Model Saving #159

Activity

1. amit4111989 commented on Jun 3, 2016

   

   amit4111989

   on Jun 3, 2016

   More actions

   Use pickle or cpickle (Python modules for serializing objects ) to store the generated model
2. djsaunde commented on Jun 6, 2016

   

   djsaunde

   on Jun 6, 2016

   Author

   More actions

   This allows me to save the SdA object, but I would like to input vectors and retrieve their encoding, or "h(x)" in the literature, where "x" is the input.
3. amarczew commented on Sep 22, 2016

   

   amarczew

   on Sep 22, 2016

   Last edited by amarczew

   More actions

   You can try something like:

   def new_representation_X_train(hidden_layer):
       new_representation_train = theano.function(
            inputs = [index],
           outputs = self.sigmoid_layers[hidden_layer].output,
           givens = {
               self.x: train_set_x[index: index + 1 ]
           }
       )
       train_lines = train_set_x.get_value(borrow=True).shape[0]
       return [new_representation_train(i) for i in xrange(train_lines)]
   
4. ohuole233 commented on Sep 22, 2016

   

   ohuole233

   on Sep 22, 2016

   More actions

   Thanks for your help, another question is that what does [index] mean in your code?^-^

   At 2016-09-22 08:22:24, "Alison Marczewski" notifications@github.com wrote:

   You can try something like:

   def new_representation_X_train(hidden_layer):
   new_representation_train = theano.function(
   inputs = [index],
   outputs = self.sigmoid_layers[hidden_layer].output,
   givens = {
   self.x: train_set_x[
   index: index + 1
   ]
   }
   )
   train_lines = train_set_x.get_value(borrow=True).shape[0]
   return [new_representation_train(i) for i in xrange(train_lines)]

   —
   You are receiving this because you are subscribed to this thread.
   Reply to this email directly, view it on GitHub, or mute the thread.
5. ohuole233 commented on Sep 22, 2016

   

   ohuole233

   on Sep 22, 2016

   More actions

   Oh, I get it and I have added it to the DBN class. Thank you again.

   At 2016-09-22 08:22:24, "Alison Marczewski" notifications@github.com wrote:

   You can try something like:

   def new_representation_X_train(hidden_layer):
   new_representation_train = theano.function(
   inputs = [index],
   outputs = self.sigmoid_layers[hidden_layer].output,
   givens = {
   self.x: train_set_x[
   index: index + 1
   ]
   }
   )
   train_lines = train_set_x.get_value(borrow=True).shape[0]
   return [new_representation_train(i) for i in xrange(train_lines)]

   —
   You are receiving this because you are subscribed to this thread.
   Reply to this email directly, view it on GitHub, or mute the thread.
6. amarczew commented on Sep 25, 2016

   

   amarczew

   on Sep 25, 2016

   More actions

   @ohuole233 remember this value comes from a sigmoid function. If you want the linear output, you need to create a linear_output = T.dot(input, self.W) + self.b and get its value inside the function I wrote above.
7. ohuole233 commented on Sep 27, 2016

   

   ohuole233

   on Sep 27, 2016

   More actions

   @amarczew Hi.professor~ After the method new_representation_X_train added in the class DBN,and I run the code like this:

   import theano
   import DBN
   import mlp
   import rbm
   import numpy

   pretraining_epochs=2
   pretrain_lr=0.1
   k=1
   batch_size=2

   train_set=[[1,2,3,1],[2,3,1,4],[3,6,4,2],[3,5,4,5],[4,2,5,2],[4,3,2,6]]
   train_set_x = theano.shared(numpy.asarray(train_set,
   dtype=theano.config.floatX),
   borrow=True)
   n_train_batches = train_set_x.get_value(borrow=True).shape[0]
   numpy_rng=numpy.random.RandomState(123)

   dbn=DBN.DBN(numpy_rng=numpy_rng,n_ins=4,hidden_layers_sizes=[3,3],n_outs=2)
   pretraining_fns=dbn.pretraining_functions(train_set_x=train_set_x,batch_size=batch_size,k=k)

   print dbn.new_representation_X_train(2)

   An unexpected bug occured to remind me that "TypeError: new_representation_X_train() takes exactly 1 argument (2 given)".
   Is there any idea cope with this?
   Much thanks and Waiting for your reply soon.
8. amarczew commented on Sep 27, 2016

   

   amarczew

   on Sep 27, 2016

   More actions

   @ohuole233 probably the problem is related to self parameter that is passed implicitly, because you are calling a function from an object. Change to def new_representation_X_train(self, hidden_layer): may fix it.
9. ohuole233 commented on Sep 28, 2016

   

   ohuole233

   on Sep 28, 2016

   More actions

   Grateful for your reply. but it seems 'global name 'index' is not defined. I haven't got how to define it and my objective is to derive new representation for each input.Waiting for your assistance sincerely .
   😀

   发自网易邮箱大师
   On 09/28/2016 03:41, Alison Marczewski wrote:

   @ohuole233 probably the problem is related to self parameter that is passed implicitly, because you are calling a function from an object. Change to def new_representation_X_train(self, hidden_layer): may fix it.

   —
   You are receiving this because you were mentioned.
   Reply to this email directly, view it on GitHub, or mute the thread.
10. amarczew commented on Sep 28, 2016

    

    amarczew

    on Sep 28, 2016

    Last edited by amarczew

    More actions

    @ohuole233 you need to declare this tensor index = T.lscalar('index'), before this function
11. ohuole233 commented on Oct 8, 2016

    

    ohuole233

    on Oct 8, 2016

    More actions

    @amarczew Hi, Professor. I have abandoned training on GUPs with some special settlements. However, after the above repair including declaring the tensor and adding self, a new error named '' NameError: global name 'train_set_x' is not defined '' occurred. Is there anything to fix the bug?
    It would be very kind of you to send me the DBN class code including the intermediate representation method and my email is hhq123go@gmail.com.
    Waiting for your reply. Thanks~^-^
12. amarczew commented on Oct 8, 2016

    

    amarczew

    on Oct 8, 2016

    More actions

    @ohuole233 Unfortunately I don't have this implementation. This function is working on SdA.py implementation. You can take a look on this file to solve the problem in your DBN implementation. I have declared this function inside build_finetune_functions(...)