Closed JafferWilson closed 6 years ago
Is there any one please guide me?
Dear Jaffer,
Sorry for belated response. We were all busy with AAAI submissions. The param to select different trait varies from 0 to 4.
Yes I understood that the param are from 0 to 4. But I see only this statement:
python conv_layer_train.py -static -word2vec 2
which I guess is for training only. How the predict statement works. Kindly add it in the Read.me file of your repository. All the Best for your Submissions.
Second'ing Jaffer's comment;
Your readme only contains instructions for pre-processing & training. Could you update it to reflect how to actually detect personality traits when given text data?
@advanced4 I didn't got you. Can you please make me understand what you in need of?
@JafferWilson you solve the python conv_layer_train.py -static -word2vec 2 ?
i got error
Traceback (most recent call last):
File "conv_net_train.py", line 476, in
can u please help me i did't understand the error .. i
@naikzinal What is the version of your Theano library? I guess the issue is due to the recent library used, the updated one.
dear jafferWilson i have check my theano version still i have that issue . can you please help me. thank you
@naikzinal What is the version?
@JafferWilson theano 0.7
@JafferWilson but i dont understand the meaning theano 0.7(tested) what is the meaning of tested?
@naikzinal I guess, you need a fresh installation. Please try using some other system and then use it. I don't find any problem if your version is correct.
which kind of system you used for run the code? @JafferWilson
@naikzinal I have used my Virtual box or Virtual Machine with ubuntu 16.04(updated). What system you have tried?
i also use ubuntu 16.04. @JafferWilson
@naikzinal Try once again with fresh installation. Better use VM for your experiment then on the right machine.
ok i will try . thank you
heloo, while running the conv_net_train.py i found the error
loading data... data loaded!
model architecture: CNN-static
using: word2vec vectors
[('image shape', 153, 300), ('filter shape', [(200, 1, 1, 300), (200, 1, 2, 300), (200, 1, 3, 300)]), ('hidden_units', [200, 200, 2]), ('dropout', [0.5, 0.5, 0.5]), ('batch_size', 50), ('non_static', False), ('learn_decay', 0.95), ('conv_non_linear', 'relu'), ('non_static', False), ('sqr_norm_lim', 9), ('shuffle_batch', True)]
Traceback (most recent call last):
File "conv_net_train.py", line 477, in
please any one can help me. thank you
dear @JafferWilson heloo, while running the conv_net_train.py i found the error
loading data... data loaded! model architecture: CNN-static using: word2vec vectors [('image shape', 153, 300), ('filter shape', [(200, 1, 1, 300), (200, 1, 2, 300), (200, 1, 3, 300)]), ('hidden_units', [200, 200, 2]), ('dropout', [0.5, 0.5, 0.5]), ('batch_size', 50), ('non_static', False), ('learn_decay', 0.95), ('conv_non_linear', 'relu'), ('non_static', False), ('sqr_norm_lim', 9), ('shuffle_batch', True)] Traceback (most recent call last): File "conv_net_train.py", line 477, in activations=[Sigmoid]) File "conv_net_train.py", line 123, in train_conv_net convfeats, = theano.scan(fn= convolve_user_statuses, sequences= layer0_input) File "/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan.py", line 745, in scan condition, outputs, updates = scan_utils.get_updates_and_outputs(fn(args)) File "conv_net_train.py", line 115, in convolve_user_statuses layer1_inputs.append(conv_layer.set_input(input=relv_input).flatten(2)) File "conv_net_classes.py", line 393, in set_input conv_out = conv.conv2d(input=input, filters=self.W,filter_shape=self.filter_shape, image_shape=self.image_shape) File "/usr/local/lib/python2.7/dist-packages/theano/tensor/nnet/conv.py", line 151, in conv2d return op(input, filters) File "/usr/local/lib/python2.7/dist-packages/theano/gof/op.py", line 507, in call node = self.make_node(inputs, **kwargs) File "/usr/local/lib/python2.7/dist-packages/theano/tensor/nnet/conv.py", line 628, in make_node "inputs(%s), kerns(%s)" % (_inputs.dtype, _kerns.dtype)) NotImplementedError: The image and the kernel must have the same type.inputs(float64), kerns(float32)
And i want to know that which device you used for run the code gpu or cpu?i think i have a problem in Theanorc file what is yr configuration for Theanorc file? thank you
My system works on CPU and GPU. But I ran the process on CPU.
