Get started with using TensorFlow to solve for regression problems (Coding TensorFlow)




[ad_1]

You often have to solve for regression problems when training your machine learning models. In this episode of Coding TensorFlow, Developer Advocate Robert Crowe discusses how to build and train a TensorFlow model using Keras, where you are looking for the model to solve for a single numerical result – in other words, regression.. Learn how to get started on regression problems, and watch to see an example involving miles-per-gallon. This requires our model to examine and learn from the data we provide, in order to predict our final number. Subscribe to the TensorFlow YouTube channel for more! β†’ http://bit.ly/TensorFlow1

Get the Colab & follow along here β†’ http://bit.ly/2xV8rVg
UCI dataset repository β†’ http://bit.ly/2k2xH8i

Watch more Coding TensorFlow β†’ https://bit.ly/Coding-TensorFlow

Source


[ad_2]

Comment List

  • TensorFlow
    November 12, 2020

    This was so helpful in many ways in my studies. Thank you very much for the easy to understand explanations

  • TensorFlow
    November 12, 2020

    thanks . it's nice to just explain it quick and let people go back in the code and review. I'll check if you have a classification model as well

  • TensorFlow
    November 12, 2020

    Thank you, very well explained

  • TensorFlow
    November 12, 2020

    Why did you choose the z-score to normalise the datasets ?
    I don't understand

  • TensorFlow
    November 12, 2020

    I applied this model to my regression problem. But loss comes to be quite high. How to choose a correct model for my regression problem?

  • TensorFlow
    November 12, 2020

    I learned more from this single video than my entire last semester, looks easy but it has lots of hidden information. Thank you

  • TensorFlow
    November 12, 2020

    i cant give better summary than this in short time. great job! thank you

  • TensorFlow
    November 12, 2020

    How can I calculate the R^2 value?

  • TensorFlow
    November 12, 2020

    great!!! ihave learnt regression more on here

  • TensorFlow
    November 12, 2020

    i want to built ML model for house price prediction using android app what i can do predict the ML model on tensorflow and deploy on android app??

  • TensorFlow
    November 12, 2020

    Awesome, I ran the model in Google Colab using tensorflow 2.2.0

  • TensorFlow
    November 12, 2020

    Great video. Thank you for sharing!

  • TensorFlow
    November 12, 2020

    Splendid lesson, clear lesson. How delicate the way he transmit ideas according python instruction. Love it!

  • TensorFlow
    November 12, 2020

    Great video! Thank you!!!

  • TensorFlow
    November 12, 2020

    This is Awesomeness!!!!

  • TensorFlow
    November 12, 2020

    Hi , Video Series is good. Is Google colab available for R language ?

  • TensorFlow
    November 12, 2020

    How to perform regression in deep neural network for image with corresponding numerical value as input? For example, the ROI in the image has specific biomass. And by using DNN with image as input, the network needs to compute for the biomass value. Thanks in advance!

  • TensorFlow
    November 12, 2020

    while training the model, it's showing NaN values everywhere. How to resolve this?

  • TensorFlow
    November 12, 2020

    why it gives differant output for multiple excecution , even I split data before model bulding () and made shufle= False

  • TensorFlow
    November 12, 2020

    What do I have to write in order to get the model to estimate the MPG consumption of a single car in this case of a single row? Like throwing in cylinder, weight, etc. and getting out the MPG of my Bugatti Veyron. πŸ˜€

    Thanks in advance, Vito.

  • TensorFlow
    November 12, 2020

    Can more than one user work on the same file at the same time on colab, if yes How??

  • TensorFlow
    November 12, 2020

    I didn't get any thing which one we have to do

  • TensorFlow
    November 12, 2020

    great tutorial !
    Can i have the dataset !
    thanks !

  • TensorFlow
    November 12, 2020

    I started with learning Tensorflow, ended looking at 1970-s car videos – how did that happen?

  • TensorFlow
    November 12, 2020

    I'm starting with TensorFlow and the video is amazing, Thanks a lot!

  • TensorFlow
    November 12, 2020

    Requesting to make videos on NLP using TF and Deep Learning.. thank you so much for sharing such wonderful videos.

  • TensorFlow
    November 12, 2020

    When I import data I'm getting shape(19,8) and data is not imported properly, can I import through pandas directly and apply tensorflow?

  • TensorFlow
    November 12, 2020

    i have data set wherein the data tells me who is first each class,, if I provide the hole school data the regression model can predict who comes first in each class or in the school as a hole.

  • TensorFlow
    November 12, 2020

    I believe that there is a conceptual error on the standardization process. One should estimate the population parameters (mean and st.dev.) from the train set only, and then scale new data (test set, in this case) using the training parameters.

  • TensorFlow
    November 12, 2020

    Excellent presentation ! Thank you !

  • TensorFlow
    November 12, 2020

    Maybe its a stupid question, but may I know what is a hot-column?

  • TensorFlow
    November 12, 2020

    where can i get this notebook?
    and.. how does the normalization (standardisation) function even make sense? why the dataframe will match the index of the series automatically?

  • TensorFlow
    November 12, 2020

    Very helpful! Thanks so much!

  • TensorFlow
    November 12, 2020

    when I want to make predictions with other data, now the output is normalized. How can I get a real value as an output?

  • TensorFlow
    November 12, 2020

    Great videos released by a great product like Google Colab. Thank you Google for continuing to push out products and services that are available and widely used by many in different parts of the world

  • TensorFlow
    November 12, 2020

    I'm getting following error. Pls help me:
    On code:def norm(x):
    return (x – train_stats['mean']) / train_stats['std']
    normed_train_data = norm(train_data)
    normed_test_data = norm(test_data)
    Error-I: TypeError: unsupported operand type(s) for -: 'str' and 'float'
    Error-II: UFuncTypeError: ufunc 'subtract' did not contain a loop with signature matching types (dtype('<U32'), dtype('<U32')) -> dtype('<U32')

  • TensorFlow
    November 12, 2020

    actually this was working very slow as compare to my system

  • TensorFlow
    November 12, 2020

    The bit.ly links are already broken Aug 2019. Can you also list the real (unshortened) links? Here is the link to the UCI dataset repository: https://archive.ics.uci.edu/ml/datasets.php but we need you to point to the Colab.

  • TensorFlow
    November 12, 2020

    the best , thank you so much

  • TensorFlow
    November 12, 2020

    Hi, where do I download the notebook from? Please can someone provide a link?

  • TensorFlow
    November 12, 2020

    Hi, I am new to Machine learning . I have a question. what if i have a new data that i want to predict how do i go about doing that? like a new entry that is not in the data set. say i have a new car . maza , 4 clyiner , etc….. what do i do to predict that?

    do i need to make a brand new data like

    brandnew= {maza , 4cylinger)

    model.predict { newdata}?

  • TensorFlow
    November 12, 2020

    I appreciate the tutorial, it is great! I have question just to make sure, so the percentage of data used is 64 : 16 : 20 (Training : Validation : Test)? since the validation split is 0.2 or 20% from training data (which is 80% from total data). thanks in advance πŸ™‚

  • TensorFlow
    November 12, 2020

    You need a better editor for your videos.

  • TensorFlow
    November 12, 2020

    Great! Thanks Robert

  • TensorFlow
    November 12, 2020

    Ignoring a warning just like that? That was odd, coming from TF themselves.

  • TensorFlow
    November 12, 2020

    don't use tf.keras.optimizers when building the optimizer because it's better to use one version of keras instead of one from tensor flow and then regular keras. Stick with one, otherwise, you will get an error like me! Use keras.optimizers!

Write a comment