python - ValueError when training TensorFlow object detection: "all elements of boxlists should be BoxList objects" -

i have dataset of 10 images of sodacans. because want process of setting tfrecords , training pipeline tested, before spend hours labeling bunch of photos.

i labeled images using rectlabel on macos. here example of annotation

<annotation> <folder>training</folder> <filename>image1.jpg</filename> <path>/users/{my_username}/desktop/models-master/object_detection/training/image1.jpg</path> <size>     <width>225</width>     <height>225</height> </size> <segmented>0</segmented> <object>     <name>sodacan</name>     <pose>unspecified</pose>     <truncated>0</truncated>     <difficult>0</difficult>     <bndbox>         <xmin>61</xmin>         <ymin>20</ymin>         <xmax>155</xmax>         <ymax>207</ymax>     </bndbox> </object> 

i added path attribute myself. don't know if need that, saw in example of annotation.

here label map looks like:

item {   id: 1   name: 'sodacan' } 

i used 2 scripts dat tran create tfrecords. can found in this repo. first use 'xml_to_csv.py' , use 'generate_tfrecord.py'.

i used config file written eshirima can found here, of course configured match data structure.

i run training script models folder using:

python object_detection/train.py \ --logtostderr \ --pipeline_config_path=object_detection/ts_configuration.config \ --train_dir=users/{my_username}/desktop/empty_folder 

after 20-30 seconds error throw:

valueerror: elements of boxlists should boxlist objects 

i have tried using tutorial on object detection repo create records, have tried using 1 of sample configs, still error. if use 'faster_rcnn_inception_resnet_v2_atrous_pets' config samples folder in object_detection folder, error:

valueerror: boxlist must boxlist 

i have no idea here. appreciated!

so figured out issue.

i had totally forgot modifications made visualization_utils.py script, extract more information. apparently seemed break training.

i downloaded models repo again, started entire process over, , training running!