Stack Overflow
Stack Overflow

Questions tagged [tensorflow-datasets]

TensorFlow's `tf.data` module provides a functional API for building input pipelines, using the `tf.data.Dataset` and `tf.data.Iterator` classes.

1667 questions
0
votes
2 answers

TensorFlow - Error when using interleave or parallel_interleave

I'm using tf.data.Datasets of V1.12 API like this Q&A to read several .h5 files pre-saved batch per file in a directory. I first made a generator: class generator_yield: def __init__(self, file): self.file = file def…
Zézouille
  • 342
  • 2
  • 17
0
votes
1 answer

Face Generation TensorFlow increase size from 28px conv2d_transpose

I am following this tutorial and can successfully generate 28px sized faces using my GPU. However I do not know how to increase the size of the face (currently 28px) with the logic of the generator function below: def generator(z, out_channel_dim,…
Peter R
  • 3
  • 3
0
votes
2 answers

Tensorflow Dataset API - explanation of behavior

Using the code below, I would like to ask a few questions about what exactly is happening underneath. dataset = tf.data.TFRecordDataset(filepath) dataset = dataset.map(parse_function, num_parallel_calls=4) dataset = dataset.repeat() dataset =…
I.D.M
  • 55
  • 5
0
votes
1 answer

How to classify correctly from TENSORFLOW LITE app using INTENT CAMERA?

I tested my fine tuned model using REAL TIME TF-LITE Cllasifier DEMO APP, it showed pretty good results. But when I test same model with Intent Camera Picture ( one at a time ) it shows pretty bad result( 0.06 or 0.04 almost every time ) . I am…
Shehwar Ahmad
  • 57
  • 7
0
votes
1 answer

tensorflow keras fit, input validation data (data, (target1,target2)) ,got error :'expected no data, but got:'

Build a subclassed model with multiple outputs, use tensorflow datasets as input. Custom defined datasets. Use keras fit to train model. When i only use train dataset, it could run. But once i use same type datasets as validation input, it goes…
longlonglong
  • 3
  • 1
0
votes
2 answers

Can I use the same model with different input tensors? Should I avoid running session.run() multiple times?

I'm trying to build a graph with trainining and validation of the same model (fully-connected MLP) without re-running the session, without using feed_dict and using tf.data. Generally, using feed_dict I would define the model with input tensor X and…
JJAlberto
  • 23
  • 5
0
votes
0 answers

How to extend functionalities of a tf.data.TextLineDataset class?

I'm loading a CSV file and I want to customize a tf.data.TextLineDataset to implement a map function depending on the attribute of the class itself. For example, I want to remove the minimum value of the previously drawn items. The only way I have…
JJAlberto
  • 23
  • 5
0
votes
1 answer

How to switch model iterator between train and validate datasets?

I'm learning TensorFlow "lower API", where you manually specify layers using tf.layers, create datasets and iterators, and run the loops to train and validate the model. I am trying to run training and validation. Unfortunately, I am running into…
Michael
  • 5,195
  • 1
  • 28
  • 46
0
votes
1 answer

How to properly build a tensor array dataset from a series of single values - tensorflow newbie

I'm new to tensorflow and the dataset APIs. looks like I'm not feeding the correct lists of dicts to the tensorflow. I get the following output: tensorflow.python.framework.errors_impl.InvalidArgumentError: In[0] is not a matrix. Instead it has…
Constantine Elster
  • 1
  • 1
0
votes
1 answer

Failed to build spark-tensorflow-connector because file already exists

I'm running into an issue when building the spark-tensorflow-connector on GCP's Dataproc. The problem occurs when one of the test fails because of java.lang.IllegalStateException: LocalPath /tmp/spark-connector-propagate7442350445858279141 already…
MajesticKhan
  • 148
  • 1
  • 11
0
votes
0 answers

Dimension error in feeding Keras with Tensorflow dataset

I have a TFRecords file consisting of 60 examples of six Landsat band values for some pixels plus a label for each pixel, and I want to train a Keras classifier with it. But I get a dimension mismatch when I try to load network with the…
Shahriar49
  • 381
  • 2
  • 12
0
votes
1 answer

How To Measure The Performance Of Map Function In Tensorflow's New DataSet API?

I've been using Tensorflow version 1.12 in my GPU instance, I have around 130 TfRecords file containing the ImageNet data which is 1.2 million. First I apply a map function and then flat_map to augment the dataset, which will ultimately be 1.2…
user2906838
  • 1,060
  • 8
  • 18
0
votes
1 answer

Combining flat_map and zip when reading TensorFlow Dataset from multiple files: Are files being read from disk a second time?

Following up on a previous question, I am using tf.data.Dataset.zip(dataset, dataset.skip(1)) to generate a dataset of successive items. I am doing this since I want my model_fn to be fed two successive frames at a time from which it calculates the…
prouast
  • 946
  • 1
  • 8
  • 14
0
votes
1 answer

Are long sentences not good for deep learning models?

Interested to know if long sentences are good for tensor2tensor model training. And why or why not?
echan00
  • 2,506
  • 2
  • 14
  • 25
0
votes
1 answer

Flatten Dataset of multiple files tensorflow

I'm trying to read the CIFAR-10 dataset from 6 .bin files, and then create a initializable_iterator. This is the site I downloaded the data from, and it also contains a description of the structure of the binary files. Each file contains 2500…
ludog
  • 54
  • 1
  • 8
1 2 3
…
99
100