Comments (5)
This is possibly due to using shape
instead of batch_shape
as this layer still cannot work with unknown batch sizes. Try setting a batch size in your layers and see if that fixes the issue. I will be working on how to get it to run with unknown batch sizes, but haven't had time to look into it yet.
from attention_keras.
The commit ae4b7ce should fix this issue. Please see if it works now.
from attention_keras.
Thank you. Actually I have already implement the attention mechanism according to some figures in your blog.
from attention_keras.
Thank you. Actually I have already implement the attention mechanism according to some figures in your blog.
attention = dot([decoder_lstm, encoder_lstm], axes=[2, 2])
attention = Activation('softmax')(attention)
context = dot([attention, encoder_lstm_], axes=[2,1])
decoder_combined_context = concatenate([context, decoder_lstm])
output = dense1(decoder_combined_context)
output = dense2(Dropout(0.5)(output))
model = Model([input_question, input_answer], output)
from attention_keras.
Sounds good :)
from attention_keras.
Related Issues (20)
- None Input Shape HOT 3
- Installation failed HOT 1
- TypeError: The added layer must be an instance of class Layer. HOT 2
- AttributeError: 'tuple' object has no attribute '_keras_mask' HOT 1
- AttentionLayer does not support model.save() and load_model() HOT 2
- The vocab size definition for English and French Tokenizers is incorrect HOT 1
- AttributeError: 'tuple' object has no attribute 'layer' HOT 3
- state HOT 1
- Failed to convert object of type HOT 3
- Minor issues - but nothing's broken HOT 12
- TypeError: object of type 'Concatenate' has no len() HOT 3
- Bahdanau attention HOT 2
- Help Required
- Very important!!!! HOT 2
- Support for using None in sequence length HOT 3
- Masking Support
- I got this error: 'tuple' object has no attribute '_keras_shape' any help please?
- ValueError: The first argument to `Layer.call` must always be passed. HOT 1
- Getting "TypeError: Exception encountered when calling layer "tf.keras.backend.rnn" (type TFOpLambda)" when I employ the Attention Layer HOT 11
- "tf.keras.backend.rnn"
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from attention_keras.