Script to convert MS COCO annotations file to Kitti bounding box label files Edit

coco2kitti.py

"""coco2kitti.py: Converts MS COCO annotation files to
                  Kitti format bounding box label files
__author__ = "Jon Barker"
"""

import os
from pycocotools.coco import COCO

def coco2kitti(catNms, annFile):

    # initialize COCO api for instance annotations
    coco = COCO(annFile)

    # Create an index for the category names
    cats = coco.loadCats(coco.getCatIds())
    cat_idx = {}
    for c in cats:
        cat_idx[c['id']] = c['name']

    for img in coco.imgs:

        # Get all annotation IDs for the image
        catIds = coco.getCatIds(catNms=catNms)
        annIds = coco.getAnnIds(imgIds=[img], catIds=catIds)

        # If there are annotations, create a label file
        if len(annIds) > 0:
            # Get image filename
            img_fname = coco.imgs[img]['file_name']
            # open text file
            with open('./labels/' + img_fname.split('.')[0] + '.txt','w') as label_file:
                anns = coco.loadAnns(annIds)
                for a in anns:
                    bbox = a['bbox']
                    # Convert COCO bbox coords to Kitti ones
                    bbox = [bbox[0], bbox[1], bbox[2] + bbox[0], bbox[3] + bbox[1]]
                    bbox = [str(b) for b in bbox]
                    catname = cat_idx[a['category_id']]
                    # Format line in label file
                    # Note: all whitespace will be removed from class names
                    out_str = [catname.replace(" ","")
                               + ' ' + ' '.join(['0']*2)
                               + ' ' + ' '.join([b for b in bbox])
                               + ' ' + ' '.join(['0']*8)
                               +'\n']
                    label_file.write(out_str[0])

if __name__ == '__main__':

    # These settings assume this script is in the annotations directory
    dataDir = '..'
    dataType = 'train2014'
    annFile = '%s/annotations/instances_%s.json' % (dataDir, dataType)

    # If this list is populated then label files will only be produced
    # for images containing the listed classes and only the listed classes
    # will be in the label file
    # EXAMPLE:
    #catNms = ['person', 'dog', 'skateboard']
    catNms = []

    # Check if a labels file exists and, if not, make one
    # If it exists already, exit to avoid overwriting
    if os.path.isdir('./labels'):
        print('Labels folder already exists - exiting to prevent badness')
    else:
        os.mkdir('./labels')
        coco2kitti(catNms, annFile)

Hey there,
I've been trying to train the DetectNet on the MSCOCO Dataset and therefore used this script to convert the annotations. I have not seen any progress in learning and found, that this script only inserts two '0's after the class label on line 42.
However, the kitti format specification is given at https://github.com/NVIDIA/DIGITS/blob/master/digits/extensions/data/objectDetection/README.md
as

Values Name Description

1 type Describes the type of object: 'Car', 'Van', 'Truck',
'Pedestrian', 'Person_sitting', 'Cyclist', 'Tram',
'Misc' or 'DontCare'
1 truncated Float from 0 (non-truncated) to 1 (truncated), where
truncated refers to the object leaving image boundaries
1 occluded Integer (0,1,2,3) indicating occlusion state:
0 = fully visible, 1 = partly occluded
2 = largely occluded, 3 = unknown
1 alpha Observation angle of object, ranging [-pi..pi]
4 bbox 2D bounding box of object in the image (0-based index):
contains left, top, right, bottom pixel coordinates
3 dimensions 3D object dimensions: height, width, length (in meters)
3 location 3D object location x,y,z in camera coordinates (in meters)
1 rotation_y Rotation ry around Y-axis in camera coordinates [-pi..pi]
1 score Only for results: Float, indicating confidence in
detection, needed for p/r curves, higher is better.

Here there are three values specified after the class label.

Am I missing a point or is this a bug?
cheers