For details, see the Google Developers Site Policies. 'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=133),Įxcept as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. 'panoptic_image/filename': Text(shape=(), dtype=tf.string), 'panoptic_image': Image(shape=(None, None, 3), dtype=tf.uint8), 'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=80), 'bbox': BBoxFeature(shape=(4,), dtype=tf.float32), 'image/filename': Text(shape=(), dtype=tf.string), 'image': Image(shape=(None, None, 3), dtype=tf.uint8), Title = Ĭonfig description: This version contains images, bounding boxes and * Coco defines 91Ĭlasses but the data only uses 80 classes. The test split don't have any annotations (only images). *Ĭoco 20 uses the same images, but different train/val/test splits * Note: * Some images from the train and validation sets don't have annotations. diabetic_retinopathy_detection (manual)ĬOCO is a large-scale object detection, segmentation, and captioning dataset.
0 Comments
Leave a Reply. |