Last active
November 9, 2017 00:25
-
-
Save Timopheym/0f4c17d8bb8e9a5460ecdb2fd026df03 to your computer and use it in GitHub Desktop.
kaggle2fastai dataset conventer
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import os | |
from shutil import copyfile,move | |
labels = pd.read_csv('data/dogbreed/labels.csv') | |
classes = list(labels['breed'].unique()) | |
source_path = 'data/dogbreed/old_train/' | |
path = 'data/dogbreed/train/' | |
valid_path = 'data/dogbreed/valid/' | |
for index, row in labels.iterrows(): | |
dst = path + row['breed'] + "/" | |
fname = row['id'] + '.jpg' | |
if not os.path.exists(dst): | |
os.makedirs(dst) | |
copyfile(source_path + fname, dst + fname) | |
for cls in classes: | |
parent_list = os.listdir(path + cls) | |
count =0 | |
dst = valid_path + cls + "/" | |
if not os.path.exists(dst): | |
os.makedirs(dst) | |
for child in parent_list: | |
if count < 20: | |
move(path + cls + "/" + child, dst + child) | |
else: | |
break | |
count = count+1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment