zoo.models.image.imageclassification package

Submodules

zoo.models.image.imageclassification.image_classification module

class zoo.models.image.imageclassification.image_classification.ImageClassifier(bigdl_type='float')

Bases: zoo.models.image.common.image_model.ImageModel

A pre-trained image classifier model.

:param model_path The path containing the pre-trained model

static load_model(path, weight_path=None, bigdl_type='float')

Load an existing object detection model (with weights).

# Arguments path: The path to save the model. Local file system, HDFS and Amazon S3 are supported.

HDFS path should be like ‘hdfs://[host]:[port]/xxx’. Amazon S3 path should be like ‘s3a://bucket/xxx’.

class zoo.models.image.imageclassification.image_classification.LabelOutput(label_map, clses, probs, bigdl_type='float')

Bases: bigdl.transform.vision.image.FeatureTransformer

Label Output tensor with corresponding real labels on specific dataset clses is the key in ImgFeature where you want to store all sorted mapped labels probs is the key in ImgFeature where you want to store all the sorted probilities for each class

zoo.models.image.imageclassification.image_classification.read_imagenet_label_map()

load imagenet label map

Module contents