instillai / tensorflow-course Goto Github PK

View Code? Open in Web Editor NEW

16.4K 16.4K 3.2K 21.21 MB

:satellite: Simple and ready-to-use tutorials for TensorFlow

License: MIT License

Python 3.03% Shell 0.02% Jupyter Notebook 96.94%

deep-learning deep-learning-tutorial python tensorflow

tensorflow-course's People

Contributors

Stargazers

Watchers

Forkers

fendaq jibolso kod3r shaoweipng tony32769 ncpope aula-kreasi sarthakveggalam hanmoi-choi dyhpoon jonpojonpo nguyendat disisisid vdt lulzzz allensmile avinassh fuath hbcbh1999 jithinraj ayoubeddafali ashbt jacksu20160407 batermj jiamim iammosespaulr cloverthe leo23 darrenzeng2012 tamjid10 locnguyenhuu josephmisiti quinndiggity 0xedb ramanathanr parampavar harlowja mewbak xbaran bhanug spartakos87 rubenbase devhttps duanshuaimin tspannhw liwenhui19941115 lyrl shabbir-hasan lasmd hhy5277 lihuawu chaoyue729 rvaughan namaljayathunga jshuadvd muratgundes duyduc-nguyen zach14c mehrdad-shokri etherruzo shaunstanislauslau hisashiq astrojose wzwyoyo gbrennon ashsago hack121 ayushghosh raghuvar pielgrin skhobahi wpf535236337 realme27 liucong1001 aancw bronwyn645 zdfccdanfeng lkit57a03 ows-ali mamunhpath vagnercazarotto sittichoke vellancer mmanupriya-korewireless 19ai sinqua steccami waltdisnep fabianobizarro andey-robins faizalpribadi hs5530hs nityaprakash10 noskillguy faviovazquez alexwang815 simpleplan2910 dexter2018 exampg yohanavishke

tensorflow-course's Issues

Spelling Mistakes?

Find a spelling mistake in this doc https://github.com/open-source-for-science/TensorFlow-Course/tree/master/docs/tutorials/1-basics/variables。
Initializing Specific Variables part, the code I think is:

# The initializer
init_custom_op = tf.variables_initializer(var_list=variable_list_custom) # not all_variables_list

Is it right?

Several typos

Convolutional Neural Networks using TensorFlow

"is the one proposed by the paper Understanding the difficulty of training deep feedforward neural networks and provided by the TensorFlow." is repeated twice .

"this layer operates like and filly-connected layer"

"In The outputs of different layers"

ending of tutorial

i think at the end if there is a little about deployment it will become a piece of cake

The version of TensorFlow?

I want to know the version of tf in this repo.
In the 0-welcome, I use tf1.12, and the executed welcome string is bytes.

Typo

There is a typo in this section of README.

'it' to 'its'.

It is not compat with tf2.2

Hi thanks for you tutorials for tf1.x, but It is not compat with tf2.x, can you provide a tutorials for tf2.2 ? Thank you

Math behind every Model

Math behind every model.

Example

Mathematical equations behind Logistic regression
At what point of the implementation those equations are being applied.

compatible with tensorflow 2.0

Is it compatible with tensorflow 2.0? There are some functions of tf1.13 are still used, is there any plan to upgrade the code for tensorflow 2.0?

Linear_SVM wrong norm_term

norm_term = tf.divide(tf.reduce_sum(tf.multiply(tf.transpose(W),W)),2)

should be

norm_term= tf.divide(tf.matmul(tf.transpose(W),W),2)

# Create a callback that saves the model's weights every 5 epochs
checkpointCallback = tf.keras.callbacks.ModelCheckpoint(
    filepath=checkpoint_path, 
    verbose=1, 
    save_weights_only=True,
    save_freq=n_samples_save)

save_freq should be number of epochs(not batches):

# Create a callback that saves the model's weights every 5 epochs
checkpointCallback = tf.keras.callbacks.ModelCheckpoint(
    filepath=checkpoint_path, 
    verbose=1, 
    save_weights_only=True,
    save_freq=n_epochs_log)

# Return unique list elements
checkpoints =list(set(checkpoints))
print('checkpoints:',checkpoints)

to make the figures understood, the checkpoints file list should be sorted by created order:

# Return unique list elements
checkpoints = sorted(list(set(checkpoints)))
print('checkpoints:',checkpoints)