diff --git a/CITATION.cff b/CITATION.cff
index 3abeb8e7d876639edc9e89d01f49fa021a1b23c8..8d1e53d00414e2c93e4d027fd4aa8c424ac209db 100644
--- a/CITATION.cff
+++ b/CITATION.cff
@@ -1,7 +1,7 @@
cff-version: 1.2.0
preferred-citation:
type: Method
- message: If you use YOLO-DYNI method, please cite it as below.
+ message: If you use RAVEN2YOLO method, please cite it as below.
authors:
- family-names: Chavin
given-names: Stéphane
@@ -9,4 +9,4 @@ preferred-citation:
version: 1.0
date-released: 2023-2-16
license: GPL-3.0
- url: "https://gitlab.lis-lab.fr/stephane.chavin/yolo-dyni"
+ url: "https://gitlab.lis-lab.fr/stephane.chavin/raven2yolo"
diff --git a/get_spectrogram.py b/get_spectrogram.py
index 2e01602b3094845198b789e3ed953797435f8269..556ce00cfd53e70dae72f427370d93caea20761c 100755
--- a/get_spectrogram.py
+++ b/get_spectrogram.py
@@ -5,29 +5,10 @@ import argparse
import numpy as np
import soundfile
from p_tqdm import p_map
-<<<<<<< HEAD
from tqdm import tqdm
import utils
import pandas as pd
-=======
-import soundfile as sf
-import scipy.signal as signal
-from tqdm import tqdm
-
-import warnings
-warnings.filterwarnings('ignore')
-
-def arg_directory(path):
- if os.path.isdir(path):
- return path
- else:
- raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
-
-def create_spectrogram(y, directory, filename, offset, duration, window_arg, hop_length_arg):
- window = np.hanning(window_arg)
- stft = librosa.core.spectrum.stft(y, n_fft=window_arg, hop_length=hop_length_arg, window=window)
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
def main(data, arguments):
"""
@@ -44,13 +25,8 @@ def main(data, arguments):
print(f'`{filename}` cannot be open : : {error}')
return
-<<<<<<< HEAD
# Create the list of all possible offset to compute spectrogram
offset_list = np.arange(0, file_duration, arguments.duration - arguments.overlap)
-=======
- log_stft = np.log10(np.abs(stft))
- vmin, vmax = log_stft.mean(), log_stft.max()
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
for offset in offset_list:
file = filename.replace('/', '_').split('.', maxsplit=1)[0]
@@ -58,6 +34,7 @@ def main(data, arguments):
sig, fs = soundfile.read(filename, start=int(
offset*fs), stop=int((offset+arguments.duration)*fs),
always_2d=True) # Load the signal
+
sig = sig[:, 0] # Only take channel 0
# Apply resample and low/high pass filter
sig = utils.signal_processing(
@@ -73,10 +50,9 @@ def main(data, arguments):
folder = 'spectrograms'
name = os.path.join(arguments.directory, folder, f'{file}_{offset}')
-<<<<<<< HEAD
utils.create_spectrogram(
- sig, arguments.directory, name, window_size=arguments.window,
- overlap=arguments.hop)
+ sig, arguments.directory, name, window_size=arguments.window,
+ overlap=arguments.hop)
return folder
except Exception as error:
print(f'`{filename}` cannot be open : {error}')
@@ -84,8 +60,7 @@ def main(data, arguments):
if __name__ == "__main__":
parser = argparse.ArgumentParser(
- formatter_class=argparse.ArgumentDefaultsHelpFormatter,
- description='Extract spectrogram for each .wav file')
+ formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='Extract spectrogram for each .wav file')
parser.add_argument('path', type=utils.arg_directory,
help='Path of the folder/file that contains the recordings')
parser.add_argument('directory', type=utils.arg_directory,
@@ -127,87 +102,3 @@ if __name__ == "__main__":
final_dest = os.path.join(directory, dest[0] if len(dest) is list else dest)
print(f'Saved to {final_dest}')
-=======
-def process_recordings(data, img_per_rec, args):
- _, (i) = data
- duration = args.duration
- overlap = args.overlap
- filename = str(i[0])
- try:
- info = sf.info(filename)
- file_duration, fs = info.duration, info.samplerate
- except Exception as error:
- print(f'`{filename}` cannot be open... : {error}')
- for count in range(img_per_rec):
- offset = count * (duration - overlap)
- if offset > file_duration:
- continue
- try:
- sig, fs = sf.read(filename, start=int(offset*fs), stop=int((offset+duration)*fs), always_2d=True)
- sig = sig[:,0]
- if not args.sr:
- args.sr = fs
- sig = signal_processing(sig, args.sr, fs, args.up, args.low)
- create_spectrogram(sig, args.directory, filename, offset, duration, args.window, args.hop)
- except Exception:
- print(f'`{filename}` cannot be open...')
