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
2
votes
2 answers
skflow allocates memory in gpu0 even when other gpu is specified
I'm running into this problem on a 4 GPU Amazon instance, using a simple example script:
import skflow
import tensorflow as tf
from sklearn import datasets
iris = datasets.load_iris()
X_train, X_test, y_train, y_test =…
P. Camilleri
- 12,664
- 7
- 41
- 76
1
vote
1 answer
How To Use tf.estimator.DNNClassifier (Scikit Flow?)
Could someone point me to a basic working example for tf.estimator.DNNClassifier (originally skflow)?
Since I'm familiar with Sklearn, I was excited to read about Scikit Flow on this blog. Especially the api looked pretty much the same as…
jl303
- 1,461
- 15
- 27
1
vote
1 answer
How to run TF learn (skflow) Kmeans clustering in multi-machine multi-gpu environment?
Is there any example / documentation which shows how to implement skflow(tf.contrib.learn) in multi-machine and multi-GPUs environment?
I want to implement KMeansClustring using skflow(tf.contrib.learn) in a multi-machine and multi-GPUs…
Rahul
- 645
- 1
- 9
- 21
1
vote
0 answers
Weight/bias initialization in Skflow
I've been using TensorFlow to create feed-forward neural nets with customized initial weights and biases (cannot provide code for proprietary reasons, but another algorithm outputs initial matrices that are then plugged into tf for optimization).…
Kelli Humbird
- 11
- 2
1
vote
1 answer
How to make contrib.learn (SKFLOW) regression predict multiple values (TensorFlow 0.12.1)
This is very similar to the question skflow regression predict multiple values. However, later versions of TensorFlow seem to rendered the answer from this question obsolete.
I would like to be able to have multiple output neurons in a TensorFlow…
JeffHeaton
- 3,250
- 1
- 22
- 33
1
vote
1 answer
Tensorflow contrib.learn.Estimator multi-GPU
In order to use the contrib.learn.Estimator for multi-GPU training, I am attempting to specify GPU assignments in my model_fn.
In pseudo-code:
def model_fn(X, y):
with tf.device('/gpu:1'):
... various tensorflow ops for model ...
…
Asher Newcomer
- 201
- 1
- 7
1
vote
2 answers
Error in saving and using model of TensorForestEstimator for Android
I use the randomforest estimator, implemented in tensorflow, to predict if a text is english or not. I saved my model (A dataset with 2k samples and 2 class labels 0/1 (Not English/English)) using the following code (train_input_fn function return…
TryToBeNice
- 323
- 3
- 14
1
vote
2 answers
Tensorflow Timeline with SKFlow
The Tensorflow Timeline described here is a method of profiling tensorflow runs using the Chrome tracing machinery. However to use it, seems to require setting options in the Session.run() call, e.g.:
with tf.Session() as sess:
run_options =…
momeara
- 1,341
- 2
- 17
- 29
1
vote
1 answer
tf.contrib.learn.BaseEstimator.evaluate(): What is the meaning of the "steps" parameter?
According to https://www.tensorflow.org/versions/r0.9/api_docs/python/contrib.learn.html, the tf.contrib.learn.BaseEstimator.evaluate function can take in a steps parameter. The parameter is explained as follows:
steps: Number of steps for which to…
Yibin Lin
- 681
- 1
- 6
- 20
1
vote
1 answer
How to use StreamingDataFeeder as contrib.learn.Estimator.fit()'s input_fn?
I have recently started using tensorflow.contrib.learn (skflow) library and really like it. However, I am facing an issue with using Estimator, the fit function uses either
(X, Y, and batch_size) - the problem with this approach is that it does…
Abhi
- 111
- 1
- 3
1
vote
1 answer
Tensorflow examples all fail due to AttributeError: 'module' object has no attribute 'load_csv'
I am running Tensor flow 0.11. This is the code which I just copied from TensorFlow tutorial to load CSV dataset.
Code
import tensorflow as tf
import numpy as np
IRIS_TRAINING = "iris_training.csv"
IRIS_TEST = "iris_test.csv"
# Load…
Paul Chandran
- 11
- 3
1
vote
1 answer
Is DNNClassifier unstable compared with TensorFlowDNNClassifier?
I'm building a DNN predicted (0 or 1) model based on skflow with TF v0.9.
My code with TensorFlowDNNClassifier is like this. I train about 26,000 records and test 6,500 one.
classifier = learn.TensorFlowDNNClassifier(hidden_units=[64, 128, 64],…
Ryo Katsuma
- 11
- 4
1
vote
2 answers
tensorflow contrib.learn save
How do you save your model output with the new contrib.learn functions like contrib.learn.DNNClassifier?
The deprecated functions like skflow.TensorFlowDNNClassifier had methods .save and .restore. These were supposedly migrated over to the…
jah
- 11
- 2
1
vote
1 answer
python error setting an array element with a sequence
I trying to explore different classifier for this example in scikit-learn
website http://scikit-learn.org/stable/tutorial/text_analytics/working_with_text_data.html. However, the code below produced an error: ValueError: setting an array element…
edwin
- 1,152
- 1
- 13
- 27
1
vote
1 answer
tensorflow DNN with two hidden layers significantly slower and produce much worse result than using scikit flow
my bio dataset has 20K rows and 170 feature. I'm doing dnn regression to predict bioactivity. ( one unit output layer with linear equation and two hidden layers). It ran very slow on my cpu and produced really bad r-square (negative). Then I ran…
zesla
- 11,155
- 16
- 82
- 147