but when running `python run-demo.py` after training and testing there is an error message: `python: can't open file 'run-demo.py': [Errno 2] No such...
A weird situation using dev branch on tensorflow1.2 I use command below train **python -m basic.cli --mode train --noload --len_opt --cluster** and this command to test **python -m basic.cli --len_opt...
Dear Team, I am running training with 2 K80 Nvidia GPUs. I tried both dev branch with tf 1.2.0, python 3.6.2 with the following line: python3 -m basic.cli --mode train...
ubuntu 16.04, python3.5, cuda9.0, cudnn7.0 nccl2, follow the installation and all is fine. python3 -m basic.cli --mode train --noload --debug fails..first on _linear solution per issue 41 from tensorflow.contrib.rnn.python.ops.rnn_cell import...
I followed the exact instructions in the 'readme.md' file and started training my model with the following command: ` python -m basic.cli --mode train --noload --len_opt --cluster --batch_size 50` After...
