yolo_trainer Module

../_images/yolov3.png

YoloTrainer class uses YOLO: Real-Time Object Detection model, which is originally proposed in this arXiv 1. However implemented trainer module refers to Yolo-v3 2 and uses this Git 3 code as reference work.

References

1

https://arxiv.org/abs/1506.02640

2

https://arxiv.org/abs/1804.02767

3

https://github.com/eriklindernoren/PyTorch-YOLOv3

YoloTrainer class

class farabio.models.detection.yolov3.yolo_trainer.YoloTrainer(config)[source]

YoloTrainer trainer class. Override with custom methods here.

Parameters
ConvnetTrainerBaseTrainer

Inherits ConvnetTrainer class

get_trainloader()[source]

Hook: Retreives training set of torch.utils.data.DataLoader class

define_data_attr()[source]

Define data related attributes here

define_model_attr()[source]

Define model related attributes here

define_train_attr()[source]

Define training related attributes here

define_test_attr()[source]

Define training related attributes here

define_log_attr()[source]

Define log related attributes here

define_compute_attr()[source]

Define compute related attributes here

define_misc_attr()[source]

Define miscellaneous attributes here

build_model()[source]

Abstract method that builds model

on_train_epoch_start()[source]

Hook: On epoch start

on_start_training_batch(args)[source]

Hook: On training batch start

training_step()[source]

Hook: During training batch

on_end_training_batch()[source]

Hook: On end of training batch

on_epoch_end()[source]

Hook: on epoch end

save_model()[source]

Hook: saves model

on_evaluate_epoch_start()[source]

Hook: on evaluation start

on_evaluate_batch_start(args)[source]
evaluate_batch(*args)[source]

Hook: batch of evaluation loop

on_evaluate_epoch_end()[source]
test()[source]

Hook: Test lifecycle

detect_perform()[source]
get_detections()[source]
plot_bbox()[source]