3. Deep Learning Tutorial (Tensorflow2.0, Keras & Python) – Movie Review Classification




[ad_1]

Using Tensorflow 2.0, keras and python, this tutorial demonstrates how to build neural network to solve movie review classification problem. We will load imdb movie reviews from tensorflow datasets and then use transfer learning technique to first create an embeding layer using tensorflow hub. This uses popular word2vec for creating embeding vector for an english sentence. After that we build a neural network to classify movie reviews as positive and negative. This deep learning tutorial as for any new begininer who has little under standing of deep learning. Here are the list of topics covered in this machine learning video,
#DeepLearningTutorial #Tensorflow #Keras

Topics that are covered in this Video:

1:30 Word2Vec for embeding words into a vector
5:03 Overview of neural network architecture for movie review classification
6:27 Google colab overview (It is cloud based jupyter notebook)
8:41 Install tensorflow 2.0 in google colab
13:06 Use tensorflow_datasets to load imdb moview reviews
19:17 tensorflow_hub overview. It uses transfer learning to utilize pre trained neural networks.
23:26 Create neural network using tensorflow.Keras.Sequential
24:55 Train the neural network
27:00 perform classification using trained neural network

Populor Playlist:
Data Science Full Course: https://www.youtube.com/playlist?list=PLeo1K3hjS3us_ELKYSj_Fth2tIEkdKXvV

Data Science Project: https://www.youtube.com/watch?v=rdfbcdP75KI&list=PLeo1K3hjS3uu7clOTtwsp94PcHbzqpAdg

Machine learning tutorials: https://www.youtube.com/watch?v=gmvvaobm7eQ&list=PLeo1K3hjS3uvCeTYTeyfe0-rN5r8zn9rw

Pandas: https://www.youtube.com/watch?v=CmorAWRsCAw&list=PLeo1K3hjS3uuASpe-1LjfG5f14Bnozjwy

matplotlib: https://www.youtube.com/watch?v=qqwf4Vuj8oM&list=PLeo1K3hjS3uu4Lr8_kro2AqaO6CFYgKOl

Python: https://www.youtube.com/watch?v=eykoKxsYtow&list=PLeo1K3hjS3usILfyvQlvUBokXkHPSve6S

Jupyter Notebook: https://www.youtube.com/watch?v=q_BzsPxwLOE&list=PLeo1K3hjS3uuZPwzACannnFSn9qHn8to8

Code: https://colab.research.google.com/drive/1fiNnGSiEsGZHkgnYufFiDBvSsiEOjWo7
Website: http://codebasicshub.com/
Facebook: https://www.facebook.com/codebasicshub
Twitter: https://twitter.com/codebasicshub
Patreon: https://www.patreon.com/codebasics

Source


[ad_2]

Comment List

  • codebasics
    November 25, 2020

    I have started a new and better version of deep learning series from scratch. Please follow this: https://www.youtube.com/playlist?list=PLeo1K3hjS3uu7CxAacxVndI4bE_o3BDtO

  • codebasics
    November 25, 2020

    In this method, Text pre processing like stemming,stopwords etc not required to perform?
    Please help sir

  • codebasics
    November 25, 2020

    As you told we need to get answer near to 0 for bad review and answer near to 1 for good review but I am getting this

    model.predict(["crap movie"])
    array([ [-2.792048]], dtype=float32), getting negative numbers for bad reviews.

    model.predict(["beautiful film"])
    array([ [2.9461546]], dtype=float32), getting positive numbers for good reviews please help tried everything unable to understand what to do.

  • codebasics
    November 25, 2020

    How to write this project on resume. Please help

  • codebasics
    November 25, 2020

    I am getting error in the below codes:

    model=tf.Keras.sequential()

    model.add(hub_layer)

    model.add(tf.keras.layers.Dense(16, activation='relu'))

    model.add(tf.keras.layers.Dense(1, activation='sigmoid'))

    AttributeError: module 'tensorflow' has no attribute 'Keras'

  • codebasics
    November 25, 2020

    In my Jupiter Notebook Tensorflow and Keras are not in the list. How to install it?

  • codebasics
    November 25, 2020

    I tried saving the model using both joblib and pickle, but that didn't worked for me, so is their any other way to save this model.

  • codebasics
    November 25, 2020

    Say I wanted to use my own data. How would I go about formatting it to be used with a model like this?

  • codebasics
    November 25, 2020

    Please more videos about Deep learning , Great Job

  • codebasics
    November 25, 2020

    What to do after completion of this course?

  • codebasics
    November 25, 2020

    Please learn about CNN,RNN

  • codebasics
    November 25, 2020

    accuracy is 0.96 but while predicting I give "Awesome movie" for this i go this one array([[0.5073642]], dtype=float32) why it is not predicting in good way 0.5 it is not nearer to 1 value

  • codebasics
    November 25, 2020

    Dear Team ,
    Please give such awesome lectures more..

  • codebasics
    November 25, 2020

    Thank you so much for understandable explanation! It was very helpful for me.

  • codebasics
    November 25, 2020

    I am using Jupyter Notebook, while running the below line i got an Error "[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate"

    hub_layer = hub.KerasLayer(pre_trained_model, input_shape=[], dtype=tf.string, trainable=True)
    Can anyone please suggest ?