-
-def signal_processing(sig, sr, fs, up, low):
- sig_r = signal.resample(sig, int(len(sig)*sr/fs)) # resample
- if up:
- sos = signal.butter(2, up/(sr/2), 'hp', output='sos') # create high pass filter
- sig_r = signal.sosfilt(sos, sig_r) # apply high pass filter
- if low:
- sos2 = signal.butter(1, low/(sr/2), 'lp', output='sos') # create low pass filter
- sig_r = signal.sosfilt(sos2, sig_r) # create low pass filter
- return(sig_r)
-
-
-if __name__ == "__main__":
- parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='Extract spectrogram for each .wav file')
- parser.add_argument('path_to_data', type=arg_directory, help='Path of the folder that contains the recordings')
- parser.add_argument('directory', type=arg_directory, help='Directory to which spectrograms will be stored')
- parser.add_argument('-m', '--mode', type=str, choices=['unique', 'multiple'], help='if unique, only 1 image per file', default='multiple')
- parser.add_argument('-n', '--columns_name', type=str, help='Name of the columns that contain the path of the .wav', default='Path')
- parser.add_argument('-f', '--file', type=str, help='Name of the file that contains the recording to print', default='None')
- parser.add_argument('--frames', type=int, help='Number of spectrogram per file', default=30)
- parser.add_argument('--duration', type=int, help='Duration for each spectrogram', default=8)
- parser.add_argument('--overlap', type=int, help='Overlap between 2 spectrograms', default=2)
- parser.add_argument('--sr', type=int, help='Sampling rate for the spectrogram. If no argument, '
- 'SR will be original SR of the recording', default=None)
- parser.add_argument('--window', type=int, help='Window size for the Fourier Transform', default=1024)
- parser.add_argument('--hop', type=int, help='Hop lenght for the Fourier Transform', default=512)
- parser.add_argument('--cpu', type=int, help='To speed up the process, write 2 or more', default=1)
- parser.add_argument('--up', type=int, help='High Pass Filter value in Hz', default=10)
- parser.add_argument('--low', type=int, help='Low Pass Filter value in Hz', default=None)
- args = parser.parse_args()
-
- if args.mode == 'multiple':
- img_per_rec = args.frames
- elif args.mode == 'unique':
- img_per_rec = 1
-
- path_to_data = args.path_to_data
-
- if args.file != 'None':
- try :
- df = pd.read_csv(args.file, low_memory=False)
- except Exception as error:
- print('Try to load as pickle...')
