I’m trying to train detectnet_v2 custom model using Transfer Learning Toolkit via Jupyter Notebook Example.
I have cross verified and checked all the Kitti format variables but too i’m getting this issue.
print("TFrecords conversion spec file for kitti training")
!cat $SPECS_DIR/detectnet_v2_tfrecords_kitti_trainval.txt
OUTPUT:
TFrecords conversion spec file for kitti training
kitti_config {
root_directory_path: “/workspace/tlt-experiments/data/training”
image_dir_name: “image_2”
label_dir_name: “label_2”
image_extension: “.jpg”
partition_mode: “random”
num_partitions: 2
val_split: 20
num_shards: 10
}
image_directory_path: “/workspace/tlt-experiments/data/training”
# Creating a new directory for the output tfrecords dump.
print("Converting Tfrecords for kitti trainval dataset")
!tlt-dataset-convert -d $SPECS_DIR/detectnet_v2_tfrecords_kitti_trainval.txt \
-o $USER_EXPERIMENT_DIR/tfrecords/kitti_trainval/kitti_trainval
OUTPUT ERROR]
Converting Tfrecords for kitti trainval dataset
Using TensorFlow backend.
2019-12-02 09:46:23,370 - iva.detectnet_v2.dataio.build_converter - INFO - Instantiating a kitti converter
2019-12-02 09:46:23,381 - iva.detectnet_v2.dataio.kitti_converter_lib - INFO - Num images in
Train: 3875 Val: 968
2019-12-02 09:46:23,381 - iva.detectnet_v2.dataio.kitti_converter_lib - INFO - Validation data in partition 0. Hence, while choosing the validationset during training choose validation_fold 0.
2019-12-02 09:46:23,382 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 0
/usr/local/lib/python2.7/dist-packages/iva/detectnet_v2/dataio/kitti_converter_lib.py:266: VisibleDeprecationWarning: Reading unicode strings without specifying the encoding argument is deprecated. Set the encoding, use None for the system default.
Traceback (most recent call last):
File “/usr/local/bin/tlt-dataset-convert”, line 10, in
sys.exit(main())
File “./detectnet_v2/scripts/dataset_convert.py”, line 64, in main
File “./detectnet_v2/dataio/dataset_converter_lib.py”, line 74, in convert
File “./detectnet_v2/dataio/dataset_converter_lib.py”, line 108, in _write_partitions
File “./detectnet_v2/dataio/dataset_converter_lib.py”, line 149, in _write_shard
File “./detectnet_v2/dataio/kitti_converter_lib.py”, line 169, in _create_example_proto
File “./detectnet_v2/dataio/kitti_converter_lib.py”, line 266, in _add_targets
File “/usr/local/lib/python2.7/dist-packages/numpy/lib/npyio.py”, line 2068, in genfromtxt
raise ValueError(errmsg)
ValueError: Some errors were detected !
Line #4 (got 15 columns instead of 16)
Line #5 (got 15 columns instead of 16)
Line #6 (got 15 columns instead of 16)
Line #7 (got 15 columns instead of 16)
Line #8 (got 15 columns instead of 16)
Line #9 (got 15 columns instead of 16)
MY LABEL EXAMPLE:
person 0.00 0 0.00 286.00 317.00 342.00 488.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
person 0.00 0 0.00 195.00 353.00 239.00 437.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
IMAGE SIZE:
WIDTH: 960
HEIGHT: 1080
Kindly do the needful ASAP.