Models - All

This page lists all our trained models that are compiled for the Coral Edge TPU™.

For more information about each model type, including code examples and training scripts, refer to the model-specific pages that are linked on the Models page.

To train a custom model, using transfer learning or by building and training your own model, see our documentation about TensorFlow models on the Edge TPU.

Notice: These are not production-quality models; they are for demonstration purposes only.

Image classification (pre-trained)

Model name	Detections/Dataset	Input size	Depth mul.	TF ver.	Latency ¹	Accuracy	Model size	Downloads
EfficientNet-EdgeTpu (L)^*	1,000 objects ILSVRC2012	300x300x3	N/A	1	21.3 ms	Top-1: 81.2% Top-5: 95.1%	12.8 MB	Edge TPU model, CPU model, Labels file, All model files
EfficientNet-EdgeTpu (M)^*	1,000 objects ILSVRC2012	240x240x3	N/A	1	7.3 ms	Top-1: 80.1% Top-5: 94.5%	8.7 MB	Edge TPU model, CPU model, Labels file, All model files
EfficientNet-EdgeTpu (S)^*	1,000 objects ILSVRC2012	224x224x3	N/A	1	5.0 ms	Top-1: 78.9% Top-5: 94.7%	6.8 MB	Edge TPU model, CPU model, Labels file, All model files
Inception V1	1,000 objects ILSVRC2012	224x224x3	N/A	1	3.4 ms	Top-1: 71.9% Top-5: 92.0%	7.0 MB	Edge TPU model, CPU model, Labels file, All model files
Inception V3	1,000 objects ILSVRC2012	224x224x3	N/A	1	13.4 ms	Top-1: 75.4% Top-5: 93.2%	12.0 MB	Edge TPU model, CPU model, Labels file, All model files
Inception V3	1,000 objects ILSVRC2012	299x299x3	N/A	1	42.8 ms	Top-1: 79.9% Top-5: 95.7%	23.9 MB	Edge TPU model, CPU model, Labels file, All model files
Inception V4	1,000 objects ILSVRC2012	299x299x3	N/A	1	84.7 ms	Top-1: 80.7% Top-5: 95.5%	42.9 MB	Edge TPU model, CPU model, Labels file, All model files
MobileNet V1	1,000 objects ILSVRC2012	128x128x3	0.25	1	0.9 ms	Top-1: 40.8% Top-5: 67.2%	0.7 MB	Edge TPU model, CPU model, Labels file
MobileNet V1	1,000 objects ILSVRC2012	160x160x3	0.5	1	1.4 ms	Top-1: 63.7% Top-5: 83.4%	1.6 MB	Edge TPU model, CPU model, Labels file
MobileNet V1	1,000 objects ILSVRC2012	192x192x3	0.75	1	1.8 ms	Top-1: 67.2% Top-5: 88.1%	2.8 MB	Edge TPU model, CPU model, Labels file
MobileNet V1	1,000 objects ILSVRC2012	224x224x3	1.0	1	2.8 ms	Top-1: 69.5% Top-5: 90.6%	4.4 MB	Edge TPU model, CPU model, Labels file, All model files
MobileNet V2	900+ birds iNaturalist 2017	224x224x3	1.0	1	2.6 ms	N/A	4.1 MB	Edge TPU model, CPU model, Labels file
MobileNet V2	1000+ insects iNaturalist 2017	224x224x3	1.0	1	2.7 ms	N/A	4.1 MB	Edge TPU model, CPU model, Labels file
MobileNet V2	2000+ plants iNaturalist 2017	224x224x3	1.0	1	2.6 ms	N/A	5.5 MB	Edge TPU model, CPU model, Labels file
MobileNet V2	1,000 objects ILSVRC2012	224x224x3	1.0	1	2.9 ms	Top-1: 73.2% Top-5: 90.0%	4.0 MB	Edge TPU model, CPU model, Labels file, All model files
MobileNet V1	1,000 objects ILSVRC2012	224x224x3	1.0	2	2.8 ms	Top-1: 69.5% Top-5: 89.8%	4.5 MB	Edge TPU model, CPU model, Labels file
MobileNet V2	1,000 objects ILSVRC2012	224x224x3	1.0	2	3.0 ms	Top-1: 73.2% Top-5: 91.8%	4.1 MB	Edge TPU model, CPU model, Labels file
MobileNet V3	1,000 objects ILSVRC2012	224x224x3	1.0	2	3.0 ms	Top-1: 77.5% Top-5: 93.6%	4.9 MB	Edge TPU model, CPU model, Labels file
ResNet-50	1,000 objects ILSVRC2012	224x224x3	N/A	2	42.2 ms	Top-1: 73.6% Top-5: 93.8%	25.0 MB	Edge TPU model, CPU model, Labels file
Popular Products V1 New	100,000 popular US products	224x224x3	N/A	1	7.0 ms	N/A	9.8 MB	Edge TPU model, CPU model, TF Hub model, Labels file

¹ Latency is the time to perform one inference, as measured with a Coral USB Accelerator on a desktop CPU. Latency varies between systems and is primarily intended for comparison between models. For more comparisons, see the Performance Benchmarks.

