CHANGELOG

  * tf: set memory growth to True when using GPU
  * model: head: correct line ending
  * tf: add **kwargs parameter to compile() and fit()
  * tf: fix strange ground truth values issue

CHANGELOG

  * tf:dataset: add data format check
  * common: base_class: change input_size from integer to (width, height)
  * common: base_class: set default arguments for candidates_to_pred_bboxes
  * tf: dataset: modify variable initialization according to input_size type change
  * common: predict: reflect input_size type change
  * common: media: reflect input_size type change to resize_image
  * tf:dataset: reflect input_size type change to data augmentation
  * common: base_class: reflect predict.fit_pred_bboxes_to_original change
  * common: predict: fix problem that occurred because image size change was not considered
  * tf: reflect input_size type change
  * model: head: reflect input_size type change
  * tf: train: reflect input_size type change
  * common: base_class: change strides to immutable constant
  * common: base_class: add cap.release() to release resources
  * tflite: reflect input_size type change
  * tf: optimize predict() using @tf.function
  * common: predict: fix problem caused by incorrect iou calculation

CHANGELOG

  * tf: set num_sample to the number of dataset, if not specified
  * tf: modify to bring images in order on post-training
  * common: base_class: add iou/score_threshold argument
  * tf: add images_optional argument in save_dataset_for_mAP()
  * common: base_class: modify to call cv2.namedWindow once
  * common: media: modify to create colors once
  * tf: dataset: update docs

CHANGELOG

  * model: remove tpu argument
  * tf: reflect model changes
  * tflite: remove tpu_hair
  * tf, tflite: move inference into BaseClass
  * model: yolov4: remove unused import
  * pylint: update .pylintrc
  * common: base_class: modify inference() to be able to use cam
  * common: base_class: add fps display to screen

CHANGELOG

  * model: add kernel_regularizer argument
  * tf: remove subdivision
  * tf: dataset: fix issue where coordinates become 0 due to repeated division
  * tf: dataset: modify to shuffle when augmentation
  * tf: train: modify order of declaration
  * tf: train: give xiou_loss to more weight
  * tf: train: use keras.losses.BinaryCrossentropy to avoid nan problem
  * tf: train: add verbose argument
  * tf: dataset: change converted_coco format
  * tf: add image_path_prefix argument to load_dataset()
  * tf: add loss_verbose argument to compile()
  * tf: reflect dataset format change to save_dataset_for_mAP()

CHANGELOG

  * tf: dataset: add `label smooting` argument
  * tf: add label_smooting argument to load_dataset()
  * tf: train: set truth_conf threshold to 0.5 because of label smoothing

CHANGELOG

  * tf: set default num of sample for mAP to 1000
  * tf: fix error handling when image is empty

CHANGELOG

  * tf: dataset: add error handling when bboxes are empty
  * common: media: replace space of class name to underbar
  * tf: implement save_dataset_for_mAP()
  * tf: dataset: add error handling when image is empty

CHANGELOG

  * tf: add TFLITE_BUILTINS, SELECT_TF_OPS to default supported_ops
  * tf: dataset: modify to check if image exists when creating a dataset
  * tf: dataset: remove preprocess_dataset
  * tf: dataset: add cut_out
  * tf: dataset: add _next_random_augmentation_data()
  * tf: dataset: add mix_up
  * tf: dataset: implement mosaic

CHANGELOG

  * tf: train: set epsilon used for division to 1e-8
  * tf: train: add giou and iou to iou_type
  * tf: train: fix loss function of bbox_probabilities