[PYTHON] The story of downgrading the version of tensorflow in the demo of Mask R-CNN.

Mask R CNN error

In the previous article, I explained how to resolve the following errors.

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

Click here for details ↓

[AttributeError: The story of solving module'tensorflow' has no attribute'log'. ] (https://qiita.com/skperfarming/items/dc2e95476bb97c830856)

However, as I proceeded with the investigation, it was ** a problem with the version of tensorflow and keras **.

Version change

This is the actual version change, tensorflow 1.5.0 keras 2.0.8 Change to.

Change procedure

https://tech-blog.optim.co.jp/entry/2019/03/28/173000 According to you, first enter the following code in Google colaboratory.

#Get source from git
%cd /content
!git clone https://github.com/matterport/Mask_RCNN.git
  
#Get library
%cd /content/Mask_RCNN
!pip install -r requirements.txt

** It's important from here! ** ** Although it is not listed on the above page, put the following code after this.

!pip install tensorflow==1.5.0
!pip install keras==2.0.8

You can now specify the version and install. (Actually, the version installed when you ran requirements.txt I have uninstalled and re-installed the specified version. )

For some reason, even though the version is specified in requirements.txt The latest version will be installed.

If you have an essential solution, please let us know!

Recommended Posts

The story of downgrading the version of tensorflow in the demo of Mask R-CNN.
The story of participating in AtCoder
The story of the "hole" in the file
[Python] Tensorflow 2.0 did not support Python 3.8, so the story of downgrading Python
The story of an error in PyOCR
The story of making the Mel Icon Generator version2
The story of finding the optimal n in N fist
The story of reading HSPICE data in Python
The story of viewing media files in Django
Extract the color of the object in the image with Mask R-CNN and K-Means clustering
The story of sys.path.append ()
The story of building the fastest Linux environment in the world
The story of FileNotFound in Python open () mode ='w'
Align the version of chromedriver_binary
Solve the problem of missing libcudart in Ubuntu 16.04 + CUDA 8.0 + Tensorflow environment
The story that the version of python 3.7.7 was not adapted to Heroku
[TensorFlow 2] How to check the contents of Tensor in graph mode
The story of outputting the planetarium master in pdf format with Pycairo
The first artificial intelligence. How to check the version of Tensorflow installed.
Using TensorFlow in the cloud integrated development environment Cloud9 ~ Basics of usage ~
Test the version of the argparse module
Raise the version of pyenv itself
Install an older version of Tensorflow
pyenv-change the python version of virtualenv
Summary of various operations in Tensorflow
Change the Python version of Homebrew
The meaning of ".object" in Django
The story of remounting the application server
The story of writing a program
The story of a Parking Sensor in 10 minutes with GrovePi + Starter Kit
Display the status of COVID 19 infection in Japan with Splunk (GitHub version)
The story of trying to reconnect the client
[Understanding in 3 minutes] The beginning of Linux
How to check the version of Django
The story of verifying the open data of COVID-19
The story of adding MeCab to ubuntu 16.04
The story of making Python an exe
Implement part of the process in C ++
About the virtual environment of python version 3.7
The story of making an immutable mold
The result of installing python in Anaconda
Let's claim the possibility of pyenv-virtualenv in 2021
[Python] Try pydash of the Python version of lodash
The story of manipulating python global variables
Migemo version of the: find command,: mfind
The basics of running NoxPlayer in Python
The story of trying deep3d and losing
The story of deciphering Keras' LSTM model.predict
In search of the fastest FizzBuzz in Python
The story of blackjack A processing (python)
The story of pep8 changing to pycodestyle
I compared the speed of regular expressions in Ruby, Python, and Perl (2013 version)
Understand the images of various matrix operations used in Keras (Tensorflow) with examples
Visualization of the firing state of the hidden layer of the model learned in the TensorFlow MNIST tutorial
How to install the deep learning framework Tensorflow 1.0 in the Anaconda environment of Windows