https://www.kaggle.com/c/whale-categorization-playground
Set up a conda environment for the project
- open this project in PyCharm
- open up settings
- select
Project:Whale
/Project Interpreter
- click on the gear
- select conda, new environment with python 3.6
- click
ok
- in Whale root,
mkdir data
- download the files from https://www.kaggle.com/c/whale-categorization-playground/data into
data
- unzip
train.zip
andtest.zip
- move the train dir to raw train:
mv train raw_train
- run the
src/utils/prepare_data.py
script (you can right click on it and clickrun
)
- this will create a directory in data called
train
which will have images in the format oflabel/example1.jpg
- click on
Edit Configurations:
from the run menu - click the
+
button, and thenPython tests/Unittests
- name it something like
unit tests
- for the
Target/script path
navigate to Whale/tests - under pattern, put
*test.py
- click on
ok
- click on the play button to run the tests
- create a conda environment using the requirements.txt:
conda install --file requirements.txt
- run the following command (outputs to TestOutput/log and git adds it):
./run-tests.sh
Either:
- right click on
trainer.py
in PyCharm and click the run button - run from the command line:
PYTHONPATH=~/PycharmProjects/Whale python src/whale/trainer.py