Questions regarding using Scikit Flow - a simplified interface for TensorFlow to help people get started on predictive analytics and data mining for deep learning. Recently integrated into the contributions section of TensorFlow and renamed to TensorFlow Learn.
Questions tagged [skflow]
76 questions
3
votes
1 answer
Adding regularizer to skflow
I recently switched form tensorflow to skflow. In tensorflow we would add our lambda*tf.nn.l2_loss(weights) to our loss. Now I have the following code in skflow:
def deep_psi(X, y):
layers = skflow.ops.dnn(X, [5, 10, 20, 10, 5], keep_prob=0.5)
…
maininformer
- 967
- 2
- 17
- 31
3
votes
1 answer
Multiple Categorical Input Variables in Tensorflow
I have a data-set in which each feature vector has 50 features, 45 of which are categorical. I am having trouble sending the categorical variables into tensorflow. I have found an example tutorial for tensorflow with categorical variables, but do…
Nick Delben
- 95
- 3
- 14
3
votes
1 answer
Limit GPU memory allocation in skflow
I am training convnets with Tensorflow and skflow, on an EC2 instance I share with other people. For all of us to be able to work at the same time, I'd like to limit the fraction of available GPU memory which is allocated.
This question does it…
P. Camilleri
- 12,664
- 7
- 41
- 76
3
votes
2 answers
Error running skflow example
I just installed skflow and TensorFlow and I'm having a problem with the example that comes with skflow. The example code is:
import random
import pandas
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import…
CBrauer
- 1,035
- 2
- 11
- 17
2
votes
0 answers
Input is not invertible. [[Node: MatrixInverse_2=MatrixInverse[T=DT_FLOAT, adjoint=false, _device="/job:localhost/replica:0/task:0/cpu:0"](add_138)]]
I am trying to implement Gaussian Mixture Model using Tensorflow's tf.learn(skflow) but I am getting the following error.
from tensorflow.contrib.factorization.python.ops import gmm as gmm_lib
import random
import numpy as np
x =…
Rahul
- 645
- 1
- 9
- 21
2
votes
1 answer
which higher layer abstraction to use for tensorflow
I am looking for higher layer abstractions for my deep learning project.
Few doubts lately.
I am really confused about which is more actively maintained tflearn(docs), or tensorflow.contrib.learn. But projects are different and actively contributed…
v78
- 2,803
- 21
- 44
2
votes
1 answer
Cannot achieve repeatability in tensorflow
I am trying to learn tensorflow with High level API for learning with TensorFlow and having problem with not getting repeatable results.
TensorFlow 0.12.0-rc0 (CPU Only)
python 3.5
import numpy as np
import tensorflow as tf
import os
import…
Bulat Gazizov
- 21
- 3
2
votes
0 answers
Cross-validation with Scikit Flow fails
I am using scikit-learn for evaluating my neural net implemented in tensorFlow and wrapped by an TensorFlow estimator:
import tensorflow.contrib.learn as skflow
from sklearn.model_selection import train_test_split
from sklearn.model_selection…
machineLearner
- 149
- 1
- 8
2
votes
1 answer
How to create `input_fn` using `read_batch_examples` with `num_epochs` set?
I have a basic input_fn that can be used with Tensorflow Estimators below. It works flawlessly without setting the num_epochs parameter; the obtained tensor has a discrete shape. Pass in num_epochs as anything other than None results in an unknown…
craymichael
- 4,578
- 1
- 15
- 24
2
votes
1 answer
tensorflow learn - initialize variables
I have a problem with getting started with “tensforflow learn” (previously called skflow).
My problem ?
I am not able to run even the simplest example of a DNN
The example below throws an error
**RuntimeError: Init operations did not make…
user1043144
- 2,680
- 5
- 29
- 45
2
votes
1 answer
tensorflow 0.9 skflow model save and restore doesn't work
I have updated my tensorflow from 0.7 to 0.9 on python3.And now i can't restore my previous saved models with skflow(tensorflow.contrib.learn).Here is the sample code example that was worked on tensorflow 0.7.
import tensorflow.contrib.learn as…
Armen Davtyan
- 23
- 6
2
votes
2 answers
TensorFlowDNNClassifier class is deprecated but replacement does not seem to work?
Using the following with TF .9.0rc0 on 60,000 (train) and 26,000 (test) on or so records with 145 coded columns (1,0) trying to predict 1 or 0 for class identification..
classifier_TensorFlow = learn.TensorFlowDNNClassifier(hidden_units=[10, 20,…
dartdog
- 10,432
- 21
- 72
- 121
2
votes
1 answer
tensorflow model has different results than the same model in skflow (optimizer)
I'm using tensorflow to replicate a neural network for the MNIST dataset, previously programmed in skflow. Here is the model in skflow:
import tensorflow.contrib.learn as skflow
from sklearn import metrics
from sklearn.datasets import…
Ismael
- 733
- 6
- 15
2
votes
0 answers
Correct use of Tensorflow tf.split function in SKFlow
There is a minimal example of an RNN in the Skflow documentation. The input data is a matrix with shape (4,5). Why is the data split according to the following function for input?:
def input_fn(X):
return tf.split(1, 5, X)
This function…
user2726995
- 2,064
- 2
- 21
- 26
2
votes
2 answers
TensorFlow with skflow: AttributeError: 'module' object has no attribute 'saver_pb2'
I tried to run the iris_save_restore.py example from skflow, without changing the code at all.
However, I got an error, and I am unsure how to proceed.
It seems that it happened when it restores the model from a saved file.
new_classifier =…
Hummer
- 21
- 1
- 3