Hi, I am customizing my deepstram_tlt_apps. I read about the rules of order for classes in label.txt, but I don’t see any correspondence between the tlt dataset_config for training and deepstream_tlt_apps.
Label File (ssd_labels.txt)
The order in which the classes are listed here must match the order in which the model predicts the output. This order is derived from the order in which the objects are instantiated in the dataset_config
field of the SSD experiment config file as mentioned in Transfer Learning Toolkit user guide. For example, if the dataset_config
is like this:
dataset_config {
data_sources {
...
}
data_sources {
...
}
validation_fold: 0
image_extension: "jpg"
target_class_mapping {
key: "AutoMobile"
value: "car"
}
target_class_mapping {
key: "Automobile"
value: "car"
}
target_class_mapping {
key: "Bicycle"
value: "bicycle"
}
target_class_mapping {
key: "Heavy Truck"
value: "car"
}
target_class_mapping {
key: "Motorcycle"
value: "bicycle"
}
target_class_mapping {
key: "Person"
value: "person"
}
...
}
target_class_mapping {
key: "traffic_light"
value: "road_sign"
}
target_class_mapping {
key: "twowheeler"
value: "bicycle"
}
target_class_mapping {
key: "vehicle"
value: "car"
}
}
The corresponding label file will be
bicycle
car
person
road_sign
In this case, would you mind telling me why it is the order of bicycle, car, person, road_sign with regard to the dataset_config for tlt training in example? I attached the readme.md below. Thanks (2.0 KB)