TF-Slim is a lightweight library for defining, training and evaluating complex models in TensorFlow.
Questions tagged [tf-slim]
117 questions
0
votes
1 answer
InceptionV4 and V2 giving low accuracy on "flower dataset" than InceptionV1
I am using the following code to train flower dataset on InceptionV1. This code is provided Here
import os
from datasets import flowers
from nets import inception
from preprocessing import inception_preprocessing
slim = tf.contrib.slim
image_size…
Asad
- 1
- 2
0
votes
0 answers
slim.conv2d does not seem to respect the reuse flag
If I understand variable_scope correctly, then the following code would be expected to throw an error:
with tf.variable_scope('f', reuse=True):
slim.conv2d(x, 128, 7)
since reuse is set to True. However, it does not. I also tried:
with…
Jack Valmadre
- 888
- 7
- 23
0
votes
1 answer
tf.contrib.slim.get_variables_to_restore() does not return value
Running below code tf.contrib.slim.get_variables_to_restore() return empty value [] for all_vars, and then causing failure when calling tf.train.Saver. Detail error message shows below.
Am I missing anything?
>>> import tensorflow as tf
>>>…
Morgan Du
- 61
- 1
- 7
0
votes
1 answer
TF-Slim: (Unreasonable?) running out of memory
I am trying to run one of the tutorials in TF SLIM, the one where you fine tune the flowers dataset using Inception-V3 (~104Mb). The GPU has about 2Gb of memory. When I have a batch size more than 8, I get an error because the GPU runs out of…
Stratis
- 1
- 1
0
votes
1 answer
Classifying images using pre-trained (Tensorflow) CNN
I have trained alexnet_v2 on my own dataset, and now would like to use it within another application. This should be very simple and I've tried to implement it in a number of ways but either I get errors I can't work around or (in the case of the…
Loz
- 136
- 2
- 9
0
votes
1 answer
Using Tensorflow.slim to apply convolution2d_transpose
I am trying to apply 2 convolutional layers with the tf.slim.conv2d function, they basically reduce the size of my input image by half each time. Then I want to apply the convolution2d_transpose to get my original image shape back. The problem is I…
Qubix
- 4,161
- 7
- 36
- 73
0
votes
1 answer
TensorFlow: slim training loop crashing "No session factory registered"
I have a working TF installation and slim works fine, too.
However, when I try to run a slim training loop, my app crashes.
Minimal code:
import tensorflow as tf
import tensorflow.contrib.slim as slim
# Load data.
...
graph = tf.Graph()
with…
Phil
- 43
- 5
0
votes
1 answer
tensorflow slim inception_v3 model error
I am trying to use the tensorflow inception_v3 model for a transfer learning project.I get the following error on building the model.
TypeError: Expected int32, got list containing Tensors of type '_Message' instead.
The same error does not arise on…
Ashish Kumar
- 23
- 6
0
votes
1 answer
Image classification by small object
I'm trying to participate in a challenge for classifying dashboard camera images (for car) with labels being -traffic light red / green / non-existent. Traffic lights are small part of the image, and no bounding box is supplied.
I'm trying to…
Alon Burg
- 2,500
- 2
- 27
- 32
0
votes
2 answers
Showing Labels When Evaluating TensorFlow-Slim
I am teaching myself TensorFlow and am currently experimenting with different models for image classification in the tensorflow/models/slim repo. Following the tutorial there, I have fine-tuned a pre-trained inception_v2_resnet model and am trying…
osama
- 622
- 2
- 10
- 19
0
votes
1 answer
Tensorflow Slim : Significance of Different versions
I am trying to use tf slim library for building model on top of inception-v3 model
The tf slim library uses a version 'import tensorflow.contrib.slim as slim'
wheras the inception model uses 'from inception.slim import slim'
both the versions have…
Ashish Kumar
- 23
- 6
-3
votes
1 answer
Transfer learning tersoflow
I'm trying to follow this tutorial enter link description hereon transfer learning, I used my own dataset , and I'm trying to use MobileNet instead to inception , the problem is in the MobileNet models there are 3 checkpoint…
