bi-att-flow icon indicating copy to clipboard operation
bi-att-flow copied to clipboard

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...

Results 74 bi-att-flow issues
Sort by recently updated
recently updated
newest added

I'm trying to work with the branch dev-demo and following the exact same steps mentioned. Once I preprocess the data and run `python -m basic.cli --mode train --noload --debug` ,...

Hello, I am not able to find the `save.zip` file in the CodaLab worksheet. Is it removed from there? Any help in this regard would be great. Thanks in advance!...

Hi, How do you get results for dev_data in the readme.txt. It is mentioned the results was got with squad official evaluator. Do you need to change any code, or...

` Traceback (most recent call last): File "/home/u19872/.conda/envs/bert01/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1567, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 900 and 300 for 'model_0/prepro/prepro/fw/fw/while/basic_lstm_cell/MatMul_6' (op: 'MatMul') with...

When I run the code,I found that some parameters were missing. I added some parameters How appropriate is the default setting of parameters? flags.DEFINE_string("out_dir", "", "Shared path []") flags.DEFINE_string("save_dir", "",...

Hi , I am trying to train Bidaf on CNN data set but it fails. Here are the steps performed. - Downloaded the CNN dataset - Ran the cnn_dm.prepro script....

HI, I'm running the dev branch code on Tensorflow 1.2. And I got this error: Variable model_1/loss/ExponentialMovingAverage/ does not exist or was not created with tf.get_variable(). Did you mean to...

Excuse me, I got a TypeError:_linear() got an unexpected keyword argument 'bias_start' please help me ~

I am trying to get the repo working in TF1.7. I was able to get the training done with the help of dev branch for TF 1.4. But I failed...