Stack Overflow
Stack Overflow

Questions tagged [tf-slim]

TF-Slim is a lightweight library for defining, training and evaluating complex models in TensorFlow.

117 questions
2
votes
0 answers

Using CNN on non-image 1-D data

I have a 2-D matrix of dimensions (batch size x 1000). The values are not random and do have meaning in their structure - they are ordered by time. I wanted to try and use a CNN on this data. Is it possible to run a CNN on non-image data such as…
dooder
  • 529
  • 1
  • 6
  • 14
2
votes
1 answer

Neural Network Skip Connections with TF-Slim?

I just have a couple questions regarding neural networks and skip connections: When people say 3-layer NN, that means there is an input layer, a hidden layer, and an output layer right? I can't seem to find many resources/information on skip…
dooder
  • 529
  • 1
  • 6
  • 14
2
votes
2 answers

Tensorflow Slim restore model and predict

I'm currently trying to learn how to use TF-Slim and I'm following this tutorial: https://github.com/mnuke/tf-slim-mnist. Assuming that I already have a trained model saved in a checkpoint, how do I now use that model and apply it? Like, in the…
asker
  • 167
  • 1
  • 3
  • 9
2
votes
3 answers

Tensorflow neural network loss value NaN

I'm trying to build a simple multilayer perceptron model on a large data set but I'm getting the loss value as nan. The weird thing is: after the first training step, the loss value is not nan and is about 46 (which is oddly low. when i run a…
dooder
  • 529
  • 1
  • 6
  • 14
2
votes
2 answers

Creating a Slim classifier using pretrained ResNet V2 model

I am trying to create an image classifier that utilizes the pre-trained ResNet V2 model provided in the slim documentation. Here is the code so far: import tensorflow as tf slim = tf.contrib.slim from PIL import Image from inception_resnet_v2 import…
Zaid Amir
  • 4,727
  • 6
  • 52
  • 101
2
votes
0 answers

What is the difference between two tensorflow inception models 'inception_v3_2016_08_28.tar.gz' and 'classify_image_graph_def.pb'?

I have tried both the tensorflow models for tranfer learning. The models are inception_v3_2016_08_28.tar.gz - from tensorflow-models classify_image_graph_def.pb - comes along with tensorflow image_retraining code. But the results i am getting are…
Nirmal Jith
  • 39
  • 7
2
votes
2 answers

How to get misclassified files in TF-Slim's eval_image_classifier.py?

I'm using a script that comes with TF-Slim to validate my trained model. It works fine but I'd like to get a list of the misclassified files. The script makes use of…
bamboofighter
  • 299
  • 1
  • 14
2
votes
0 answers

Training Inception V3 using tensorflow slim on multiple machines with CPUs only

I'm trying to use the tf-slim library to train Inception V3 using multiple machines which do not have GPUs. I'm following the tutorial given here: https://github.com/tensorflow/models/tree/master/slim. I can train using a single CPU only machine but…
Darshan
  • 181
  • 1
  • 10
2
votes
2 answers

Interleaving slim.dropout and slim.fully_connected in slim.stack?

In tf.slim, I'd like to create a stack of fully-connected layers with dropout. To the example from documentation: slim.stack(x, slim.fully_connected, [32, 64, 128], scope='fc'), I'd like to add dropout. Is it possible to use slim.stack or do I have…
mkbubba
  • 61
  • 6
2
votes
1 answer

What is the difference between saving a summary and saving the model in the logdir?

Using Tensorflow (tf.contrib.slim in particular) we are required to calibrate a few parameters to produce the graphs that we want at tensorboard. Saving a summary interval is more clear for us what it does. It saves the value (or an average of…
George Pligoropoulos
  • 2,919
  • 3
  • 33
  • 65
2
votes
1 answer

Error loading saved checkpoint in TFSlim

Using v0.12.1 version of tensorflow, I'm trying to finetune a pre-trained vgg16 model using checkpoint available at http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz. I'm getting the following errors: W…
HuckleberryFinn
  • 1,489
  • 2
  • 16
  • 26
2
votes
0 answers

TensorFlow: Do we exclude a scope or operation when we fine-tune certain layers of a pre-trained model?

I'm quite confused about what a scope or operation means when I'm referring to a layer of a network. If I want to fine-tune the last softmax layer of the network, do I go to the scope, the operation or the variables to work on it? What are the…
kwotsin
  • 2,882
  • 9
  • 35
  • 62
2
votes
1 answer

AttributeError: module 'tensorflow.contrib.slim' has no attribute 'nets'

I want to use the built in resnet in tf-slim for a quick experiment. I did according to the README in github: import tensorflow as tf import tensorflow.contrib.slim as slim resnet = tf.contrib.slim.nets.resnet_v1 mnist =…
southdoor
  • 431
  • 1
  • 8
  • 22
2
votes
0 answers

Unable to freeze inception v1 (tf-slim) graph

After successfully running all examples from slim walkthrough notebook, I wanted to freeze the graph. In order to do that, I ran the following (copy from original notebook): import os from datasets import flowers from nets import inception from…
Niko Gamulin
  • 66,025
  • 95
  • 221
  • 286
2
votes
2 answers

Two training ops for slim.learning.train (TensorFlow, TF-Slim)

Some architectures require two or more training ops (for example, in GAN you need to train a generator and discriminator). How can you achieve that with TF-Slim training functions? As far as I can see slim.learning.train takes only one training op.
Andrew Brown
  • 63
  • 7
1 2
3
4 5 6 7 8