- df = pd.read_pickle(args.file, low_memory=False)
- df['Path'] = df[args.columns_name]
- else:
- df = pd.DataFrame(glob.glob(os.path.join(path_to_data, '*'), recursive=True), columns=['Path'])
-
- if args.cpu == 1:
- for num, row in tqdm(df.iterrows(), total = len(df)):
- process_recordings([num, [row.Path]], img_per_rec, args)
- final_dest = os.path.join(args.directory,'Spectrogram')
- print(f'Saved to {final_dest}')
- else:
- img_per_rec = [img_per_rec]*len(df.groupby('Path'))
- args = [args]*len(df.groupby('Path'))
- p_map(process_recordings, enumerate(df.groupby('Path')), img_per_rec, args, num_cpus=args[0].cpu, total=len(df.groupby('Path')))
- final_dest = os.path.join(args[0].directory,'Spectrogram')
- print(f'Saved to {final_dest}')
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
diff --git a/get_time_freq_detection.py b/get_time_freq_detection.py
index 70d9fc6aa48d061c368d312da7ad026b5e90c0e8..29655bef8e59c4c0a2d3c82e1d6068c0650757bc 100755
--- a/get_time_freq_detection.py
+++ b/get_time_freq_detection.py
@@ -1,4 +1,3 @@
-<<<<<<< HEAD
"""Compiles detections into a dataframe and/or into Raven annotation format (.txt)"""
import argparse
@@ -8,40 +7,6 @@ import utils
import xarray as xr
import pandas as pd
-=======
-import pandas as pd
-import os
-import argparse
-import yaml
-from datetime import date
-from tqdm import tqdm
-
-def arg_directory(path):
- if os.path.isdir(path):
- return path
- else:
- raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
-
-def process_annotations(annotations_folder, duration, outdir, sr, names):
- today = date.today()
- out_file = f'YOLO_detection_{today.day}_{today.month}_freq_{sr}_duration_{duration}'
-
- df_list = []
-
- for file_name in tqdm(os.listdir(annotations_folder)):
- if file_name.endswith('.txt'):
- file_path = os.path.join(annotations_folder, file_name)
- try:
- annotation_df = pd.read_csv(file_path, sep=' ', names=['espece', 'x', 'y', 'w', 'h', 'conf'])
- except Exception:
- annotation_df = pd.read_csv(file_path, sep=' ', names=['espece', 'x', 'y', 'w', 'h'])
-
- annotation_df['file'] = file_name
- annotation_df['idx'] = annotation_df['file'].str.split('_').str[-1].str.split('.').str[0]
-
- annotation_df['file'] = ['.'.join(x.file.split('.')[:-1]) for i, x in annotation_df.iterrows()]
- annotation_df.file = annotation_df.file + '.wav'
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
def main(arguments):
"""
@@ -78,7 +43,6 @@ def main(arguments):
if __name__ == "__main__":
-<<<<<<< HEAD
parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='Collect detections and return a complete dataframe')
parser.add_argument('path_to_data', type=utils.arg_directory,
@@ -98,19 +62,3 @@ if __name__ == "__main__":
args = parser.parse_args()
main(args)
-=======
- parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='Collect detections and return a complete dataframe')
- parser.add_argument('path_to_data', type=arg_directory, help='Path of the folder that contains the .txt files')
- parser.add_argument('directory', type=arg_directory, help='Directory where the dataframe will be stored')
- parser.add_argument('names', type=str, help='path to YOLOv5 custom_data.yaml file')
-
- parser.add_argument('-s','--sr', type=int, help='Sampling Rate of the spectrogram', required=True)
- parser.add_argument('--duration', type=int, help='Duration of the spectrogram', default=8)
- args = parser.parse_args()
-
- with open(args.names, 'r') as file:
- data = yaml.safe_load(file)
- names = data['names']
-
- process_annotations(args.path_to_data, args.duration, args.directory, args.sr, names)
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
diff --git a/get_train_annot.py b/get_train_annot.py