@JafferWilson ok, thank you for a reply. what is your theanorc file configuration?
@JafferWilson Did you got output after running the conv_net_train.py? I am struck ed in this step.can you please help.
Thanks in advance.
@radhikakuttala I tried it way before.. Now I do not have anything. Frankly, its results wasted time. Hence, do not want to discuss about it. For your answer, yes I got the output.
Hi Guys
While running the conv_net_train.py I found the error
loading data... data loaded! model architecture: CNN-static using: word2vec vectors [('image shape', 153, 300), ('filter shape', [(200, 1, 1, 300), (200, 1, 2, 300), (200, 1, 3, 300)]), ('hidden_units', [200, 200, 2]), ('dropout', [0.5, 0.5, 0.5]), ('batch_size', 50), ('non_static', False), ('learn_decay', 0.95), ('conv_non_linear', 'relu'), ('non_static', False), ('sqr_norm_lim', 9), ('shuffle_batch', True)] Traceback (most recent call last): File "conv_net_train.py", line 477, in activations=[Sigmoid]) File "conv_net_train.py", line 123, in train_conv_net convfeats, = theano.scan(fn= convolve_user_statuses, sequences= layer0_input) File "/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan.py", line 745, in scan condition, outputs, updates = scan_utils.get_updates_and_outputs(fn(args)) File "conv_net_train.py", line 115, in convolve_user_statuses layer1_inputs.append(conv_layer.set_input(input=relv_input).flatten(2)) File "conv_net_classes.py", line 393, in set_input conv_out = conv.conv2d(input=input, filters=self.W,filter_shape=self.filter_shape, image_shape=self.image_shape) File "/usr/local/lib/python2.7/dist-packages/theano/tensor/nnet/conv.py", line 151, in conv2d return op(input, filters) File "/usr/local/lib/python2.7/dist-packages/theano/gof/op.py", line 507, in call node = self.make_node(inputs, **kwargs) File "/usr/local/lib/python2.7/dist-packages/theano/tensor/nnet/conv.py", line 628, in make_node "inputs(%s), kerns(%s)" % (_inputs.dtype, _kerns.dtype)) NotImplementedError: The image and the kernel must have the same type.inputs(float64), kerns(float32)
I am using theano 0.7, pandas 0.18.0 and Python 2.7 ( which is mentioned in the read me file). I have tried all combinations of these three ( Python 2.7 and 3.5), Theano ( 0.7,0.8,0.9,1.0) and pandas( 0.18.0,0.22.0)
Can you help me with this issue ? Also how can I use these to get all the five personality traits in one go using the trained model ? Thanks for your help! Nitin
@JafferWilson Are you able to find the answer to this issue? Can you please share it with us.
this is exactly what i want @JafferWilson how to use and predict all the five traits throws this code if you found or create any solution for this problem
Hi @SenticNet i read your papers and do my effort to run the code but i have some questions 1)what is content of mairesse file and how get it 2)how use this code to get big five traits through text input
Hi @JafferWilson did you found any solution to your problem
@SenticNet
Please check the pre-processing section of readme to know about the generation of mairesse feature.
Hi @JafferWilson, if you can help me please with the code used to predict the five traits using trained model. @SenticNet
Hi, I was just going through your repository and I like the way you have explain regarding the project. But I can see while training we are just passing one traits number; for example in your sample you have used
2
code and started the training. But what if for others?Also you have not mentioned anything related to the model usage after training. Kindly answer the questions I have. Thank you in advance.