Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixed invalid link in model_pruning readme #25840

Merged
merged 4 commits into from
Apr 8, 2019
+2 −4
Merged

Fixed invalid link in model_pruning readme #25840

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
852c4ab
Fixed invalid link
cenh Feb 18, 2019
c3db955
Removed double dollar signs
cenh Feb 21, 2019
0e203eb
Reverted
cenh Feb 21, 2019
dd0a1b2
Updated based on request
cenh Apr 7, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
6 changes: 2 additions & 4 deletions tensorflow/contrib/model_pruning/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,7 @@ The pruning library allows for specification of the following hyper parameters:

The sparsity $$s_t$$ at global step $$t$$ is given by:

$$ s_{t}=s_{f}+\left(s_{i}-s_{f}\right)\left(1-\frac{t-t_{0}}{n\Delta t}\right)^{3} $$
$$s_{t}=s_{f}+\left(s_{i}-s_{f}\right)\left(1-\frac{t-t_{0}}{n\Delta t}\right)^{3}$$

The interval between sparsity_function_begin_step and sparsity_function_end_step
is divided into $$n$$ intervals of size equal to the pruning_frequency ($$\Delta
Expand Down Expand Up @@ -133,9 +133,7 @@ For now, it is assumed that the underlying hardware platform will provide mechan

## Example: Pruning and training deep CNNs on the cifar10 dataset <a name="example"></a>

Please see https://www.tensorflow.org/tutorials/deep_cnn for details on neural
network architecture, setting up inputs etc. The additional changes needed to
incorporate pruning are captured in the following:
Please see [Advanced Convolutional Neural Networks](https://www.tensorflow.org/tutorials/images/deep_cnn) for details on neural network architecture, setting up inputs etc. The additional changes needed to incorporate pruning are captured in the following:

* [cifar10_pruning.py](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/model_pruning/examples/cifar10/cifar10_pruning.py)
creates a deep CNN with the same architecture, but adds mask and threshold
Expand Down