index 1c7835ff5e0990d0054236eb2eabacdb67cd0d7d..fa7f0834b15d1f8146dcd90eaad087f884e0430d 100755
--- a/get_train_annot.py
+++ b/get_train_annot.py
@@ -3,20 +3,21 @@
import argparse
import random
import os
-import sys
-import cv2
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import soundfile as sf
+import cv2
+import sys
+import subprocess
import utils
from p_tqdm import p_map
from tqdm import tqdm
-def process(entry, arguments, species_list, colors):
+def process(entry, arguments, species_list):
"""
Precess the annotation to get the .jpg spectrogram and the .txt annotation file
:param x (tuple): Enumerate number, [filename, group] per file
@@ -28,8 +29,8 @@ def process(entry, arguments, species_list, colors):
try:
info = sf.info(filename) # Collection recording information
file_duration, fs = info.duration, info.samplerate
- except Exception as e:
- print(f'`{filename}` cannot be open... : {e}')
+ except Exception as error:
+ print(f'`{filename}` cannot be open... : {error}')
return
# create the time list between 0 and 1000 * duration
@@ -62,13 +63,13 @@ def process(entry, arguments, species_list, colors):
sig, fs = sf.read(filename, start=int(
offset*fs), stop=int((offset+arguments.duration)*fs), always_2d=True) # Load the signal
sig = sig[:, 0] # Only take channel 0
- if arguments.rf is None:
+ if arguments.rf == None:
arguments.rf = fs
# Apply resample and low/high pass filter
sig = utils.signal_processing(
sig, rf=arguments.rf, fs=fs, high=arguments.high, low=arguments.low)
- _ = utils.create_spectrogram(
- sig, arguments.directory, names=None,
+ fig = utils.create_spectrogram(
+ sig, arguments.directory, names=None,
window_size=arguments.window,
overlap=arguments.hop)
@@ -93,7 +94,7 @@ def process(entry, arguments, species_list, colors):
columns=['id', 'x', 'y', 'width', 'height'])
annotation = annotation.dropna(axis=1, how='all')
- new_table = new_table.dropna(axis=1, how='all')
+ new_table = new_table.dropna(axis=1, how='all')
annotation = pd.concat([annotation, new_table])
grp = grp.drop(table.index)
@@ -168,13 +169,11 @@ if __name__ == '__main__':
parser.add_argument(
'--rf', type=int, help='Frequency Resampling ', default=None)
parser.add_argument(
- '--window', type=int, help='Window size for the Fourier Transform',
- default=1024)
+ '--window', type=int, help='Window size for the Fourier Transform', default=1024)
parser.add_argument(
'--hop', type=float, help='Ratio of hop in window : 50%% = 0.5', default=.5)
parser.add_argument(
- '--cpu', type=int, help='To speed up the process, write 2 or more',
- default=1)
+ '--cpu', type=int, help='To speed up the process, write 2 or more', default=1)
parser.add_argument('--high', type=int,
help='High Pass Filter value in Hz', default=10)
parser.add_argument('--low', type=int,
@@ -192,18 +191,16 @@ if __name__ == '__main__':
for file, _ in df.groupby('Path'):
new_df = utils.open_file(file)
if len(new_df) >= 1:
- new_df['Path'] = os.path.join(args.path_to_data,
- str(file.split('.Table')[0]+f'.{suffix}'))
+ new_df['Path'] = os.path.join(args.path_to_data, str(file.split('.Table')[0]+f'.{suffix}'))
final.append(new_df)
else:
continue
df = pd.concat(final)
elif 'Path' not in df.columns:
- df['Path'] = os.path.join(args.path_to_data,
- args.filename_path.split('/')[-1].split('.Table')[0]+f'.{suffix}')
+ df['Path'] = os.path.join(args.path_to_data, args.filename_path.split('/')[-1].split('.Table')[0]+f'.{suffix}')
df, species = utils.prepare_dataframe(df, args)
- list_colors = [(random.randint(0, 255), random.randint(0, 255),
+ colors = [(random.randint(0, 255), random.randint(0, 255),
random.randint(0, 255)) for _ in range(len(species))]
species.to_csv(os.path.join(
