mehdiabbanabennani/neural-networks-for-collaborative-filtering

Deep Learning for Recommendation

neural-networks-for-collaborative-filtering's Issues

I tensorflow/stream_executor/dso_loader.cc:119] Couldn't open CUDA library libcupti.so.

rzai@rzai00:~/prj/Neural-Networks-for-Collaborative-Filtering$ CUDA_VISIBLE_DEVICES=1 python3 main.py
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcurand.so locally
/usr/local/lib/python3.4/dist-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
"This module will be removed in 0.20.", DeprecationWarning)
.................................................................................................
Please switch to tf.summary.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
WARNING:tensorflow:From /home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/autoencoder/Autoencoder.py:76 in run_training.: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.global_variables_initializer instead.
I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties:
name: GeForce GTX 1080
major: 6 minor: 1 memoryClockRate (GHz) 1.7335
pciBusID 0000:01:00.0
Total memory: 7.92GiB
Free memory: 7.43GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0)
I tensorflow/stream_executor/dso_loader.cc:119] Couldn't open CUDA library libcupti.so. LD_LIBRARY_PATH: /home/rzai/torch/install/lib:/home/rzai/torch/install/lib:/home/rzai/torch/install/lib:/home/rzai/torch/install/lib:/usr/local/cuda-8.0/lib64:/home/rzai/torch/install/lib:/home/rzai/torch/install/lib:/home/rzai/torch/install/lib:/home/rzai/torch/install/lib:
F tensorflow/core/platform/default/gpu/cupti_wrapper.cc:59] Check failed: ::tensorflow::Status::OK() == (::tensorflow::Env::Default()->GetSymbolFromLibrary( GetDsoHandle(), kName, &f)) (OK vs. Not found: /usr/local/lib/python3.4/dist-packages/tensorflow/python/_pywrap_tensorflow.so: undefined symbol: cuptiActivityRegisterCallbacks)could not find cuptiActivityRegisterCallbacksin libcupti DSO

Aborted (core dumped)
rzai@rzai00:~/prj/Neural-Networks-for-Collaborative-Filtering$

A bug report.---add 'mkdir -p ../Databases' at 'bash/import.sh'

diff --git a/bash/import.sh b/bash/import.sh
index 0cbbd10..52e790b 100755
--- a/bash/import.sh
+++ b/bash/import.sh
@@ -1,5 +1,5 @@
#!/bin/bash

+mkdir -p ../Databases
if [ $1 = "2" ]
then
echo 'Downloading files'

ImportError: No module named 'fs'

rzai@rzai00:/prj/Neural-Networks-for-Collaborative-Filtering$ python3 main.py
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcurand.so locally
/usr/local/lib/python3.4/dist-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
"This module will be removed in 0.20.", DeprecationWarning)
Traceback (most recent call last):
File "main.py", line 1, in
from config.stability.V_1M import Experiment
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/config/stability/V_1M.py", line 1, in
from stability.ExperimentStability import ExperimentStability
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/stability/ExperimentStability.py", line 1, in
from autoencoder.Experiment import Experiment
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/autoencoder/Experiment.py", line 5, in
from autoencoder.Import import Import
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/autoencoder/Import.py", line 5, in
from tools.tools import global_parameters
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/tools/tools.py", line 1, in
from fs.osfs import OSFS
ImportError: No module named 'fs'
rzai@rzai00:/prj/Neural-Networks-for-Collaborative-Filtering$

Remove the boring warning message by...........

diff --git a/tools/tools.py b/tools/tools.py
index 9aee363..988e950 100644
--- a/tools/tools.py
+++ b/tools/tools.py
@@ -68,13 +68,13 @@ def log_folder():
def variable_summaries(var, name):
with tf.name_scope(name + 'summaries'):
mean = tf.reduce_mean(var)

• tf.scalar_summary(name + 'mean', mean)

• tf.summary.scalar(name + 'mean', mean)
  with tf.name_scope(name + 'stddev'):
  stddev = tf.sqrt(tf.reduce_sum(tf.square(var - mean)))

• tf.scalar_summary(name + 'sttdev', stddev)
• tf.scalar_summary(name + 'max', tf.reduce_max(var))
• tf.scalar_summary(name + 'min', tf.reduce_min(var))
• tf.histogram_summary(name, var)

• tf.summary.scalar(name + 'sttdev', stddev)
• tf.summary.scalar(name + 'max', tf.reduce_max(var))
• tf.summary.scalar(name + 'min', tf.reduce_min(var))
• tf.summary.histogram(name, var)

--- a/autoencoder/Train.py
+++ b/autoencoder/Train.py
@@ -81,7 +81,7 @@ class Train(object):

 @staticmethod
 def training(loss, optimiser):

•    tf.scalar_summary(loss.op.name, loss)
  

•    tf.summary.scalar(loss.op.name, loss)
     global_step = tf.Variable(0, name='global_step', trainable=False)
     train_op = optimiser.minimize(loss=loss, global_step=global_step)
     return train_op
  

TypeError: listdir() missing 1 required positional argument: 'path'

Train Data Eval:
0.5560789520477667
differences evaluation time 15.92467975616455
check self.rmse different from zero:
0.5560789520477667
check that the value changed
check assertion
WARNING:tensorflow:From /home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/stability/AutoencoderStability.py:81 in run_training.: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.global_variables_initializer instead.
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0)
epoch 14.0
Test Data Eval:

--- parameters ---
{'stability': {'probability': 0.80000000000000004, 'subsets_number': 3, 'rmse': 0.5560789520477667, 'first_learning': 'autoencoder', 'landa_array': array([ 0.42600274, 0.3418732 , 0.1191205 , 0.11300356]), 'differences': <3952x6040 sparse matrix of type '<class 'numpy.float32'>'
with 900188 stored elements in Compressed Sparse Row format>}, 'rmse': {'autoencoder': 0.8819002411444694, 'stability_factorisation': 0.984447690186304, 'stability_autoencoder': 0.983267223202749}, 'factorisation': {'iterations': 10, 'dimension': 10, 'landa': 3}, 'autoencoder': {'learning_decay': 0.90000000000000002, 'regularisation': 0.20000000000000001, 'learning_rate0': 0.001, 'hidden1_units': 700, 'batch_size_evaluate': 100, 'is_test': True, 'batch_size_train': 35, 'nb_epoch': 15}, 'experiments': {'mean_iterations': 1, 'nb_draws': 30}, 'sets': {'validation_ratio': 0.10000000000000001, 'database_id': 1, 'learning_type': 'V', 'test_ratio': 0.10000000000000001}}
--- rmse ---
0.9854376045587415
--- 202.1434624195099 seconds ---

Traceback (most recent call last):
File "main.py", line 1, in
from config.stability.V_1M import Experiment
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/config/stability/V_1M.py", line 50, in
Experiment.run()
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/autoencoder/Experiment.py", line 127, in run
self.log_to_file()
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/autoencoder/Experiment.py", line 42, in log_to_file
file_name = log_folder() + 'log.txt'
File "/home/rzai/prj/Neural-Networks-for-Collaborative-Filtering/tools/tools.py", line 64, in log_folder
test_n = len(list(n for n in folder.listdir() if n.startswith('test')))
TypeError: listdir() missing 1 required positional argument: 'path'
rzai@rzai00:~/prj/Neural-Networks-for-Collaborative-Filtering$