python (65.1k questions)

javascript (44.2k questions)

reactjs (22.7k questions)

java (20.8k questions)

c# (17.4k questions)

html (16.3k questions)

r (13.7k questions)

android (12.9k questions)

Questions - tensorflow

tensorflow 2 use keras.sequence as data generator for training machine learning model with multiprocessing error

I would like to do a test about training a machine learning model on EC2 instance with only CPUs from jupyter notebook. The code is tensorflow 2.8. Based on the tf doc, https://www.tensorflow.org/api_...
test-img

user3448011

python

tensorflow

machine-learning

keras

tensorflow-datasets

Votes: 0

Answers: 1

Latest Answer

If you want to parse / deserialize a tf.train.Example, you have to serialize it first by creating a protobuf string. Otherwise it makes no sense. Here is an example: import tensorflow.keras as keras i...
test-img

AloneTogether

how to pad sequences in a tensor slice dataset in TensorFlow?

I have a tensor slice dataset made from two ragged tensors. tensor_a is like: <tf.RaggedTensor [[3, 3, 5], [3, 3, 14, 4, 17, 20], [3, 14, 22, 17]]> tensor_b is like: <tf.RaggedTensor [[-1, 1,...
test-img

pieckannie

python

tensorflow

padding

ragged-tensors

Votes: 0

Answers: 1

Latest Answer

You could try something like this: import tensorflow as tf tensor_a = tf.ragged.constant([[3, 3, 5], [3, 3, 14, 4, 17, 20], [3, 14, 22, 17]]) tensor_b = tf.ragged.constant([[-1, 1, -1], [-1, -1, 1, -...
test-img

AloneTogether

Serialize TF graph after XLA compilation

I was wondering if there is a way to serialize a TF graph after compiling with XLA. Typically we can serialize a graph as a proto file and load it afterwards. However, the graph execution is slow the ...
test-img

photon1981

tensorflow

Votes: 0

Answers: 0

keras pad_sequence and Tokenizer

i learn on kaggle dataset Here to practice on nlp i have an error when i tokenize the tweets and go to padding them i got an error i search for an solution but i don't get answer # Get tha max Numbe...
test-img

Ahmed Soliman

python

tensorflow

keras

nlp

tokenize

Votes: 0

Answers: 1

Latest Answer

The problem is that LENGTH is not an integer but a Pandas series. Try something like this: from sklearn.model_selection import train_test_split import pandas as pd import tensorflow as tf df = pd.Da...
test-img

AloneTogether

Posts

Questions

Blogs

Jobs