TensorFlow with GPU support
Questions tagged [tensorflow-gpu]
430 questions
0
votes
0 answers
Unable to install v0.11.0 tensorflow-gpu
I am having issues with installing the v0.11.0 version of tensorflow-gpu. My code works on tensorflow==0.11.0 but really slow. I had a tensorflow-gpu==0.11.0 but i had lost it due to an upgrade. The pip repository doesn't have a v0.11 anymore and…
canonball
- 473
- 7
- 20
0
votes
1 answer
Specific topics on Tensorflow for CNN
I have a mini project for my new course in Tensorflow for this semester with random topics. Since I have some background on Convolution Neuron Network, I intend to use it for my project. My computer can only run CPU version of TensorFlow.
However,…
Chuong Nguyen
- 57
- 1
- 8
0
votes
0 answers
keras Installation with already installed Tensorflow GPU version in windows 10
I have following environment in my windows 10 machine
Python : 3.6.0
Anaconda:4.3.1
Tensorflow:1.1.0
Screen Shots
OS:Windows 10-64bit
Now when I am trying to install keras into my system I am getting a huge list of errros.
Detailed Error Log
Now…
Naseer
- 3,147
- 5
- 31
- 61
0
votes
0 answers
TensorFlow OutOfRangeError FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements
I am desperately trying to find the error in my program. I consistently get the following error:
[[Node: input_producer/limit_epochs/CountUpTo = CountUpTo[T=DT_INT64, _class=["loc:@input_producer/limit_epochs/epochs"], limit=1,…
Squall
- 31
- 2
0
votes
1 answer
while upgrading tensorflow to gpu version , it thowrs PermissionError
Exception: Traceback (most recent call last): File
"C:\ProgramData\Anaconda3\lib\site-packages\pip\basecommand.py", line
215, in main
status = self.run(options, args) File…
0
votes
1 answer
Compile custom tensorflow op for CUDA
I'm developing a custom OP for tensorflow that needs GPU support, following the guide in the tensorflow documentation. While tracing the errors in my own code I went back to the example from the documentation and tried to compile the referenced code…
ma0ho
- 491
- 1
- 3
- 12
0
votes
1 answer
How do you extract the weight matrix and hyperparameters along with the layer parameters in Tensorflow?
I saw tf.train.Saver but I believe that doesn't solve my problem and I am worried that I might have to do surgery on Tensorflow to make the weight matrix and hyperparameters along with the activation function and layer parameters exportable and…
Shyamal Chandra
- 31
- 3
0
votes
1 answer
GPU - Black Screen when running Tensorflow on Python3.5 in Windows 8.1
Followed instructions on https://www.tensorflow.org/install/install_windows
When I get to
activate tensorflow-gpu
$ python
import tensorflow as tf
hello = tf.constant('Hello, TensorFlow!')
sess = tf.Session()
Screen goes Black. When I move the…
yukimach
- 1
- 2
0
votes
1 answer
Extracting feature from the last layer before classification in keras
I have tried to extract feature in the keras ( with tensorflow and as well as with theano background). But became not successful.
My code is :
model = Sequential()
model.add(Convolution2D(64, 5, 5, input_shape=(3,img_width,…
Rapa
- 41
- 7
0
votes
1 answer
Tensorflow-GPU Error - Pycharm
I am installing Tensor flow.
I was having trouble installing through Anaconda, so I uninstalled everything including Python, and downloaded Python 3.5 from here:
https://www.python.org/downloads/release/python-352/
After installing Python 3.5 I…
Justin Scott
- 51
- 3
0
votes
1 answer
tensorflow neural network, TypeError: eval() got multiple values for argument 'feed_dict'
I'm using tensorflow to implement a 4 hidden layer sigmoid activated neural network, the following is the code.
import tensorflow as tf
import numpy as np
from sklearn import preprocessing
import pandas as pd
#importing and preprocessing…
OwnThisField
- 23
- 8
0
votes
1 answer
Tensorflow allocates all GPU despite saying otherwise
I want to run a script written on Python and using Tensorflow. SInce the server is shared with other colleagues, I would like to restrict my script to use at most 1/3 of the GPU memory the server has.
In order to accomplish that, I do the following…
C. Güzelhan
- 107
- 1
- 12
0
votes
1 answer
Error training images using tensorflow inception v3
I am implementing image classification using TensorFlow Inception v3 with GTX 1060 GPU. I trained around 3000 images in 9 different classifier, where each classifier contains from 100 to 500 images(100*100 px) using tensor for poets.
But when I…
sk3145
- 142
- 14
0
votes
1 answer
python tensorflow won't install
I've tried to install tensorflow (python 3.5) in many ways without succeed:
By typing "pip install tensorflow" and "pip install tensorflow-gpu" and
getting the error:
Could not find a version that satisfies the requirement tensorflow (from
…
0
votes
2 answers
How is tensorflow's Back propagation implemented ? (Memory problems)
I've started implementing a fast-rcnn in TF (VGG16 based). While doing my learning, I'm having memory issues if I try to back propagate over all layers. But test works good though. (I have a Gforce GTX 1060 with 6G of ram)
I was wondering how comes…
Sam
- 473
- 2
- 5
- 13