^* Beware that the EfficientNet family of models have unique input quantization values (scale and zero-point) that you must use when preprocessing your input. For example preprocessing code, see the classify_image.py or classify_image.cc examples.

Example code and more about image classification

Image classification (on-device training)

Model name	Training style	Base dataset	Input size	TF ver.	Model size	Downloads
EfficientNet-EdgeTpu (L)	Backpropagation	1,000 objects ILSVRC2012	300x300x3	1	11.7 MB	Edge TPU model, CPU model, Labels file
EfficientNet-EdgeTpu (M)	Backpropagation	1,000 objects ILSVRC2012	240x240x3	1	7.6 MB	Edge TPU model, CPU model, Labels file
EfficientNet-EdgeTpu (S)	Backpropagation	1,000 objects ILSVRC2012	224x224x3	1	5.7 MB	Edge TPU model, CPU model, Labels file
MobileNet V1	Backpropagation	1,000 objects ILSVRC2012	224x224x3	1	3.5 MB	Edge TPU model, CPU model, Labels file
MobileNet V1	Weight imprinting	1,000 objects ILSVRC2012	224x224x3	1	5.3 MB	Edge TPU model, CPU model, Labels file, All model files

Example code and more about image classification

Object detection

Model name	Detections/Dataset	Input size	TF ver.	Latency ¹	mAP ²	Model size	Downloads
SSD MobileNet V1	90 objects COCO	300x300x3	1	6.5 ms	21.5%	7.0 MB	Edge TPU model, CPU model, Labels file, All model files
SSD/FPN MobileNet V1 New	90 objects COCO	640x640x3	2	229.4 ms	31.1%	37.7 MB	Edge TPU model, CPU model, Labels file
SSD MobileNet V2	90 objects COCO	300x300x3	1	7.3 ms	25.6%	6.6 MB	Edge TPU model, CPU model, Labels file, All model files
SSD MobileNet V2 New	90 objects COCO	300x300x3	2	7.6 ms	22.4%	6.7 MB	Edge TPU model, CPU model, Labels file
SSD MobileNet V2	Faces	320x320x3	1	5.2 ms	N/A	6.7 MB	Edge TPU model, CPU model, All model files
SSDLite MobileDet	90 objects COCO	320x320x3	1	9.1 ms	32.9%	5.1 MB	Edge TPU model, CPU model, Labels file, All model files
EfficientDet-Lite0 New	90 objects COCO	320x320x3	2	37.4 ms	30.4%	5.7 MB	Edge TPU model, CPU model, Labels file
EfficientDet-Lite1 New	90 objects COCO	384x384x3	2	56.3 ms	34.3%	7.6 MB	Edge TPU model, CPU model, Labels file
EfficientDet-Lite2 New	90 objects COCO	448x448x3	2	104.6 ms	36.0%	10.2 MB	Edge TPU model, CPU model, Labels file
EfficientDet-Lite3 New	90 objects COCO	512x512x3	2	107.6 ms	39.4%	14.4 MB	Edge TPU model, CPU model, Labels file
EfficientDet-Lite3x^* New	90 objects COCO	640x640x3	2	197.0 ms	43.9%	20.6 MB	Edge TPU model, CPU model, Labels file

¹ Latency is the time to perform one inference, as measured with a Coral USB Accelerator on a desktop CPU. Latency varies between systems and is primarily intended for comparison between models. For more comparisons, see the Performance Benchmarks.

² mAP is the "mean average precision," as specified by the COCO evaluation metrics. Our evaluation uses a subset of the COCO17 dataset.

^* EfficientDet-Lite3x is not compatible with Edge TPUs over USB; it can be used only with PCIe-based devices. Our benchmarks for EfficientDet-Lite3x come from a desktop system paired with the Asus AI Accelerator—your results will vary.

