Questions tagged [skflow]

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.

76 questions
0
votes
1 answer

CSV File Into SkFlow

I'm just starting out with Tensorflow. As I understand it, SkFlow is a... Simplified interface for TensorFlow And for me simple is good. TensorFlow's Github has some useful starter examples using the Iris dataset included in SkFlow. This is from…
Ben Mayo
  • 1,285
  • 2
  • 20
  • 37
0
votes
1 answer

How do I create non fully connected layers in skflow?

I want to create a more complex architecture than requires layers connected in a custom way.Can I achive this in skflow ? And if not which framework is best ? Thanks
0
votes
0 answers

How to pass data from arbitrary sources (not files) though tensorflow.contrib.learnEstimator.fit input_fn() ?

The Estimator.fit() function takes as argument either (x, y, and batch_size) where x and y could be numpy arrays or iterators. PROS Easy to use. Allows feeding data from arbitrary source as long as problem can be decomposed into x and y. CONS No…
Abhi
  • 111
  • 1
  • 3
0
votes
1 answer

Classifer partial fit in tensorflow

I would like to use SKFLOW to step through the fit of a DNNClassifier, unfortunately code such as: step_classifier = skflow.DNNClassifier(hidden_units=[10, 20, 10], n_classes=3) for _ in range(50): step_classifier =…
Rob Umbra
  • 1
  • 3
0
votes
2 answers

How to input data in a tensorflow learn validation monitor?

I'm trying to use a validation monitor in skflow by passing my validation set as numpy array. Here is some simple code to reproduce the problem (I installed tensorflow from the provided binaries for Ubuntu/Linux 64-bit, GPU enabled, Python…
dbikard
  • 491
  • 1
  • 4
  • 13
0
votes
1 answer

skflow with Docker images gets learn.datasets not imported error

I set the docker image with Dockerfile below. FROM gcr.io/tensorflow/tensorflow:latest-devel RUN pip install --upgrade pip RUN pip install scikit-learn RUN pip install scipy RUN pip install pandas I am using Pycharm and set the remote Docker tf…
tompal18
  • 1,164
  • 2
  • 21
  • 39
0
votes
1 answer

How do I get variables used in model/function pass to TensorFlowEstimator

How do I get variables (e.g., embedding table, RNN variables, etc.) after the model fitting, when using TensorFlowEstimator for fitting, such as in this skflow example? As tf.all_variables() returns empty list.
chentingpc
  • 1,283
  • 3
  • 18
  • 24
0
votes
1 answer

skflow.TensorFlowDNNRegressor parameters

I am new to skflow. With the following example code, I am able to initialize a neural network estimator. regressor = skflow.TensorFlowDNNRegressor( hidden_units=[10, 10], steps=5000, learning_rate=0.1, batch_size=1) I would…
0
votes
1 answer

Applying custom costfunction in TensorFlow's SKFlow model training

I'm trying to make a regression model with TensorFlow while using the sklearn implementation so it plays nicely with all the other models I've made. However I cannot seem to find a way to train the model with a custom score function (cost function…
SARose
  • 3,558
  • 5
  • 39
  • 49
0
votes
1 answer

Does TensorFlowDNNClassifier or any other deep neural-network model in TensorFlow support predicting of a float value?

In TensorFlowDNNClassifier, I have to specify n_classes (number of classes). What if i am predicting a float value between 0 and 1 ? there could be infinite number of classes if I want full accuracy. To be more clear, the neural-network in skflow of…
Yee Liu
  • 1,417
  • 3
  • 15
  • 17
0
votes
1 answer

Are scalar_summary missed in skflow?

I'm having issue to get the loss (training or monitoring) summary showing in tensorboard using skflow This is my code: classifier = skflow.TensorFlowEstimator( model_fn=conv_model, n_classes=2, batch_size=BATCH_SIZE, steps=100000,…
laouer
  • 1
0
votes
2 answers

Why Pycharm cannot recognize functions of Skflow?

I install Skflow and ran digits.py example on Pycharm and saw that it returns an error "AttributeError: 'module' object has no attribute 'TensorFlowDNNRegressor". I proceed and ran the same program on Ipython and everything's fine. What should be…
user3147590
  • 1,231
  • 2
  • 10
  • 16
0
votes
2 answers

Install SKFLOW to work with Anaconda

Now that SKFLOW has been moved within TensorFlow I am not sure how to use it. I am running Anaconda on Ubuntu server and I installed Tensorflow as suggested in this question: Tensorflow and Anaconda on Ubuntu? My scripts are seeing Tensorflow but…
denson
  • 2,366
  • 2
  • 24
  • 25
0
votes
1 answer

Is it desirable to scale data for skflow.TensorFlowDNNClassifier?

My colleagues and this question on Cross Validated say you should transform data to zero mean and unit variance for neural networks. However, my performance was slightly worse with scaling than without. I tried using: scaler =…
denson
  • 2,366
  • 2
  • 24
  • 25
0
votes
1 answer

skflow example throws errors

I'm quite new to python and skflow, but I am experiencing a really basic problem and hope someone could help me. I've installed skflow and downloaded the dbpedia_csv which is used in the examples. However upon running the…
GameOfThrows
  • 4,510
  • 2
  • 27
  • 44