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.

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

Generating Handwritten Digits on MNIST using GANs #161

Closed
wants to merge 7 commits into from

Conversation

swaingotnochill
Copy link
Contributor

This PR is for discussing the issues and working on GANs notebook for MNIST dataset.

@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@swaingotnochill
Copy link
Contributor Author

swaingotnochill commented Jun 30, 2021

@zoq @kartikdutt18 When I am adding convulation layer, it seems to give an error that

/home/viole/anaconda3/envs/notebook/include/mlpack/methods/ann/ffn.hpp:290:36: error: no member named 'push_back'

Is it due to syntax error while using the modules or something else? I tried working around it, but don't know why its giving push_back not found(this function should be available).

your thoughts?

@@ -0,0 +1,404 @@
{
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

model.Add(new mlpack::ann::Convolution<>(,6,5,5,1,1,0,0,28,28))

Could you try this?


Reply via ReviewNB

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I tried but it doesn't seems to work too.
input_line_65:2:16: error: no matching constructor for initialization of 'mlpack::ann::Convolution<>' model.Add(new mlpack::ann::Convolution<>(1,6,5,5,1,1,0,0,28,28)); ^ ~~~~~~~~~~~~~~~~~~~~~ /home/viole/anaconda3/envs/notebook/include/mlpack/methods/ann/layer/layer_types.hpp:172:7: note: candidate constructor (the implicit copy constructor) not viable: requires 1 argument, but 10 were provided class Convolution; ^ /home/viole/anaconda3/envs/notebook/include/mlpack/methods/ann/layer/layer_types.hpp:172:7: note: candidate constructor (the implicit move constructor) not viable: requires 1 argument, but 10 were provided

No matching constructor..

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I just tested it on lab.mlpack.org and there it works fine, I had some problems with namespaces in the past, can you put each namespace into a separate cell?

Copy link
Member

@zoq zoq left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For an example about how to save/load a model you can checkout https://github.com/mlpack/examples/blob/master/mnist_simple/mnist_simple.cpp, the interesting part is:

https://github.com/mlpack/examples/blob/master/mnist_simple/mnist_simple.cpp#L170

and

mlpack::data::Load("../data/mnist_test.csv", dataset, true);

Let me know if I should clarify anything further.

@kartikdutt18
Copy link
Member

Hi Swain, Could you push the latest changes (if you have got the issue resolved).

@swaingotnochill
Copy link
Contributor Author

Hi Swain, Could you push the latest changes (if you have got the issue resolved).

Sure...I will push it by Tonight (I don't have the computer right now )

@swaingotnochill
Copy link
Contributor Author

I redirected the PR at #172 . Closing this one.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants