yolo3_generator: Generates batches of data (images and box...

Description Usage Arguments

Description

Generates batches of data (images and box coordinates/scores). The data will be looped over (in batches).

Usage

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
yolo3_generator(
  annot_path,
  images_path,
  only_images = FALSE,
  net_h = 416,
  net_w = 416,
  annot_format = "pascal_voc",
  grayscale = FALSE,
  scale = 1/255,
  anchors = coco_anchors,
  labels = coco_labels,
  batch_size = 32,
  shuffle = TRUE
)

Arguments

annot_path

Annotations directory.

images_path

Images directory.

only_images

Should generator read only images (e.g. on train set for predictions).

net_h

Input layer height. Must be divisible by '32'.

net_w

Input layer width. Must be divisible by '32'.

annot_format

Annotations format. One of 'pascal_voc', 'labelme'.

grayscale

Defines input layer color channels - '1' if 'TRUE', '3' if 'FALSE'.

scale

Scaling factor for images pixel values. Default to '1 / 255'.

anchors

Prediction anchors. For exact format check coco_anchors.

labels

Character vector containing class labels. For example coco_labels.

batch_size

Batch size.

shuffle

Should data be shuffled.


maju116/platypus documentation built on Oct. 18, 2020, 9:40 a.m.