Issue regarding pickling a convolutional neural network

[ramyabandaru]

I have modified "convolutional_mlp.py" file so that I can pickle the cnn class's object which will further help me to predict the classes of image using the saved model.But I am getting an error while doing so in the line-377 where I am actually calling the pickle.dump() method.
I am attaching the code for the file and the screenshot of the error.I guess the error is due to pickling the instance methods of logistic_sgd(though I am not sure about it)

self.layer3 = LogisticRegression(input=self.layer2.output, n_in=500, n_out=10)
self.negative_log_likelihood = (
self.layer3.negative_log_likelihood
)
#predicting the calss value and calculating errors
self.predict=self.layer3.y_pred
self.errors = self.layer3.errors
# the cost we minimize during training is the NLL of the model
#self.cost = self.layer3.negative_log_likelihood(y)
# create a list of all model parameters to be fit by gradient descent
self.params = self.layer3.params + self.layer2.params + self.layer1.params + self.layer0.params
self.input = input

covolutional.txt

[nouiz]

Can you confirm that you use Theano 0.8? If not, update to it.

On Mon, Mar 28, 2016 at 1:36 PM, Ramya Bandaru notifications@github.com
wrote:

I have modified "convolutional_mlp.py" file so that I can pickle the cnn
class's object which will further help me to predict the classes of image
using the saved model.But I am getting an error while doing so in the
line-377 where I am actually calling the pickle.dump() method.
I am attaching the code for the file and the screenshot of the error.
covolutional.txt
https://github.com/lisa-lab/DeepLearningTutorials/files/192184/covolutional.txt
[image: capture]
https://cloud.githubusercontent.com/assets/8428862/14084693/9ccc5256-f539-11e5-84f0-347787a4e038.PNG

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub
#151

[ramyabandaru]

I have updated the version to 0.8 but it still prompts the same error(The CNN I was trying to build above is for CIFAR-10 dataset)

[ramyabandaru]

Hi @nouiz
I have made certain changes in my code and it is executing without any error but while I am trying to load the pickled model to predict the class labels I am getting some error and I am unable to figure it out. I am attaching the screenshot of error and the modified file.
Thanks.
covolutional.txt
predict.txt

[nouiz]

In the DLT we hardcode that batch size to make the code easier to understand. But this ask you to respect it. Use the same batch size or update the original code to not hard code the batch size.

[ramyabandaru]

I am sorry but I didnot understand what you meant @nouiz ! what is the batchsize that i have to use now?

[nouiz]

If you don't understand what I mean by batch size, I would recommand that
you read all the tutorials before the convolution one. To know the size of
the batch size to use, I would suggest you to read the code. It is written
explicitly. If you want to understand well what is being done, reading and
understanding the code is useful. See this as a small exercice :)

On Thu, Mar 31, 2016 at 9:57 AM, Ramya Bandaru notifications@github.com
wrote:

I am sorry but I didnot understand what you meant @nouiz
https://github.com/nouiz ! what is the batchsize that i have to use now?

—
You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#151 (comment)

[ramyabandaru]

Thanks for your suggestion :) but i do understand what a batchsize is . But I was unable to figureout the problem with it.