All models

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) link

Model name Detections/Dataset Input size Depth mul. TF ver. Latency 1 Accuracy Model size Downloads

EfficientNet-EdgeTpu (L)

1,000 objects
ILSVRC2012

300x300 N/A 1 24.5 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

240x240 N/A 1 8.4 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

224x224 N/A 1 4.9 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

224x224 N/A 1 3.1 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

224x224 N/A 1 13.0 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

299x299 N/A 1 42.2 ms Top-1: 79.9%
Top-5: 95.7%
24.0 MB

Edge TPU model, CPU model,
Labels file, All model files

Inception V4

1,000 objects
ILSVRC2012

299x299 N/A 1 84.0 ms Top-1: 80.5%
Top-5: 95.7%
43.0 MB

Edge TPU model, CPU model,
Labels file, All model files

MobileNet V1

1,000 objects
ILSVRC2012

128x128 0.25 1 0.6 ms Top-1: 41.2%
Top-5: 66.6%
0.7 MB

Edge TPU model, CPU model,
Labels file

MobileNet V1

1,000 objects
ILSVRC2012

160x160 0.5 1 1.0 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

192x192 0.75 1 1.4 ms Top-1: 67.2%
Top-5: 88.1%
2.9 MB

Edge TPU model, CPU model,
Labels file

MobileNet V1

1,000 objects
ILSVRC2012

224x224 1.0 1 2.3 ms Top-1: 69.5%
Top-5: 90.6%
4.5 MB

Edge TPU model, CPU model,
Labels file, All model files

MobileNet V2

900+ birds
iNaturalist 2017

224x224 1.0 1 2.5 ms N/A 4.1 MB

Edge TPU model, CPU model,
Labels file

MobileNet V2

1000+ insects
iNaturalist 2017

224x224 1.0 1 2.5 ms N/A 4.1 MB

Edge TPU model, CPU model,
Labels file

MobileNet V2

2000+ plants
iNaturalist 2017

224x224 1.0 1 2.6 ms N/A 5.5 MB

Edge TPU model, CPU model,
Labels file

MobileNet V2

1,000 objects
ILSVRC2012

224x224 1.0 1 2.5 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

224x224 1.0 2 2.4 ms Top-1: 69.5%
Top-5: 89.8%
4.6 MB

Edge TPU model, CPU model,
Labels file

MobileNet V2

1,000 objects
ILSVRC2012

224x224 1.0 2 2.5 ms Top-1: 73.2%
Top-5: 91.8%
4.2 MB

Edge TPU model, CPU model,
Labels file

MobileNet V3

1,000 objects
ILSVRC2012

224x224 1.0 2 2.7 ms Top-1: 77.5%
Top-5: 93.6%
5.0 MB

Edge TPU model, CPU model,
Labels file

ResNet-50

1,000 objects
ILSVRC2012

224x224 N/A 2 42.9 ms Top-1: 73.6%
Top-5: 93.8%
25.0 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.

More about image classification

Image classification (on-device training) link

Model name Training style Base dataset Input size TF ver. Model size Downloads

EfficientNet-EdgeTpu (L)

Backpropagation

1,000 objects
ILSVRC2012

300x300 1 11.7 MB

Edge TPU model, CPU model,
Labels file

EfficientNet-EdgeTpu (M)

Backpropagation

1,000 objects
ILSVRC2012

240x240 1 7.6 MB

Edge TPU model, CPU model,
Labels file

EfficientNet-EdgeTpu (S)

Backpropagation

1,000 objects
ILSVRC2012

224x224 1 5.7 MB

Edge TPU model, CPU model,
Labels file

MobileNet V1

Backpropagation

1,000 objects
ILSVRC2012

224x224 1 3.5 MB

Edge TPU model, CPU model,
Labels file

MobileNet V1

Weight imprinting

1,000 objects
ILSVRC2012

224x224 1 5.4 MB

Edge TPU model, CPU model,
Labels file, All model files

More about image classification

Object detection link

Model name Detections/Dataset Input size TF ver. Latency 1 mAP 2 Model size Downloads

