- Python 3.6 <-- VALIDATED WITH 3.6.0
- Git
- FFmpeg
Open bash or command prompt and run the following commands on current working directory
pip install simba-uw-tf-dev
Note: If you are seeing error messages related to some dependency conflicts, then you need to either downgrade your pypi package or instruct SimBA to ignore these dependency conflicts - either works. To find more information on how to do this, click HERE
-
Open up command prompt anywhere.
-
In the command prompt type
simba
- Hit
Enter
.
Note: If you installed SimBA on a virtual environment (anaconda), after installation, you may have to run run
conda install shapely
for SimBA to work.
- Open bash or command prompt and run the following commands on current working directory
python -m venv venv
or (to make sure your virtuall environment is python 3.6 if you have multiple python versions in your machine)
py -3.6 -m venv venv
- Then activate virtual environment by
venv\Scripts\activate
- Make sure you are using the latest pip version and setup tools
python -m pip install --upgrade pip
pip uninstall setuptools
pip install setuptools
- Install simba
pip install simba-uw-tf-dev
- Fix some package version
pip3 uninstall pyparsing
pip3 install pyparsing==2.4.7
- Now you can launch simba in the terminal
simba
Click here for a detail step by step guide on how to install using anaconda.
-
Open up terminal of your environment
-
In the terminal type
pip install simba-uw-tf-dev
- It will error out when running simba. To fix it, first uninstall shapely.
pip uninstall shapely
- Then, install shapely with conda command:
conda install -c conda-forge shapely
- XCode installed
- Homebrew
- ffmpeg
- Python 3.6
- Anaconda
-
Create an environment for simba using anaconda terminal.
-
In the terminal type,
pip install simba-uw-tf-dev
-
Then,
conda install -c anaconda python.app
-
Then,
conda install matplotlib
-
Then,
conda uninstall shapely
-
Then,
conda install -c conda-forge shapely
-
Then,
pip install shap
-
Lastly,
pip install h5py
-
In the terminal, type in
simba
to test if it works.
package | ver. |
---|---|
Pillow | 5.4.1 |
deeplabcut | 2.0.9 |
eli5 | 0.10.1 |
imblearn | 0.5.0 |
imutils | 0.5.2 |
matplotlib | 3.0.3 |
Shapely | 1.6.4.post2 |
deepposekit | 0.3.5 |
dtreeviz | 0.8.1 |
opencv_python | 3.4.5.20 |
numpy | 1.18.1 |
imgaug | 0.4.0 |
pandas | 0.25.3 |
scikit_image | 0.14.2 |
scipy | 1.1.0 |
seaborn | 0.9.0 |
sklearn | 1.1.0 |
scikit-learn | 0.22.1 |
tensorflow_gpu | 0.14.1 |
scikit-learn | 0.22.1 |
tqdm | 4.30.0 |
yellowbrick | 0.9.1 |
xgboost | 0.9 |
tabulate | 0.8.3 |
tables | ≥ 3.5.1 |
dash | 1.14.0 |
dash color picker | 0.0.1 |
dash daqs | 0.5.0 |
h5py | 2.9.0 |
numba | 0.48.0 |
numexpr | 2.6.9 |
plotly | 4.9.0 |
statsmodels | 0.9.0 |
cefpython3 | 66.0 |
pyarrow | 0.17.1 |
shap | 0.35.0 |