  • codebasics
    November 25, 2020

    Sir, please make more videos on Deep Learning

  • codebasics
    November 25, 2020

    Everything which is said to be discussed later is never gonna be discussed. LMAO

  • codebasics
    November 25, 2020

    sir please upload video on Adam optimizer

  • codebasics
    November 25, 2020

    Thank you!

  • codebasics
    November 25, 2020

    Sir, I hope you're health is fine now. You seem very well. Are there any chances of you making a playlist for Deep learning tutorials?

  • codebasics
    November 25, 2020

    PROBLEM : same code run in my colab for many times but it show "AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60])"
    SOLUTION : train_data, validation_data, test_data = tfds.load(name="imdb_reviews",split=('train[:60%]', 'train[60%:]', 'test'), as_supervised=True)

  • codebasics
    November 25, 2020

    sir, i am working on project of tweet sentiment analysis, there is previously given train and test csv file. how to give approach and there is no need of train_test_split method.

  • codebasics
    November 25, 2020

    Sir, I have seen some of videos on Data Structures. Request you to provide us comprehensive Deep Learning and Machine Learning before starting new video series on new subject. Your videos are making us subject much more easier. Keep it up

  • codebasics
    November 25, 2020

    Thank you, brother. This tutorial was amazing. Although TensorFlow banned Iranian people from entering the website, Indian people like you help people around the world to access the data freely.

  • codebasics
    November 25, 2020

    Getting error on 15:53. AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60]). I am using Tensorflow 2.1.0

  • codebasics
    November 25, 2020

    Dear sir,
    When downloading datasets on colab does it consume my internet or it gets downloaded on the colab VM and hence saves my internet consumption too?

  • codebasics
    November 25, 2020

    same code run in my colab for many times but it show "AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60])" , tried many times but can't solve this problem

  • codebasics
    November 25, 2020

    wherever I'm trying subsplit, I'm Getting this error

    AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60])
    anything in particular that i'm missing?, I tried the code exactly as you've shown in this tutorial

  • codebasics
    November 25, 2020

    I am getting this error after executing the code at 16:10 . I am unable to find the solution to it. Please help
    AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60]) site:stackoverflow.com

  • codebasics
    November 25, 2020

    I'm getting

    AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60])

    when I try to execute
    (train_data, validation_data), test_data = tfds.load(name='imdb_reviews',

    split=(tfds.Split.TRAIN.subsplit([6,4]),tfds.Split.TEST),

    as_supervised=True)

    I'm using TF version '2.1.0' on google colab. Pls. let me know f you've any suggestions to resolve this error. Thanks,

  • codebasics
    November 25, 2020

    sir can you make video on NLP all real life topic. most of company want that type of knowledge that why i am asking. NLP series

  • codebasics
    November 25, 2020

    Step by step guide on how to learn data science for free: https://www.youtube.com/watch?v=Vn_mmOuQkSA
    Machine learning tutorials with exercises:
    https://www.youtube.com/watch?v=gmvvaobm7eQ&list=PLeo1K3hjS3uvCeTYTeyfe0-rN5r8zn9rw

  • codebasics
    November 25, 2020

    Hello. Sir, help me please. When I execute the command (import tensorflow_datasets as tfds), I have a few errors

    1) AttributeError: module 'tensorflow' has no attribute 'keras'
    2) AttributeError: 'AttributeError' object has no attribute '_render_traceback_'
    3) ImportError: DLL load failed: The specified module was not found.
    4) Failed to load the native TensorFlow runtime.

    How to solve this problem?

  • codebasics
    November 25, 2020

    Thank you very much. Can use word2vec to predict the most frequent 10 words that come before a specific word and the most frequent 10 words that come after that specific word? and how?

  • codebasics
    November 25, 2020

    Perfect.. Thank you sir..

    Can we use any deep learning model for predicting classification problems like 'iris dataset'.?

  • codebasics
    November 25, 2020

    Thank you, a great video, the flow is very good and smooth, I wish there was more explanation on some parts (e.g. vector2word, validation set, optimiser, metrics), but I found it really helpful especially it was made by Tensorflow 2. Many thanks

  • codebasics
    November 25, 2020

    Sir kindly make video on autoencoder

  • codebasics
    November 25, 2020

    great explanation sir i tried the code its great

  • codebasics
    November 25, 2020

    Please complete more tutorials on deep learning (image classification)

  • codebasics
    November 25, 2020

    I am really relieved after watching this video after so long

  • codebasics
    November 25, 2020

    Sir please guide me regarding clustering using deep learning on graphs please sir suggest me ….it's urgent

  • codebasics
    November 25, 2020

    Nice content… If I want to reuse full/part of your content from this video in my session/presentation, How do I get in touch with you to get permission? Can you send details to: vrthatha2016@gmail.com. Thanks a lot

  • codebasics
    November 25, 2020

    can you also make a video how to use word2vor in search option in particular database or suggest me how to do it

  • codebasics
    November 25, 2020

    really appreciate your updates. thanks a lot man

  • codebasics
    November 25, 2020

    Please share your contact details

  • codebasics
    November 25, 2020

    Waitng for your next video

  • codebasics
    November 25, 2020

    Nice to have you back sir, Please continue the series ,Eagerly waiting for topics like CNN,RNN,LSTM . You are the best .

  • codebasics
    November 25, 2020

    I want a suggestion from you!
    I have to learn CNN in deep learning from scratch I have tried to search a lot of resources but they were all for intermediate or PRO…..can you suggest me any youtube channel, or book or any website where i can learn this topic

Write a comment