lucid
lucid copied to clipboard
Using my own dataset for Activation Atlas
This is the provided code to setup the dataset:
data_split = imagenet.get_split(options['split'])
provider = tf.contrib.slim.dataset_data_provider.DatasetDataProvider(data_split, seed=7)
image_tensor, t_label, t_record_key, t_label_text = provider.get(["image", "label", "record_key", "label_text"])
What is the best way to use my own dataset (TFRecord / raw images) instead of the Imagenet one?