Deep Learning Tutorial With Python, Tensorflow & Keras – Neural Network For Image Classification




[ad_1]

Learn to build first neural network in keras and python using keras fashion mnist datasset. We will learn keras sequential model and how to add Flatten and Dense layers into it for image classification problem. In the end we have an exercise for you to solve.
#DeepLearningTutorial #Tensorflow #Keras

https://github.com/codebasics/py/blob/master/DeepLearningML/1_keras_fashion_mnist_neural_net/1_keras_fashion_mnist.ipynb

Next Video:
3. Deep Learning Tutorial (Tensorflow2.0, Keras & Python) – Movie Review Classification: https://www.youtube.com/watch?v=xU-ZQSxtGaA&list=PLeo1K3hjS3uvCeTYTeyfe0-rN5r8zn9rw&index=17

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

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 18, 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 18, 2020

    is there any tutorial on gist descriptor ?

  • codebasics
    November 18, 2020

    sir can get the models in git hub can u please send the link

  • codebasics
    November 18, 2020

    code basics can you how to download the tensor flow it will be easy for others and will useful
    so I am not asking for myself but asking for my friend😅

  • codebasics
    November 18, 2020

    sir, I have a doubt. I have installed keras and restarted the kernel too, but it is showing 'Name Error', keras is not defined. please help me

  • codebasics
    November 18, 2020

    thank a lot for clear explanation

  • codebasics
    November 18, 2020

    plz hindi me

  • codebasics
    November 18, 2020

    Import error: could not find DLL

  • codebasics
    November 18, 2020

    sir with epochs=10,neurons=200……… i got this score [0.13948381552211941, 0.9591000080108643]

  • codebasics
    November 18, 2020

    what is the difference between compilation and fitting the model

  • codebasics
    November 18, 2020

    sir why only normalize the x_test and x_train why not normalize the y_train,y_test and what is the use of this normalization

  • codebasics
    November 18, 2020

    Hi Sir, the array values of X_train and X_test ranged from 0 to 255. What was the benefit of normalizing the values by dividing by 255?

  • codebasics
    November 18, 2020

    I am getting this error "error: Error -3 while decompressing data: invalid distance too far back" on this statement "(x_train, y_train), (xtest, ytest)=fashion_mnist.load_data()" If anyone knows please help

  • codebasics
    November 18, 2020

    Accuracy = 0.957
    dense=60
    epochs=10

  • codebasics
    November 18, 2020

    I got 97,11% with 300 hidden layers and relu activation

  • codebasics
    November 18, 2020

    from keras.models import Sequential

    from keras.layers import Dense,Activation,Flatten

    model=Sequential()

    model.add(Flatten(input_shape=[28,28]))

    model.add(Dense(100,activation='relu'))

    model.add(Dense(100,activation='relu'))

    model.add(Dense(10,activation='softmax'))
    ACCURACY=97.6%

  • codebasics
    November 18, 2020

    87% with 200 hidden layer and relu activation

  • codebasics
    November 18, 2020

    How can i give custom input, like i give it a pic of my shirt and ask it to predict it?

  • codebasics
    November 18, 2020

    Please continue your Great Deep Learning Tutorial Series! If it is not possible due to your health issues, request you to suggest currently available a book/online course (Similar to yours) on "Deep Learning for Absolute Beginners". It will be a great help!

  • codebasics
    November 18, 2020

    I am getting prediction array as array([1., 0., 0.,…]) i want in scientific notation eg. 3.424e-07. What should I do ?

  • codebasics
    November 18, 2020

    Thanks a lot for your explanation, really your effort is appreciated

    I have some questions, now we are just applying for two databases one train and one test, how to insert and test my own data that i want the code to test? can we make it?
    should we make a new database for that?
    can that database renew itself once i add new data?
    >>>>
    also for the last line i have found that we used the function np.argmax[xxx]
    i have tried argmin to check what will happen and i found it gave me the number 6 not the targeted number 7
    should we use "argmax" because it is related to the accuracy percentage which is max 1.00?
    >>>>
    Thanks

  • codebasics
    November 18, 2020

    Wow Crystal Clear Explanation

  • codebasics
    November 18, 2020

    You are amazing Bro!!!

  • codebasics
    November 18, 2020

    How to find the param for different layers??
    Eg: for dense 1: params: 15700

  • codebasics
    November 18, 2020

    %matplotlib not running

  • codebasics
    November 18, 2020

    Sir, just wanted to ask

    in this dataset, there are various variety of data, there can be some image which is in train set, is not available in test set, or vice versa, in that case, wouldn't it lead to less accuracy? For that we will have to use K Fold cross validation? Please let me know if i am wrong in this

  • codebasics
    November 18, 2020

    For those who are running into issues with 'No module named 'keras'' or conflict between pipenv/tensorflow. Here is the docker method:
    – install docker desktop from here: https://docs.docker.com/install/
    – once installed and logged in, enter in terminal: docker run -it -p 8888:8888 tensorflow/tensorflow:nightly-py3-jupyter
    – docker will install a bunch of things and give you a link to enter in browser
    – link shows jupyter notebook folder with all tensorflow tutorials pre-installed. You can delete them.
    – create a new notebook as usual and you might have to skip the explicit keras import and use tf datasets directly

Write a comment