How to use Lazy Adam optimizer in tensorflow 2.0.0 - python-3.x

This code doesnt work: it has problem with tf.contrib
model.compile(optimizer=TFOptimizer(tf.contrib.opt.LazyAdamOptimizer()), loss='categorical_crossentropy')
I have tried something with tensorflow_addons.optimizers.LazyAdam() but that does not work either.
Any ideas how to run LazyAdam in tensorflow 2.0.0 ?
PS: only Adam works well as following:
model.compile(optimizer=tf.keras.optimizers.Adam(), loss='categorical_crossentropy')

import tensorflow_addons as tfa
optimizer = tfa.optimizers.LazyAdam()
tensorflow_addons is an extra functionality for TensorFlow 2.x, but now Tensorflow 2.x is still not very stable, if you are facing with module 'tensorflow_core.keras.utils' has no attribute 'register_keras_serializable', try to update you tensorflow to the latest stable version.

Related

why YOLO v3 Keras buggy?

I am running this colab from Roboflow: https://colab.research.google.com/drive/1ByRi9d6_Yzu0nrEKArmLMLuMaZjYfygO#scrollTo=WgHANbxqWJPa
The code should be as-is, but i get errors at the end...
I suspect a TF versioning issue, but how do i know which version of TF i should install instead?
It should use TF1:
%tensorflow_version 1.x
But
!python -c 'import keras;
print(keras.version)'
returns: Using TensorFlow backend. 2.2.4
What am i doing wrong here? Unistall TF & reinstall which version?
Thanx
Fred

After downgrading Tensorflow 2.0 to 1.5 results changed and results reproduction is not available

Would you help me to achieve reproducible results with Tensorflow 1.15 without restarting Python kernel. And why the output results in TF 2.0 and TF 1.5 are different with absolutely identical parameters and dataset? Is it possible to achieve identical output?
More details:
I tried to interpret model results in TF 2.0 by:
import shap
background = df3.iloc[np.random.choice(df3.shape[0], 100, replace=False)]
explainer = shap.DeepExplainer(model, background)
I recieved an error:
`get_session` is not available when using TensorFlow 2.0.`get_session` is not available when using TensorFlow 2.0.
According to the SO topic, I tried to setup TF 2.0 compatibility with TF 1 by using in the front of my code:
import tensorflow.compat.v1 as tf
But the error appeared again.
Following advice by many users, I downgraded TF2 to TF 1.15 it solved the problem, and shap module interprets the results but:
1) to make results reproducible now I have to change tf.random.set_seed(7) on tf.random.set_random_seed(7) and restart the Python kernel every time! In TF2 I didn't have to restart the kernel.
2) prediction results has been changed, especially, Economical efficiency (that is, TF1.5. wrongly classifies more important samples than TF2.0).
TF 2:
Accuracy: 94.95%, Economical efficiency = 64%
TF 1:
Accuracy: 94.85%, Economical efficiency = 56%
The code of the model is here
First, results differ from each other not only in TF1 and TF2 versions, but also in TF2.0 and TF2.2 versions. Probably, it depends on diffenent internal parameters in the packages.
Second, TensorFlow2 works with DeepExplainer in the following versions:
import tensorflow
import pandas as pd
import keras
import xgboost
import numpy
import shap
print(tensorflow.__version__)
print(pd.__version__)
print(keras.__version__)
print(xgboost.__version__)
print(numpy.__version__)
print(shap.__version__)
output:
2.2.0
0.24.2
2.3.1
0.90
1.17.5
0.35.0
But you will face some difficulties in updating the libraries.
In Python 3.5, running TF2.2, you will face the error 'DLL load failed: The specified module could not be found'.
It 100% can be solved by installing newer C++ package. See this:https://github.com/tensorflow/tensorflow/issues/22794#issuecomment-573297027
Link to download the package:https://support.microsoft.com/ru-ru/help/2977003/the-latest-supported-visual-c-downloads
In Python 3.7 you will not find the shap 0.35.0 version with whl extention. Only tar.gz extension which gives the error: "Install visual c++ package". But installation doesn't help.
Then download shap 0.35.0 for Python 3.7 here: https://anaconda.org/conda-forge/shap/files. Run Anaconda shell. Type: conda install -c conda-forge C:\shap-0.35.0-py37h3bbf574_0.tar.bz2.

After installing Tensorflow 2.0 in a python 3.7.1 env, do I need to install Keras, or does Keras come bundled with TF2.0?

I need to use Tensorflow 2.0(TF2.0) and Keras but I don't know if it's necessary to install both seperately or just TF2.0 (assuming TF2.0 has Keras bundled inside it). If I need to install TF2.0 only, will installing in a Python 3.7.1 be acceptable?
This is for Ubuntu 16.04 64 bit.
In Tensorflow 2.0 there is strong integration between TensorFlow and the Keras API specification (TF ships its own Keras implementation, that respects the Keras standard), therefore you don't have to install Keras separately since Keras already comes with TF in the tf.keras package.

How to use densenet in Keras

I notice densenet has been added to keras (https://github.com/keras-team/keras/tree/master/keras/applications)and I want to apply it in my project but when I tried to import it in jupyter anaconda, I got an error saying:
module 'keras.applications' has no attribute 'densenet'
it seems like densenet has not been incorporated into current version of keras.
Any idea how can I add it myself?
Densenet was added in keras version 2.1.3. What version of keras are you running?
Have you tried to update keras with pip install keras --upgrade since January?

keras import fails "no module named contrib.ctc"

On OSX El CApitan 10.11.6 I've installed theano & tensorflow fine. But the keras install is not happy as seen from the trace below. I've seen this reported on github issues but with no solution there, only a suggestion to post here on SO.
>>>import theano
>>>
>>> import tensorflow
>>>
>>> import keras
File "/Users/petercotton/anaconda2/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 6, in <module>
import tensorflow.contrib.ctc as ctc
ImportError: No module named contrib.ctc`
Suggestions appreciated.
This is a problem with Keras, not TensorFlow and a known issue.
A workaround is mentioned here but that would mean that you have to modify Keras code (keras/backend/tensorflow_backend.py).
Luckily, it seems that this issue is fixed in the master branch of Keras.

Resources