Comments (3)
The new variable_scope is created when entering the method (it is buried in
the registration code, which is quite hairy to read).
The general way to share variables is to do the following pattern:
with tf.variable_scope('my_scope') as vs:
build_model()
with tf.variable_scope(vs, reuse=True): # could also enter 'my_scope'
build_model()
You can do this with any sub-part as well. If you want to share variables
across different layer types, you can supply the same name to the layer or
do something like the following:
Getting the shapes to line up is tricky, but possible.
x = single_patch.fully_connected(...)
y = full_image.conv2d(..., init = x.layer_parameters['weight'],
bias_init=x.layer_parameters['bias'])
On Sat, Apr 2, 2016 at 7:23 AM, Rasmus [email protected] wrote:
How do I not create create a scope for new variables? I've looked into the
code, but I simply cannot see how .variable() creates a new scope for the
variable.
This is undesired behavior for me, since I want to use the current scope
that I assigned with tf.variable_scope() to share some variables.—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub
#18
from prettytensor.
I see, I am indeed sharing variables across different layer types - namely conv2d and deconv2d (which is a custom layer). Does initializing in that way actually share the variables though? It seems to me that once x_layer parameters are updated, y_layer won't be.
from prettytensor.
Yes it does. Under the hood it is just reusing the variables and the gradients are computed correctly.
from prettytensor.
Related Issues (20)
- How to do regularization? HOT 3
- AttributeError: type object 'GraphKeys' has no attribute 'GLOBAL_VARIABLES' HOT 3
- AttributeError: module 'tensorflow' has no attribute 'complex_abs' HOT 3
- TypeError: Expected int32, got <prettytensor.pretty_tensor_class.Layer > of type 'Layer' instead. HOT 16
- weights reuse in {gru, lstm}_cell/_sequence methods HOT 2
- Bug with template, phase=Unbound and batch_normalize=True
- loading from checkpoint
- conv2d 'kernel'
- run baby_names.py error HOT 1
- PrettyTensor's template.construct() yielding ValueError HOT 2
- TypeError: slice indices must be integers or None or have an __index__ method
- using tensorboard with prettytensor
- manipulating output layer of tensorflow during learning
- how to use the dropout and l2loss ?
- Prettytensor not working with TF1.8 HOT 4
- With Tensorflow 0.12, it is throwing "TypeError: zeros_initializer() takes at least 1 argument (0 given)".
- How can i use inspect_checkpoint tool to print all the weight ?
- AttributeError: 'VariableScope' object has no attribute 'current_scope HOT 2
- AttributeError: module 'tensorflow' has no attribute 'GraphKeys'. In python while importing tflearn. HOT 2
- c++
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 prettytensor.