Files
inaturalist_pytorch_model/flag_videos_to_keep.py
2021-07-12 13:08:45 -04:00

63 lines
1.2 KiB
Python

import json
import shutil
import os
source_path = '/srv/ftp/hummingbird/2021'
#target_path = '/home/thebears/Videos/ftp'
target_path = '/home/thebears/ftp_links'
have_json = set()
for di, _, fns in os.walk(source_path):
for fn in fns:
if fn.endswith('.json'):
have_json.add(os.path.join(di, fn))
do_stop = False
fracs = dict()
for c_js in have_json:
hits = 0
total = 0
o = json.load(open(c_js,'r'))
for i in o:
total += 1
# if len([x for x in i['scores'] if x > 0.1]) > 0:
if len(i['boxes']) > 0:
hits += 1
fracs[c_js] = [hits, total]
if do_stop:
break
ratios = dict()
for x,y in fracs.items():
ratios[x] = y[0]/y[1]
# %%
import math
dir_created = set()
for fname, ratio in ratios.items():
cr = math.floor(ratio * 10)/10
target_dir = os.path.join(target_path, str(cr))
if not os.path.exists(target_dir) and target_dir not in dir_created:
os.mkdir(target_dir)
dir_created.add(target_dir)
else:
dir_created.add(target_dir)
source_file = fname.replace('.json','.mp4')
target_file = os.path.join(target_dir, os.path.basename(source_file))
os.symlink(source_file, target_file)