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
1
vote
0 answers

what the meaning of slim.metrics.streaming_sparse_average_precision_at_k?

This function refer to tf.contrib.metrics.streaming_sparse_average_precision_at_k,and the explanation in source code is follow,any one can explain it by giving some simply example? And I wonder whether this metric is same as the average precision…
qiushi223
  • 11
  • 4
1
vote
1 answer

tensorflow slim concurrent train and evaluation loops; single device

I am interested in using the tensorflow slim library (tf.contrib.slim) to do evaluation of a model performance on a(n) (entire) test set periodically during training. The documentation is pretty clear that slim.evaluation.evaluation_loop is the way…
user3391229
  • 798
  • 9
  • 17
1
vote
1 answer

Defining a very simple bias initializer in tensorflow

I need to write a simple initializer for my convolutional layer biases. I am using tf.slim so I can specify the initializer when calling the convolutional layer, like so. I want to replace the biases_initializer=init_ops.zeros_initializer() with my…
Qubix
  • 4,161
  • 7
  • 36
  • 73
1
vote
2 answers

Image centering in ResNet-50 in tensorflow-slim

I am using ResNet-50 model in tensorflow-slim to extract features. My question is do I need to centre the images according to some standard ResNets-50 mean values before feeding in the images? I know that for vgg-19 tf-slim provides options for…
HIMANSHU RAI
  • 305
  • 1
  • 4
  • 13
1
vote
4 answers

ResNet RGB means in tensorflow-slim

I am using tensorflow slim to load pre-trained models like vgg and resnet-50. So for vgg , tf-slim provides a way to load RGB mean values like: from preprocessing.vgg_preprocessing import (_mean_image_subtraction, …
HIMANSHU RAI
  • 305
  • 1
  • 4
  • 13
1
vote
1 answer

How to pass images through TensorFlow-Slim VGG Pre-Trained Net in Batches?

I want to pass the images through the network for a transfer learning task. In the following code I'm building the graph and then getting the outputs of a fully connected layer. I wanted to get the outputs in batches because I have an array with…
Thiago
  • 652
  • 1
  • 9
  • 29
1
vote
1 answer

tfslim "Training a model from scratch." some kind of error occured

i'm training tf slim with https://github.com/tensorflow/models/tree/master/slim training a model form scratch. some kind of error occured i think its kind of gpu and cpu running problem. other codes works fine at me. but this occuring error i run…
Suk Kyu Sun
  • 53
  • 1
  • 5
1
vote
1 answer

decode_jpeg, encode_jpeg type error

I am adapting to my own needs the following code https://github.com/tensorflow/models/blob/master/slim/datasets/download_and_convert_flowers.py I need to add zero-padding and resize the images to 299x299 (inception V3 input size). I am doing this…
user1188243
  • 61
  • 1
  • 5
1
vote
0 answers

Implementing skip/residual layers in tf-slim

I've been trying to figure out how to implement a skip/residual connection using tf-slim but I can't seem to get it. I know that a skip connection basically provides input to, not only the immediate next layer, but also the layer after that. I've…
dooder
  • 529
  • 1
  • 6
  • 14
1
vote
1 answer

How restore training from Inception-3 checkpoint with different trainable variables

I have the pretty common use case of freezing the bottom layers of Inception and training only the first two layers, after which I lower the learning rate and fine tune the entire Inception model. Here is my code for running the first…
Reii Nakano
  • 1,318
  • 1
  • 9
  • 9
1
vote
2 answers

TensorFlow-Slim Multi-GPU training

I'm using TensorFlow-Slim. My aim is to run a given standard script (located in /models/slim/scripts) in multi-GPU mode. I've tested the finetune_resnet_v1_50_on_flowers.sh script (cloned on 12.04.2017). I've just added --num_clones=2 at the end of…
Elternhaus
  • 45
  • 2
  • 9
1
vote
0 answers

How to perform upsampling using the convolution_transpose function ?

I want to use the convolution_transpose function of tf.slim and it seems that, no matter how I choose my kernel size and strides, I cannot get the output of the convolution_transpose layer to be larger than that of the initial convolutional layer.…
Qubix
  • 4,161
  • 7
  • 36
  • 73
1
vote
1 answer

tensorflow TF-slim inceptionv3 training loss curve is strange

TF-slim inceptionv3 train from scratch I use slim/train_image_classifier.py to train a inception_v3 model on my own dataset: python train_image_classifier.py --train_dir=${TRAIN_DIR} --dataset_name=mydataset --dataset_split_name=train…
rickymf4
  • 37
  • 3
1
vote
1 answer

Why is my transfer learning implementation on tensorflow is throwing me an error after a few iterations?

I am using inception v1 architecture for transfer learning. I have downloded the checkpoints file, nets, pre-processing file from the below github repository https://github.com/tensorflow/models/tree/master/slim I have 3700 images and pooling out…
Prakash Vanapalli
  • 677
  • 1
  • 9
  • 16
1
vote
1 answer

How to share a queue containing variable length sequences batches between multiple gpus?

According to Tensorflow: Multi-GPU single input queue, it might be better to have a single queue shared by multiple GPUs. And the link suggested that we could increase the batch size and then split batches by ourselves. However, when the input data…
Meuu
  • 2,023
  • 1
  • 10
  • 7
1 2 3 4
5
6 7 8