@@ -212,13 +209,12 @@ if __name__ == '__main__':
if args.cpu == 1:
for i in tqdm(enumerate(df.groupby('Path')), total=len(df.groupby('Path')),
desc="Processing", ascii='░▒▓█'):
- process(i, args, species, list_colors)
+ process(i, args, species)
else:
- args = [args for _ in range(len(df.groupby('Path')))]
- species = [species for _ in range(len(df.groupby('Path')))]
- list_colors = [list_colors for _ in range(len(df.groupby('Path')))]
+ args = [args for i in range(len(df.groupby('Path')))]
+ species = [species for i in range(len(df.groupby('Path')))]
p_map(process, enumerate(df.groupby('Path')), args,
- species, list_colors, num_cpus=args[0].cpu, total=len(df.groupby('Path')))
+ species, num_cpus=args[0].cpu, total=len(df.groupby('Path')))
args = args[0]
print('saved to', args.directory)
@@ -238,9 +234,10 @@ if __name__ == '__main__':
directory_path = os.path.join(path, args.directory, 'set')
# Create the directory path if not exists
utils.create_directory(directory_path)
- try :
+ try :
# Run the split command
os.system(f'{sys.executable} {script} {data_path} {directory_path} -r 0.7 --test')
+
print(f'Train saved in {directory_path}\n')
print('To train your model, use the following command : \n')
@@ -253,8 +250,7 @@ if __name__ == '__main__':
print(command,'\n')
print('\u26A0\uFE0F Be aware that it is recommended to have background images that',
' represents 10% of your dataset. To do so, please use the script "get_spectrogram.py"',
- ' with --background arguments. Comptue on recordings that contains multiple',
- ' type of noise...')
+ ' with --background arguments. Comptue on recordings that contains multiple type of noise...')
except Exception as error:
print(error)
diff --git a/get_train_val.py b/get_train_val.py
index 6a5fc193658ab4148ce8bbbdbd0a5d0920aed1f8..de6d9a637b3ef979f2e3f47d5b4292388573fd49 100755
--- a/get_train_val.py
+++ b/get_train_val.py
@@ -1,4 +1,3 @@
-<<<<<<< HEAD
"""Separates training and validation datasets in a balanced manner"""
import argparse
@@ -56,129 +55,10 @@ def export_split(entry, path, directory):
os.path.join(directory, 'custom_data.yaml'))
with open(os.path.join(directory, 'custom_data.yaml'), 'w', encoding='utf-8') as f:
-=======
-import yaml
-import os
-import pandas as pd
-from tqdm import tqdm
-import numpy as np
-import shutil
-import argparse
-
-def arg_directory(path):
- if os.path.isdir(path):
- return path
- else:
- raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
-
-def create_directory_if_not_exists(directory):
- if not os.path.exists(directory):
- os.mkdir(directory)
-
-def copy_files_to_directory(file_list, source_dir, destination_dir, suffix):
- for file_name in file_list:
- source_path = os.path.join(source_dir, f'{file_name}.{suffix}')
- destination_path = os.path.join(destination_dir, f'{file_name}.{suffix}')
- shutil.copy2(source_path, destination_path)
-
-def split(df, ratio):
- classes = df.espece.unique()
- n_class = classes.size
- train_count = pd.DataFrame(np.zeros((n_class, 1)), index=classes)
- test_count = train_count.copy()
- train_df = pd.DataFrame()
- test_df = pd.DataFrame()
- for i, c in enumerate(classes):
- try:
- sdf = df.groupby('espece').get_group(c)
- except Exception:
- continue
- if train_count.loc[c].iloc[0] == 0:
- f = sdf.sample(1).file.iloc[0]
- mask = df.file == f
- train_count = train_count.add(df[mask].espece.value_counts(), axis = 0).fillna(0)
- train_df = pd.concat([train_df,df[mask]])
- df = df[~mask]
- if test_count.loc[c].iloc[0] == 0:
- f = sdf.sample(1).file.iloc[0]
- mask = df.file == f
- test_count = test_count.add(df[mask].espece.value_counts(), axis = 0).fillna(0)
- test_df = pd.concat([test_df, df[mask]])
- df = df[~mask]
- while len(df):
