Introducing LiteRT : Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite.
Learn more
Send feedback
mediapipe_model_maker.object_detector.SupportedModels
Stay organized with collections
Save and categorize content based on your preferences.
Predefined object detector model specs supported by Model Maker.
Supported models include the following:
MOBILENET_V2: MobileNetV2 256x256 input
MOBILENET_V2_I320: MobileNetV2 320x320 input
MOBILENET_MULTI_AVG: MobileNet-MultiHW-AVG 256x256 input
MOBILENET_MULTI_AVG_I384: MobileNet-MultiHW-AVG 384x384 input
Class Variables
MOBILENET_MULTI_AVG
<SupportedModels.MOBILENET_MULTI_AVG: functools.partial(<class 'mediapipe_model_maker.python.vision.object_detector.model_spec.ModelSpec'>, downloaded_files=DownloadedFiles(path='object_detector/mobilenetmultiavg', url='https://storage.googleapis.com/tf_model_garden/vision/qat/mobilenetv3.5_ssd_coco/mobilenetv3.5_ssd_i256_ckpt.tar.gz', is_folder=True), checkpoint_name='ckpt-277200', input_image_shape=[256, 256, 3], model_id='MobileNetMultiAVG', min_level=3, max_level=7)>
MOBILENET_MULTI_AVG_I384
<SupportedModels.MOBILENET_MULTI_AVG_I384: functools.partial(<class 'mediapipe_model_maker.python.vision.object_detector.model_spec.ModelSpec'>, downloaded_files=DownloadedFiles(path='object_detector/mobilenetmultiavg_i384', url='https://storage.googleapis.com/tf_model_garden/vision/qat/mobilenetv2_ssd_coco/mobilenetv3.5_ssd_i384_ckpt.tar.gz', is_folder=True), checkpoint_name='ckpt-277200', input_image_shape=[384, 384, 3], model_id='MobileNetMultiAVG', min_level=3, max_level=7)>
MOBILENET_V2
<SupportedModels.MOBILENET_V2: functools.partial(<class 'mediapipe_model_maker.python.vision.object_detector.model_spec.ModelSpec'>, downloaded_files=DownloadedFiles(path='object_detector/mobilenetv2_i256', url='https://storage.googleapis.com/tf_model_garden/vision/qat/mobilenetv2_ssd_coco/mobilenetv2_ssd_i256_ckpt.tar.gz', is_folder=True), checkpoint_name='ckpt-277200', input_image_shape=[256, 256, 3], model_id='MobileNetV2', min_level=3, max_level=7)>
MOBILENET_V2_I320
<SupportedModels.MOBILENET_V2_I320: functools.partial(<class 'mediapipe_model_maker.python.vision.object_detector.model_spec.ModelSpec'>, downloaded_files=DownloadedFiles(path='object_detector/mobilenetv2_i320', url='https://storage.googleapis.com/tf_model_garden/vision/qat/mobilenetv2_ssd_coco/mobilenetv2_ssd_i320_ckpt.tar.gz', is_folder=True), checkpoint_name='ckpt-277200', input_image_shape=[320, 320, 3], model_id='MobileNetV2', min_level=3, max_level=6)>
Send feedback
Except 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 . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-05-07 UTC.
Need to tell us more?
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-05-07 UTC."],[],[]]
View source on GitHub