Comments (4)
Hi, can you provide details on which code you ran? Was it the examples/addition_rnn.py
script or the example code in the Readme? Did you run it on master
or another branch?
I hope, we can find the problem.
from indrnn.
I think it's something related with tf.variable_scope. When I run the addition_rnn.py script directly using python everything is OK, but if I copy the code into my Jupyter Notebook and run the bug happened. I have fixed the bug by adding:
with tf.variable_scope("indrnn", reuse=None):
in front of
output, state = tf.nn.dynamic_rnn(cell, inputs_ph, dtype=tf.float32)
and make all the rest code within that with loop, then it started running.
from indrnn.
The error usually occurs, when you run
output, state = tf.nn.dynamic_rnn(cell, inputs_ph, dtype=tf.float32)
twice. Then, it will create the variables again in the second call and complain that they already exist. It might be that you ran the cell Jupyter Notebook twice, so all the variables were already initialized. I have not used TensorFlow in Jupyter yet, but restarting the notebook would probably help in such cases. Apart from that you can also use the reuse
parameter of a variable scope, as you mentioned above.
from indrnn.
Cool!
Tanks again!
from indrnn.
Related Issues (16)
- Constrain (0, max) instead of (-max, max)? HOT 6
- Result of Sequential MNIST HOT 14
- AttributeError: module 'tensorflow.python.ops.rnn_cell_impl' has no attribute '_LayerRNNCell' HOT 1
- Please release the code of action recognition HOT 2
- Cell structure HOT 3
- Errors when used in bidirectional_dynamic_rnn HOT 2
- ReLU activation with IndyLSTMCell HOT 5
- Would you like to contribute this cell to TF's tf.contrib.rnn? HOT 2
- how to reimplement the action recognition experiment of the original paper HOT 2
- How to add dropout to indrnn cells HOT 2
- Dimension Mismatch ?
- Performance issue in the definition of build_rnn, examples/sequential_mnist.py HOT 1
- Performance issues in the program HOT 2
- Probably wrong indexing HOT 2
- Initialization of recurrent weight for the adding problem or similar problems HOT 14
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 indrnn.