- min_esp = df.groupby('espece').count().file.idxmin()
- sdf = df.groupby('espece').get_group(min_esp)
- f = sdf.sample(1).file.iloc[0]
- if (train_count.loc[min_esp]/(test_count.loc[min_esp] + train_count.loc[min_esp]))[0] > ratio:
- test_count.loc[min_esp] += df[df.file == f].groupby('espece').count().iloc[0].file
- test_df = pd.concat([test_df,df[df.file == f]])
- else:
- train_count.loc[min_esp] += df[df.file == f].groupby('espece').count().iloc[0].file
- train_df = pd.concat([train_df, df[df.file == f]])
- df = df[df.file != f]
- print('\nratio', train_count/(test_count + train_count))
- return train_df, test_df
-
-def process_data(args):
- path = args.path_to_data
- directory = args.directory
-
- df = pd.concat({f: pd.read_csv(os.path.join(path, f), sep=' ', names=['espece', 'x', 'y', 'w', 'h'])
- for f in tqdm(os.listdir(path))}, names=['file'])
-
- df = df.reset_index(level=[0])
- df = df.reset_index()
- del df['index']
-
- df = df[df.espece != 'y']
- df.espece = df.espece.astype(float)
- tab = df.groupby('espece').count()
- tab = tab.sort_values(tab.columns[0], ascending=False)
- compte = pd.DataFrame(np.zeros((len(tab) + 1, 1)), columns=['nombre'])
-
- return df
-
-
-def export_split(entry, path, directory):
- val = entry[0]
- train = entry[1]
- create_directory_if_not_exists(os.path.join(directory, 'images'))
- create_directory_if_not_exists(os.path.join(directory, 'labels'))
-
- if args.test == 1:
- test = entry[2]
- test.file = ['.'.join(x.split('.')[:-1]) for num, x in enumerate(test.file)]
- create_directory_if_not_exists(os.path.join(directory, 'images/test'))
- create_directory_if_not_exists(os.path.join(directory, 'labels/test'))
- copy_files_to_directory(test.file, path, os.path.join(directory, 'labels/test'), 'txt')
- copy_files_to_directory(test.file, os.path.join(path, '../images/all'), os.path.join(directory, 'images/test'), 'jpg')
-
-
- val.file = ['.'.join(x.split('.')[:-1]) for num, x in enumerate(val.file)]
- train.file = ['.'.join(x.split('.')[:-1]) for num, x in enumerate(train.file)]
- create_directory_if_not_exists(os.path.join(directory, 'images/train'))
- create_directory_if_not_exists(os.path.join(directory, 'images/val'))
- create_directory_if_not_exists(os.path.join(directory, 'labels/train'))
- create_directory_if_not_exists(os.path.join(directory, 'labels/val'))
-
- copy_files_to_directory(val.file, path, os.path.join(directory, 'labels/val'), 'txt')
- copy_files_to_directory(val.file, os.path.join(path, '../images/all'), os.path.join(directory, 'images/val'), 'jpg')
-
- copy_files_to_directory(train.file, path, os.path.join(directory, 'labels/train'), 'txt')
- copy_files_to_directory(train.file, os.path.join(path, '../images/all'), os.path.join(directory, 'images/train'), 'jpg')
-
- try:
- liste_espece = pd.read_csv(os.path.join(path, '../liste_especes.csv'))
- except Exception:
- print('No species list detected, please add it to', os.path.join(directory, 'custom_data.yaml'))
-
- with open(os.path.join(directory, 'custom_data.yaml'), 'w') as f:
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
if args.test == 1:
f.write(f'test: {os.path.join(directory, "images/test")}\n')
f.write(f'train: {os.path.join(directory, "images/train")}\n')
f.write(f'val: {os.path.join(directory, "images/val")}\n')
-<<<<<<< HEAD
f.write(f'nc: {len(species_list)}\n')
f.write(f'names: {species_list.species.tolist()}')
@@ -246,24 +126,4 @@ if __name__ == '__main__':
print('\u26A0\uFE0F Be aware that it is recommended to have background images that',
'represents 10% of your dataset. To do so, please use the script "get_spectrogram.py"',
'with --background arguments. Comptue on recordings that contains multiple type of noise...')
