Snehal Patel

@JohnGiorgi Attaching the snippet from train folder.. train_text_03477.txt ``` Compared to the Motorola H500 , this is a wonderful piece of gear although it is much larger . I only...

 @JohnGiorgi I can see the annotations, and they looks correct! Also, I can run the scripts without any errors, it's just I...

I was actually going through all the scripts and trying to debug the issue here, it's just seems little complex given the structure of the repo. Will post the solution...

@JohnGiorgi Just if you want to see that output I am getting from running main.py with having everything in proper place! ``` Formatting train set from BRAT to CONLL... Done....

Train: 3477 files Test: 412 files Valid: 614 files All files are having average of 20 sentences in each. Everything is .txt and .ann format

Having a same error! Any solution? or am I missing something here? @yinghuaxuehai any update?? ``` NeuroNER version: 1.0-dev TensorFlow version: 1.3.0 {'character_embedding_dimension': 25, 'character_lstm_hidden_state_dimension': 25, 'check_for_digits_replaced_with_zeros': 1, 'check_for_lowercase': 1,...

@liormagen You got any update on this? I'm trying out same thing on 8 GPUs but looks like model is only using single GPU for transform() method! CC: @Newmu

Any update on visualization part? @ni9elf @richliao I'm trying to get the weights, but it always end up to `1.0` ``` > _dot = np.dot(out[0], att_w[0]) > _tanh = np.tanh(_dot)...

@deepankar27 the closest working solution I got is this: https://github.com/cbaziotis/neat-vision

@deepankar27 If your model has attention layer, you can easily get the output of that layer. With Keras, you can get it like this; [Obtain the output of an intermediate...