Stack Overflow
Stack Overflow

Questions tagged [pruning]

Use pruning for questions related to algorithms used on data structures to facilitate generalization and performance optimization.

Pruning is a general technique to guard against the creation of an algorithm too specific to the training data so that it can be applied to other data sets.

References

193 questions
2
votes
0 answers

Can't use KerasSurgeon with Tensorflow 2.4.1 version

I'm using the library KerasSurgeon to prune a neural network. When I call the method delete_channels() I get the following error: TypeError Traceback (most recent call last) in…
Luk
  • 21
  • 1
2
votes
1 answer

Pytorch Global Pruning is not reducing the size of the model

I am trying to Prune my Deep Learning model via Global Pruning. The original UnPruned model is about 77.5 MB. However after pruning, when I am saving the model, the size of the model is the same as the original. Can anyone help me with this…
Whatsinthename
  • 21
  • 3
2
votes
1 answer

PostgreSQL doesn't prune partitions correctly if I replace a numeric literal in the where clause with a simple query that returns 1 row

fast query select ... from table1 t1 join table2 t2 on t2.org_id = t1.org_id where t1.org_id = 1 slow query select ... from table1 t1 join table2 t2 on t2.org_id = t1.org_id where t1.org_id = (select org_id from table3 where org_name = "abc" limit…
David Charles
  • 21
  • 1
2
votes
3 answers

Keras-surgeon: For pruning and Model optimization

I am working on a Convolutional Neural Net built using Keras. And since the final model needs to be deployed on a processing unit with less processing capabilities, I started looking for ways to reduce the resources it'd consume. Luckily, I came…
Waqas Kayani
  • 133
  • 2
  • 9
2
votes
1 answer

How do I prune over the highest weights in tensorflow layer? tfmot.sparsity.keras.prune_low_magnitude

I want to prune over the highest weight values in a tf layer. I'm thinking about using tf.nn.top_k but I'm not exactly sure how I would go about doing this. Documentation:…
iiooii
  • 551
  • 2
  • 9
  • 15
2
votes
0 answers

Is there any keras code to reproduce the weight pruning of MobileNet?

I want to prune the MobileNetV1 model using the weight pruning method from https://www.tensorflow.org/model_optimization/guide/pruning However, I don't know how to set the pruning_schedule. pruning_params = { 'pruning_schedule':…
bin.li
  • 61
  • 5
2
votes
1 answer

Minimax theory including alpha beta pruning for R code

Need help with developing an alpha beta pruning minimax algorithm in R. Currently I have implemented the minimax algorithm but it is only usable for 3x3 board. 4x4 boards do not run --> to long run time I have copied the code from the 3x3 board but…
Daan Berends
  • 21
  • 2
2
votes
1 answer

Pruning before running convex hull algorithm

I have to form a Convex Hull from large amount of points and I came across this article. Whole process of pruning is described and well explained, except for one part. I don't know what this part means and how to convert it to code: Since the space…
ZigaK
  • 21
  • 4
2
votes
2 answers

Finding removed elements in a vector in matlab

I have a process that is iteratively and randomly pruning a huge vector of integers and I want to find what elements are removed between each iteration. This vector has a lot of repetitions and using ismember() and setdiff() doesn't helped me much.…
Grasshoper
  • 457
  • 2
  • 13
2
votes
1 answer

SqueezeNet Deep Compression

Do you guys know where or how to obtain the 0.47MB version of SqueezeNet ? In other words, how to make the weights bitwidth to be 6 instead of 8 ? I cannot find the modification spot in this SqueezeNet generation code.
kevin998x
  • 899
  • 2
  • 10
  • 23
2
votes
1 answer

borg backup- how to keep weekly backups

I have a daily cronjob which backs up with borg backup like this: borg create -v --stats \ $REPOSITORY::'{now:%Y-%m-%d_%H:%M}' \ /root \ /etc \ /var/www …
mart
  • 354
  • 3
  • 14
2
votes
1 answer

How to save Tf.contrib model pruning?

I have built a model and I am successfully able to prune it using tf.contrib's model pruning module with default params and sparsity as 90%, but the problem is when I run the model it still takes the same amount of execution time as of the original…
Avinash Rai
  • 171
  • 6
2
votes
0 answers

Configure npm's package-lock.json to prevent pruning a specific module

So, at the risk of inciting knee jerk responses of "why would you ever want to do that?!?!"... Does anyone know of a config setting one could put into either package.json or the generated package-lock.json such that npm will ignore a given module…
Shin
  • 101
  • 5
2
votes
0 answers

Scikit-Learn Post pruning in RandomForestClassifier

Does the RandomForestClassifier() in scikit-learn support post-pruning? So there are parameters such as max_depth etc but they are more on the pre-pruning side. So is it possible to build out the tree as far as possible and then prune the tree after…
ml_enthusiast
  • 21
  • 2
2
votes
0 answers

Decision Tree with no pruning in R

I would like to build a decision tree with no pruning at all. As can be seen in this question using default rpart also prunes the decision tree. Does using the value for cp=-1 avoid pruning at all?
Avi
  • 2,247
  • 4
  • 30
  • 52
1 2 3
…
12 13