All Questions
18
questions
7
votes
1
answer
21k
views
Unable to train my keras model : (Data cardinality is ambiguous:)
I am using the bert-for-tf2 library to do a Multi-Class Classification problem. I created the model but training throws the following error:
-----------------------------------------------------------...
- 669
4
votes
1
answer
3k
views
Difference between Tokenizer and TextVectorization layer in tensorflow
New to TensorFlow
I saw couple of small NLP projects where people use the 'tf.keras.preprocessing.Tokenizer' to pre-process their text (link: https://www.tensorflow.org/api_docs/python/tf/keras/...
- 71
3
votes
1
answer
3k
views
How to make custom validation_step in tensorflow 2 Tensorflow 2 / Keras?
I have a question regarding the validation Data.
I have this neural network and I divided my data into train_generator, val_generator, test_generator.
I made a custom model with a custom fit.
class ...
- 53
3
votes
1
answer
1k
views
How to normalize output from BERT classifier
I've trained a BERT classifier using HuggingFace transformers.TFBertForSequenceClassification classifier. It's working fine, but when using the model.predict() method, it gives a tuple as output which ...
- 4,498
2
votes
2
answers
5k
views
error Node: 'binary_crossentropy/Cast' Cast string to float is not supported while train model
i want to train my data i already make my data to string with word2vec pretrain model from here https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.id.300.vec.gz and success to make a model, but ...
- 35
2
votes
1
answer
153
views
Parallel Convolutions using Keras
What i am trying to do is create a text classification model which combines CNNS and word embeddings.The basic idea is that we have an Embedding layer at the start of the network and then 2 parallel ...
- 21
2
votes
1
answer
125
views
I have trained a custom transformer model on language modeling, now how do I make predictions with it?
I have trained a transformer model on language modeling (i.e predicting the next character given the context) on a dataset. CONTEXT_LENGTH = 200, I want the model to predict when the input is not of ...
- 49
2
votes
1
answer
1k
views
Tensorflow loading weights on CPU when model is trained on GPU
I wrote a Bert model in Colab and I trained it using GPU and downloaded the weights for further inference. For prediction, I don't need GPU and I was testing on my local machine without GPU. But I was ...
- 110
1
vote
2
answers
483
views
TF predict multiple predictions at once
I am trying to batch predict a number of inputs to my model which expects an input containing 2 1D lists of a fixed size like this:
[<tf.Tensor: shape=(1, 150), dtype=int64, numpy=array([[2, 924, ....
- 176
1
vote
0
answers
170
views
Transformer model using functional API
I started learning NLP a couple of months ago. So now i am trying to implement transformer model using functional API and i want to train this transformer model using model.fit. Encoder and Decoder ...
- 11
1
vote
1
answer
502
views
The problem with tf.keras.datasets.imdb.load_data
from keras.datasets import imdb
(X_train, y_train), (X_test, y_test) = imdb.load_data(path="imdb.npz",
num_words=10,
...
- 75
0
votes
1
answer
927
views
ModelCheckpoint not saving checkpoint files (.h5 files)
model = Model(sequence_input, preds)
adadelta = tf.keras.optimizers.Adadelta(lr=0.9, rho=0.95, epsilon=None, decay=0.002)
lr_metric = get_lr_metric(adadelta)
model.compile(loss='...
0
votes
1
answer
160
views
BERT to XLNET train model
I'm trying to do something like this in XLNet but I can't find this part in the documentation, any help would be valuable, thanks!
# we access the transformer model within our bert object using the ...
- 113
0
votes
0
answers
20
views
Vanishing Gradient in Keras Spelling Correction Model
I'd like some help with the following problem.
I'm working on a spelling correction model using Tensorflow (Keras). I'm using "binary accuracy" and "accuracy" as my metrics. ...
- 11
0
votes
0
answers
71
views
Predicting the next word using KerasNLP
I'm using KerasNLP to generate next sequence and predicting the next word. For that, I'm following Colab. I'm getting trouble in converting the logits into tokens & words. So here is the summary ...
- 2,790
0
votes
0
answers
7
views
Tensorflow Keras InvalıdArgumentError
I tried to develop a simple chatbot with seq2seq architecture and it gave the following error that I could not solve.
Code :
import tensorflow as tf
import numpy as np
from tensorflow.keras.models ...
- 13
0
votes
1
answer
464
views
Tensorflow Keras load_model does not load the Model anymore after updating from tf 2.7
After Updating from tf 2.7 to any higher tensorflow version (i have tested them all), the loading of my previously trained models does not work anymore. When I downgrade Tensorflow the imports work ...
- 134
-1
votes
1
answer
87
views
loss value deep learning model is inf
I train a RNN deep learning model as bellow:
model = Sequential()
initializer = tf.keras.initializers.RandomNormal(mean=.5, stddev=1)
model.add(LSTM(512, return_sequences=True, dropout=0.2,input_shape=...
- 1