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
17
votes
3 answers

TensorFlow: does tf.train.batch automatically load the next batch when the batch has finished training?

For instance, after I have created my operations, fed the batch data through the operation and run the operation, does tf.train.batch automatically feed in another batch of data to the session? I ask this because tf.train.batch has an attribute of…
kwotsin
  • 2,882
  • 9
  • 35
  • 62
11
votes
3 answers

How to use evaluation_loop with train_loop in tf-slim

I'm trying to implement a few different models and train them on CIFAR-10, and I want to use TF-slim to do this. It looks like TF-slim has two main loops that are useful during training: train_loop and evaluation_loop. My question is: what is the…
Alex Sax
  • 723
  • 1
  • 6
  • 10
7
votes
1 answer

Tensorflow slim pre-trained alexnet

The Tensorflow slim library provides the graph structure for alexnet, however it doesn't seem to provide a pre-trained (on Imagenet) alexnet checkpoint (https://github.com/tensorflow/models/tree/master/research/slim). Is there anywhere a pre-trained…
h1234s
  • 87
  • 1
  • 3
6
votes
1 answer

tf-slim batch norm: different behaviour between training/inference mode

I'm attempting to train a tensorflow model based on the popular slim implementation of mobilenet_v2 and am observing behaviour I cannot explain related (I think) to batch normalization. Problem Summary Model performance in inference mode improves…
DomJack
  • 4,098
  • 1
  • 17
  • 32
6
votes
1 answer

Reusing layer weights in Tensorflow

I am using tf.slim to implement an autoencoder. I's fully convolutional with the following architecture: [conv, outputs = 1] => [conv, outputs = 15] => [conv, outputs = 25] => => [conv_transpose, outputs = 25] => [conv_transpose, outputs = 15] =>…
Qubix
  • 4,161
  • 7
  • 36
  • 73
6
votes
1 answer

TFSlim - problems loading saved checkpoint for VGG16

(1) I'm trying to fine-tune a VGG-16 network using TFSlim by loading pretrained weights into all layers except thefc8 layer. I achieved this by using the TF-SLIm function as follows: import tensorflow as tf import tensorflow.contrib.slim as…
HuckleberryFinn
  • 1,489
  • 2
  • 16
  • 26
5
votes
1 answer

Geting ERROR: Config value cuda is not defined in any .rc file when trying to train mobilenet in tensorflow

I'm trying to run MobileNet_v1 on ImageNet and for that I'm using the official Tensorflow Model repository and following their guide. However when I actually tried to run the training for MobileNet_v1 by first initiating : models/research/slim$…
Hossein
  • 24,202
  • 35
  • 119
  • 224
5
votes
1 answer

Using pre-trained Inception_v4 model

https://github.com/tensorflow/models/tree/master/slim This gives download link for checkpoints for Inception v1-4 pretrained models. However, the tar.gz contains only the .ckpt file. In the tutorial on using Inception v3 2012 [This link], the tar.gz…
megan adams
  • 355
  • 1
  • 6
  • 10
4
votes
3 answers

Decoding tfrecord with tfslim

I use Python 2.7.13 and Tensorflow 1.3.0 on CPU. I want to use DensNet( https://github.com/pudae/tensorflow-densenet ) for regression problem. My data contains 60000 jpeg images with 37 float labels for each image. I saved my data into tfrecords…
Hosein
  • 81
  • 1
  • 6
4
votes
0 answers

Training ResNetv1 From Scratch using Tensorflow Slim

Although it is stated in the slim model that train_image_classifier.py can be used to train models from scratch, I found it hard in practice. In my case, I am trying to train ResNet from scratch on a local machine with 6xK80s. I used…
Amirreza Shaban
  • 41
  • 3
4
votes
1 answer

TensorFlow Data Starved GPU

I need help optimizing a custom TensorFlow model. I have a 40GB ZLIB compressed .TFRecords file containing my training data. Each sample consists of two 384x512x3 images and a 384x512x2 vector field. I am loading my data as follows: num_threads…
Sam P
  • 1,821
  • 13
  • 26
4
votes
1 answer

Using Tensorflow TF-Slim without slim.learning.train()

TF-Slim uses its own training loop. However, I would like to use a TF-Slim model (Resnet50) while still using my own tensorflow training loop. The TF-Slim model simply outputs the prediction and I calculate my own total loss. I am able to train the…
user3142067
  • 1,222
  • 3
  • 13
  • 26
4
votes
3 answers

How can I I initialize the weights in slim.conv2d() with the value of existing model

I use slim.conv2d to set up VGG-net with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME'): conv1_1 = slim.conv2d(img, 64, [3, 3], scope='conv1') conv1_2 = slim.conv2d(conv1_1, 64, [3, 3], scope='conv1_1') pool1 =…
Frank Mouzrt
  • 57
  • 1
  • 5
4
votes
3 answers

Tensorflow (tf-slim) Model with is_training True and False

I would like to run a given model both on the train set (is_training=True) and on the validation set (is_training=False), specifically with how dropout is applied. Right now the prebuilt models expose a parameter is_training that is passed it the…
Alex Rothberg
  • 10,243
  • 13
  • 60
  • 120
3
votes
0 answers

Inception_v3 finetuning : Running model failed: Not found: FeedInputs: unable to find feed output input

I am trying to fine tune inception_v3 model for reduced number of custom classes. I followed example script finetune_inception_v3_on_flowers.sh to retrain the model. Retraining script generated list of .data, .meta and .index files. I am also able…
pragnesh
  • 1,240
  • 7
  • 18
1
2 3 4 5 6 7 8