-
-=======
- f.write(f'nc: {len(liste_espece)}\n')
- f.write(f'names: {liste_espece.espece.tolist()}')
-
-if __name__ == '__main__':
- parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='TODO')
- parser.add_argument('-r', '--ratio', type=float, default=0.7, help='Train Ratio (val = 1 - ratio)')
- parser.add_argument('-p', '--path_to_data', type=arg_directory, help='Path of the folder that contains the .txt (ending with labels/)', required=True)
- parser.add_argument('-d', '--directory', type=arg_directory, help='Directory to which spectrogram and .txt files will be stored (different from -p)', required=True)
- parser.add_argument('--test', type=int, help='1 if True. Split into train/test/val. 1 - Ratio / 2 for test and same for validation', default=0)
- args = parser.parse_args()
-
- df = process_data(args)
- train, val = split(df, args.ratio)
- if args.test == 1:
- val, test = split(val, 0.5)
- export_split([val, train, test], args.path_to_data, args.directory)
- else :
- export_split([val, train], args.path_to_data, args.directory)
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
+
\ No newline at end of file
diff --git a/labelme2yolo.py b/labelme2yolo.py
index 2294804ecf9b7ea99221d207b0d76aa996d747d6..8c6a4c13538ec024cfdbed919231733d69dc99a8 100755
--- a/labelme2yolo.py
+++ b/labelme2yolo.py
@@ -2,50 +2,11 @@
import os
import json
-<<<<<<< HEAD
import argparse
from glob import glob
import utils
-=======
-import base64
-import argparse
-from glob import glob
-from pathlib import Path
-
-def arg_directory(path):
- if os.path.isdir(path):
- return path
- else:
- raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
-
-def create_directory(directory):
- try:
- os.makedirs(os.path.join(directory,'labels'), exist_ok=True)
- except Exception as e:
- print(f'`{path}` has been created')
- return (directory)
-
-
-def convert_labelme_to_yolo(labelme_annotation_path, yolo_directory):
- # Load LabelMe annotation
- image_id = Path(labelme_annotation_path).stem
- with open(labelme_annotation_path, 'r') as labelme_annotation_file:
- labelme_annotation = json.load(labelme_annotation_file)
-
- # YOLO annotation and image paths
- yolo_annotation_path = os.path.join(yolo_directory, 'labels', f'{image_id}.txt')
- yolo_image_path = os.path.join(yolo_directory, 'images/all', f'{image_id}.jpg')
- with open(yolo_annotation_path, 'w') as yolo_annotation_file:
- yolo_image_data = base64.b64decode(labelme_annotation['imageData'])
- # Write YOLO image
- with open(yolo_image_path, 'wb') as yolo_image_file:
- yolo_image_file.write(yolo_image_data)
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
-
-
-<<<<<<< HEAD
def main(arguments):
"""
Launch the processing on each .txt.
