ktrain is a lightweight python wrapper for the deep learning library TensorFlow Keras (and other libraries) to help build, train, and deploy neural networks and other machine learning models. Github: https://github.com/amaiya/ktrain
Questions tagged [ktrain]
25 questions
2
votes
3 answers
BERT Multi-class Sentiment Analysis got low accuracy?
I am working on a small data set which:
Contains 1500 pieces of news articles.
All of these articles were ranked by human beings with regard to their sentiment/degree of positive on a 5-point scale.
Clean in terms of spelling errors. I used…
Xu Wang
- 21
- 4
2
votes
1 answer
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()||| Ktrain| BERT
need your support...I am following one tutorial and trying to run on my dataset. I am getting below error ...Pls consider me a beginner so I would appreciate if you can let me know how to fix and what is the reason?
(x_train_bert, y_train_bert),…
Kevin
- 21
- 6
1
vote
1 answer
How to load a model on local system for testing it on data
I have trained a model on google colab and saved it using the save function. How do I load this model on my local system for testing this model on the data I have?
.....
# Trained a model and ran it for some…
Ujjwal Karnani
- 27
- 4
1
vote
1 answer
Unable to import ktrain due to ImportError: DLL load failed while importing defs: The specified procedure could not be found
Below is the error that I got when I am trying to import ktrain.
---------------------------------------------------------------------------
ImportError Traceback (most recent call…
Ming Jun Lim
- 134
- 2
- 12
1
vote
2 answers
!pip install ktrain errors
I am trying to install the ktrain package in Python (Using Jupyter Notebook) and I get a huge set of errors every time. I am on a Windows 10 laptop (if that contributes).
As of now, my code in jupyter has only had one line:
!pip install ktrain
I…
Parv Joshi
- 11
- 3
1
vote
1 answer
Can not predict on Front end streamlit with ktrain model, kindly provide suggestions about how to provide input for predict function
Can not predict on Front end streamlit with ktrain model, kindly provide suggestions about how to provide input for predict function.
basically I would like to understand how to provide input for my saved ktrain regression model so that I can…
user13227382
1
vote
1 answer
distillbert ktrain 'too many values to unpack'
I am trying to run DistilBert with ktrain in Colab but I am getting "error too many values to unpack". I am trying to perform toxic comment classification, I uploaded 'train.csv' from CivilComments, I am able to run BERT but not…
semper pi
- 11
- 2
1
vote
1 answer
Solve Speed Difference in ktrain Predictor vs. Learner prediction?
I am using ktrain huggingface library to build a language model. When implementing it for production, I noticed, there is a huge difference in speed for a "learner prediction" vs. a "predictor prediction".
How come and is there any way to speed up…
Jasper Schwenzow
- 21
- 4
1
vote
2 answers
Facing Error while importing ktrain that tensorflow has not attribute named swish
While importing ktrain, I am getting the following error:
AttributeError: module 'tensorflow_core.keras.activations' has no attribute 'swish'
Can anyone please help and tell how to get it going?
The same works fine on google colab.
Full…
Anmol Gupta
- 21
- 5
1
vote
1 answer
How to use another pretrained BERT model with the ktrain text classifier?
How can we use a different pretrained model for the text classifier in the ktrain library? When using:
model = text.text_classifier('bert', (x_train, y_train) ,
preproc=preproc)
This uses the multilangual pretrained model
However, I want to try…
stacksonoverflow
- 111
- 7
0
votes
0 answers
Increasing epoch length during iterative Resnet model development with Ktrain
I have a script that performs 5-fold cross validation on an image set with the pretrained Resnet50 model using Ktrain, which is just a wrapper for Tensorflow Keras. A model for each fold is trained using 30 epochs, and the CV is repeated 5…
nburner
- 1
0
votes
1 answer
How to take a parameter from a image filename to CNN predictor using regular expression?
I learned how to predict ages of people by the photo. In this situation, the age was the first filename number, and they used regular expression, like this:
import re
pattern = r'([^/]+)_\d+_\d+.jpg$'
p = re.compile(pattern)
r =…
0
votes
1 answer
Can't get 'bert' model to run using ktrain and pandas dataframe
I try to work with ktrain to finetune bert model. I'm using pandas dataframe named train_df to store my data.
x_train, x_val, y_train, y_val = train_test_split(train_df['text'], train_df['target'], shuffle=True, test_size = 0.2,…
ledbug
- 11
- 2
0
votes
1 answer
ValueError: if 'bert' is selected model, then preprocess_mode='bert' should be used and vice versa
I have a problem. I got the following error ValueError: if 'bert' is selected model, then preprocess_mode='bert' should be used and vice versa. But I do not see any problem. What is wrong with my code?
%%time
#Importing
import ktrain
from ktrain…
Test
- 571
- 13
- 32
0
votes
1 answer
How to understand loss-learning rate (log scale) plot using learner.lr_plot in ktrain package?
I am using ktrain package to classify text. My experiment is shown as:
lr_find and lr_plot are functions in ktrain. They can be used to highlight the best learning rate, which is shown as the red dot in the plot.
I do not understand how to…
Feng Chen
- 2,139
- 4
- 33
- 62