Computer_Vision/Chapter07/images/.ipynb_checkpoints/convert-to-yolo-format-checkpoint.ipynb

from torch_snippets import *

from sklearn.model_selection import train_test_split
df = pd.read_csv('df.csv')
trn_df, val_df = train_test_split(df, random_state=10)

df_mini = df[df.ImageID.isin(df.ImageID.unique()[:500].tolist())]
trn_df_mini, val_df_mini = train_test_split(df_mini, random_state=10)

df_micro = df[df.ImageID.isin(df.ImageID.unique()[:50].tolist())]
trn_df_micro, val_df_micro = train_test_split(df_micro, random_state=10)

len(df)
df.head()

	ImageID	Source	LabelName	Confidence	XMin	XMax	YMin	YMax	IsOccluded	IsTruncated	...	IsDepiction	IsInside	XClick1X	XClick2X	XClick3X	XClick4X	XClick1Y	XClick2Y	XClick3Y	XClick4Y
0	0000599864fd15b3	xclick	Bus	1	0.343750	0.908750	0.156162	0.650047	1	0	...	0	0	0.421875	0.343750	0.795000	0.908750	0.156162	0.512700	0.650047	0.457197
1	00006bdb1eb5cd74	xclick	Truck	1	0.276667	0.697500	0.141604	0.437343	1	0	...	0	0	0.299167	0.276667	0.697500	0.659167	0.141604	0.241855	0.352130	0.437343
2	00006bdb1eb5cd74	xclick	Truck	1	0.702500	0.999167	0.204261	0.409774	1	1	...	0	0	0.849167	0.702500	0.906667	0.999167	0.204261	0.398496	0.409774	0.295739
3	00010bf498b64bab	xclick	Bus	1	0.156250	0.371250	0.269188	0.705228	0	0	...	0	0	0.274375	0.371250	0.311875	0.156250	0.269188	0.493882	0.705228	0.521691
4	00013f14dd4e168f	xclick	Bus	1	0.287500	0.999375	0.194184	0.999062	0	1	...	0	0	0.920000	0.999375	0.648750	0.287500	0.194184	0.303940	0.999062	0.523452

5 rows × 21 columns

labels = ['Bus', 'Truck']

def do(trn_df, val_df, folder):
    splits = [('train', trn_df), ('val', val_df)]
    for split, df in splits:
        os.makedirs(f'{folder}/labels', exist_ok=True)
        ImageIDs = df.ImageID.unique()
        for ImageID in ImageIDs:
            fname = ImageID
            _df = df[df['ImageID'] == ImageID][['LabelName','XMin','YMin','XMax','YMax']]
            _df['Xc'] = (_df['XMax'] + _df['XMin'])/2
            _df['Yc'] = (_df['YMax'] + _df['YMin'])/2
            _df['w'] = _df['XMax'] - _df['XMin']
            _df['h'] = _df['YMax'] - _df['YMin']
            _df['LabelName'] = _df['LabelName'].map(lambda x: labels.index(x))
            _df.drop(['XMin','YMin','XMax','YMax'], inplace=True, axis=1)
            with open(f'{folder}/labels/{fname}.txt', 'w') as f:
                for a,b,c,d,e in _df.values:
                    f.write(f'{int(a)} {b} {c} {d} {e}')
                    f.write('\n')
        with open(f'{folder}/{split}.txt', 'w') as f:
            for ImageID in ImageIDs:
                f.write(f'{ImageID}.jpg\n')

do(trn_df_micro, val_df_micro, 'yolo_labels/micro/')
do(trn_df_mini, val_df_mini, 'yolo_labels/mini/')
do(trn_df, val_df, 'yolo_labels/all/')

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-26-ca0e2222a2b7> in <module>
     25 do(trn_df_micro, val_df_micro, 'yolo_labels/micro/')
     26 do(trn_df_mini, val_df_mini, 'yolo_labels/mini/')
---> 27 do(trn_df, val_df, 'yolo_labels/all/')

<ipython-input-26-ca0e2222a2b7> in do(trn_df, val_df, folder)
     15             _df['LabelName'] = _df['LabelName'].map(lambda x: labels.index(x))
     16             _df.drop(['XMin','YMin','XMax','YMax'], inplace=True, axis=1)
---> 17             with open(f'{folder}/{fname}.txt', 'w') as f:
     18                 for a,b,c,d,e in _df.values:
     19                     f.write(f'{int(a)} {b} {c} {d} {e}')

FileNotFoundError: [Errno 2] No such file or directory: 'yolo_labels/all//b708f693265636d6.txt'