@@ -60,32 +21,6 @@ def main(arguments):
utils.labelme2yolo(labelme_annotation_path, arguments.directory)
# Add all the information in the .txt file
with open(labelme_annotation_path, 'r', encoding='utf-8') as labelme_annotation_file:
-=======
- label = shape['label']
-
- # shape['points'] format : [[x1,y1],[x2,y2]...] #
- scale_width = 1.0 / labelme_annotation['imageWidth']
- scale_height = 1.0 / labelme_annotation['imageHeight']
- width = abs(shape['points'][1][0] - shape['points'][0][0]) * scale_width
- height = abs(shape['points'][1][1] - shape['points'][0][1]) * scale_height
-
- x = min(shape['points'][0][0], shape['points'][1][0]) * scale_width + width / 2
- y = min(shape['points'][0][1], shape['points'][1][1]) * scale_height + height / 2
- if x+width/2 > 1 or y+height/2>1:
- print(f'Error with bounding box values over 1 in file {yolo_image_file}')
- annotation_line = f'{label} {x} {y} {width} {height}\n'
- yolo_annotation_file.write(annotation_line)
-
-def main(args):
- yolo_names = set()
- create_directory(os.path.join(args.directory, 'images'))
- create_directory(os.path.join(args.directory, 'images/all'))
- create_directory(os.path.join(args.directory, 'labels'))
- for labelme_annotation_path in glob(f'{args.path_to_data}/*.json'):
- convert_labelme_to_yolo(labelme_annotation_path, args.directory)
-
- with open(labelme_annotation_path, 'r') as labelme_annotation_file:
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
labelme_annotation = json.load(labelme_annotation_file)
for shape in labelme_annotation['shapes']:
diff --git a/requirements.txt b/requirements.txt
index 98831621502e682ee0e6d7d761877afd4e28431b..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,81 +0,0 @@
-# Raven2YOLO requirements
-# Usage: pip install -r requirements.txt
-
-# Base ------------------------------------------------------------------------
-<<<<<<< HEAD
-
-argparse==1.4.0 # Command-line argument parsing
-matplotlib>=3.2.2 # Plotting library
-numpy>=1.18.5 # Numerical computing library
-opencv-python>=4.1.1 # Computer vision library
-Pillow>=7.1.2 # Python Imaging Library
-PyYAML>=5.3.1 # YAML parser and emitter
-os>=0.11.0 # Operating system interface
-pandas>=2.2.2 # Data manipulation and analysis
-tqdm>=4.64.0 # Progress bar library
-=======
-gitpython>=3.1.30
-globox==2.4.5
-matplotlib>=3.2.2
-multiprocess==0.70.16
-mycolorpy==1.5.1
-numpy>=1.18.5
-opencv-python>=4.1.1
-Pillow>=7.1.2
-psutil # system resources
-p-tqdm==1.4.0
-PyYAML>=5.3.1
-requests>=2.23.0
-scipy>=1.4.1
-soundfile>=0.11.0
-thop>=0.1.1 # FLOPs computation
-torch>=1.7.0 # see https://pytorch.org/get-started/locally (recommended)
-torchvision>=0.8.1
-tqdm>=4.64.0
-labelme==5.1.1
-librosa==0.9.2
-# protobuf<=3.20.1 # https://github.com/ultralytics/yolov5/issues/8012
-albumentations>=1.0.3 #data augmentation (optional)
-
-
-# Logging ---------------------------------------------------------------------
-tensorboard>=2.4.1
-# clearml>=1.2.0
-# comet
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856
-
-# Plotting --------------------------------------------------------------------
-
-matplotlib>=3.7.1 # Plotting library
-seaborn>=0.11.0 # Statistical data visualization
-
-# Extras ----------------------------------------------------------------------
-<<<<<<< HEAD
-
-ipdb>=0.13.9 # IPython debugger
-ipython>=8.1.1 # Interactive Python shell
-
-# Additional Packages ---------------------------------------------------------
-
-glob>=1.3.0 # Unix-style pathname pattern expansion
-shutil>=1.0.0 # High-level file operations
-base64>=1.2.0 # Base16, Base32, Base64, Base85 data encoding
-json>=1.0.0 # JSON encoder/decoder
-datetime>=1.0.0 # Basic date and time types
-pathlib>=1.0.0 # Object-oriented filesystem paths
-librosa>=0.9.2 # Audio and music processing library
-scipy>=1.8.0 # Scientific library for numerical computations
-cv2>=1.0.0 # OpenCV computer vision library
-soundfile>=0.11.0 # Sound library
-p_tqdm==1.4.0 # Parallel tqdm (progress bar) for Python
-yaml==6.0 # YAML parser and emitter
-torch==1.12.0 # PyTorch deep learning framework
-albumentations>=1.0.3 # Image augmentation library
-scikit-learn<=1.1.2 # Machine learning library
-=======
-# ipython # interactive notebook
-# mss # screenshots
-# pycocotools>=2.0.6 # COCO mAP
-# roboflow
-# ultralytics # HUB https://hub.ultralytics.com
->>>>>>> 729ca99066972cd2d914d6054b6e8885d8e9c856