Example code and more about object detection

Semantic segmentation

Model name	Detections/Dataset	Input size	Depth mul.	Output stride	TF ver.	Latency¹	Model size	Downloads
U-Net MobileNet v2	37 pets Oxford-IIIT pets	128x128x3	N/A	N/A	1	2.7 ms	7.2 MB	Edge TPU model, CPU model, Labels file
U-Net MobileNet v2	37 pets Oxford-IIIT pets	256x256x3	N/A	N/A	1	29.0 ms	7.3 MB	Edge TPU model, CPU model, Labels file
MobileNet v2 DeepLab v3	20 objects PASCAL VOC2012	513x513x3	0.5	N/A	1	36.8 ms	1.1 MB	Edge TPU model, CPU model, Labels file
MobileNet v2 DeepLab v3	20 objects PASCAL VOC2012	513x513x3	1.0	N/A	1	43.0 ms	2.9 MB	Edge TPU model, CPU model, Labels file
EdgeTPU-DeepLab-slim New	28 objects Cityscapes	513x513x3	0.75	N/A	1	65.9 ms	3.1 MB	Edge TPU model, CPU model, Model info
MobileNet v1 BodyPix	24 body parts	352x480x3	0.75	16	1	6.9 ms	1.6 MB	Edge TPU model, CPU model
MobileNet v1 BodyPix	24 body parts	512x512x3	0.75	16	1	10.7 ms	1.7 MB	Edge TPU model, CPU model
MobileNet v1 BodyPix	24 body parts	480x640x3	0.75	16	1	12.3 ms	1.8 MB	Edge TPU model, CPU model
MobileNet v1 BodyPix	24 body parts	576x768x3	0.75	16	1	17.7 ms	1.8 MB	Edge TPU model, CPU model
MobileNet v1 BodyPix	24 body parts	768x1024x3	0.75	16	1	30.8 ms	2.0 MB	Edge TPU model, CPU model
MobileNet v1 BodyPix	24 body parts	720x1280x3	0.75	16	1	38.8 ms	2.3 MB	Edge TPU model, CPU model
ResNet-50 BodyPix	24 body parts	288x416x3	N/A	16	1	46.9 ms	24.5 MB	Edge TPU model, CPU model
ResNet-50 BodyPix	24 body parts	480x640x3	N/A	16	1	384.0 ms	26.6 MB	Edge TPU model, CPU model
ResNet-50 BodyPix	24 body parts	496x768x3	N/A	32	1	87.0 ms	26.9 MB	Edge TPU model, CPU model
ResNet-50 BodyPix	24 body parts	624x864x3	N/A	32	1	153.5 ms	28.5 MB	Edge TPU model, CPU model
ResNet-50 BodyPix	24 body parts	672x928x3	N/A	16	1	737.2 ms	35.3 MB	Edge TPU model, CPU model
ResNet-50 BodyPix	24 body parts	736x960x3	N/A	32	1	N/A	38.6 MB	Edge TPU model

¹ Latency is the time to perform one inference, as measured with a Coral USB Accelerator on a desktop CPU. Latency varies between systems and is primarily intended for comparison between models. For more comparisons, see the Performance Benchmarks.

If you want to process portrait-orientation images, download BodyPix models for portrait input.

Example code and more about semantic segmentation

Pose estimation

Model name	Detections/Dataset	Input size	Output stride	TF ver.	Latency¹	Model size	Downloads
PoseNet MobileNet V1	17 body points	353x481x3	16	1	5.8 ms	1.5 MB	Edge TPU model, CPU model
PoseNet MobileNet V1	17 body points	481x641x3	16	1	10.3 ms	1.7 MB	Edge TPU model, CPU model
PoseNet MobileNet V1	17 body points	721x1281x3	16	1	32.4 ms	2.5 MB	Edge TPU model, CPU model
MoveNet.SinglePose.Lightning New	17 body points	192x192x3	4	2	7.1 ms	3.1 MB	Edge TPU model, CPU model
MoveNet.SinglePose.Thunder New	17 body points	256x256x3	4	2	13.8 ms	7.5 MB	Edge TPU model, CPU model
PoseNet ResNet-50	17 body points	288x416x3	16	1	N/A	24.4 MB	Edge TPU model, CPU model
PoseNet ResNet-50	17 body points	480x640x3	16	1	N/A	26.4 MB	Edge TPU model, CPU model
PoseNet ResNet-50	17 body points	496x768x3	32	1	N/A	26.8 MB	Edge TPU model, CPU model
PoseNet ResNet-50	17 body points	624x864x3	32	1	N/A	28.4 MB	Edge TPU model, CPU model
PoseNet ResNet-50	17 body points	672x928x3	16	1	N/A	35.0 MB	Edge TPU model, CPU model
PoseNet ResNet-50	17 body points	736x960x3	32	1	N/A	38.5 MB	Edge TPU model, CPU model

¹ Latency is the time to perform one inference, as measured with a Coral USB Accelerator on a desktop CPU. Latency varies between systems and is primarily intended for comparison between models. For more comparisons, see the Performance Benchmarks.

Note: BodyPix is another model that performs pose estimation, but it also provides semantic segmentation output for 24 body parts, so you can find it with the semantic segmentation models.

Example code and more about pose estimation

Speech recognition

Model name	Detections/Dataset	Input size	Model size	Downloads
Keyword Spotter v0.8	140+ phrases	198x32x1	578 KB	Edge TPU model, Labels file

Example code and more about speech recognition

All models

Image classification (pre-trained)

Image classification (on-device training)

Object detection

Semantic segmentation

Pose estimation

Speech recognition

More resources

Image classification (pre-trained) link

Image classification (on-device training) link

Object detection link

Semantic segmentation link

Pose estimation link

Speech recognition link

More resources link

Image classification (pre-trained)

Image classification (on-device training)

Object detection

Semantic segmentation

Pose estimation

Speech recognition

More resources