SSD MobileNet V1

90 objects
COCO

300x300 1 9.9 ms 21.7% 7.0 MB

Edge TPU model, CPU model,
Labels file, All model files

SSD MobileNet V2

90 objects
COCO

300x300 1 7.4 ms 25.7% 6.6 MB

Edge TPU model, CPU model,
Labels file, All model files

SSD MobileNet V2

Faces

320x320 1 5.0 ms N/A 6.7 MB

Edge TPU model, CPU model, All model files

SSDLite MobileDet

90 objects
COCO

320x320 1 8.0 ms 32.8% 5.1 MB

Edge TPU model, CPU model,
Labels file, All model files

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.

More about object detection

Semantic segmentation link

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

128x128 N/A N/A 1 3.6 ms 7.2 MB

Edge TPU model, CPU model,
Labels file

U-Net MobileNet v2

37 pets
Oxford-IIIT pets

256x256 N/A N/A 1 27.7 ms 7.3 MB

Edge TPU model, CPU model,
Labels file

MobileNet v2 DeepLab v3

20 objects
PASCAL VOC2012

513x513 0.5 N/A 1 43.3 ms 1.1 MB

Edge TPU model, CPU model,
Labels file

MobileNet v2 DeepLab v3

20 objects
PASCAL VOC2012

513x513 1.0 N/A 1 49.4 ms 2.9 MB

Edge TPU model, CPU model,
Labels file

MobileNet v1 BodyPix

24 body parts

512x512 0.75 16 1 10.7 ms 1.7 MB

Edge TPU model

MobileNet v1 BodyPix

24 body parts

480x352 0.75 16 1 N/A 1.6 MB

Edge TPU model

MobileNet v1 BodyPix

24 body parts

640x480 0.75 16 1 N/A 1.8 MB

Edge TPU model

MobileNet v1 BodyPix

24 body parts

768x576 0.75 16 1 N/A 1.8 MB

Edge TPU model

MobileNet v1 BodyPix

24 body parts

1024x768 0.75 16 1 N/A 2.0 MB

Edge TPU model

MobileNet v1 BodyPix

24 body parts

1280x720 0.75 16 1 N/A 2.3 MB

Edge TPU model

ResNet-50 BodyPix

24 body parts

416x288 N/A 16 1 N/A 24.5 MB

Edge TPU model

ResNet-50 BodyPix

24 body parts

640x480 N/A 16 1 N/A 26.6 MB

Edge TPU model

ResNet-50 BodyPix

24 body parts

768x496 N/A 32 1 N/A 26.9 MB

Edge TPU model

ResNet-50 BodyPix

24 body parts

864x624 N/A 32 1 N/A 28.5 MB

Edge TPU model

ResNet-50 BodyPix

24 body parts

928x672 N/A 16 1 N/A 35.3 MB

Edge TPU model

ResNet-50 BodyPix

24 body parts

960x736 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.

More about semantic segmentation

Pose estimation link

Model name Detections/Dataset Input size Output stride TF ver. Latency1 Model size Downloads

PoseNet MobileNet V1

17 body parts

353x481 16 1 5.9 ms 1.5 MB

Edge TPU model, CPU model

PoseNet MobileNet V1

17 body parts

481x641 16 1 10.3 ms 1.7 MB

Edge TPU model, CPU model

PoseNet MobileNet V1

17 body parts

721x1281 16 1 32.9 ms 2.5 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body parts

288x416 16 1 N/A 24.4 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body parts

480x640 16 1 N/A 26.4 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body parts

496x768 32 1 N/A 26.8 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body parts

624x864 32 1 N/A 28.4 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body parts

672x928 16 1 N/A 35.0 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body parts

736x960 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.

More about pose estimation

Speech recognition link

Model name Detections/Dataset Input size Model size Downloads

Keyword Spotter v0.8

140+ phrases

32x198 578 KB

Edge TPU model,
Labels file

More about speech recognition