The following pretrained models are available to use for transfer learning with the Image Classification - TensorFlow algorithm.
The following models vary significantly in size, number of model parameters, training time, and inference latency for any given dataset. The best model for your use case depends on the complexity of your fine-tuning dataset and any requirements that you have on training time, inference latency, or model accuracy.
| Model Name | model_id |
Source |
|---|---|---|
MobileNet V2 1.00 224 |
|
|
MobileNet V2 0.75 224 |
|
|
MobileNet V2 0.50 224 |
|
|
MobileNet V2 0.35 224 |
|
|
MobileNet V2 1.40 224 |
|
|
MobileNet V2 1.30 224 |
|
|
MobileNet V2 |
|
|
Inception V3 |
|
|
Inception V2 |
|
|
Inception V1 |
|
|
Inception V3 Preview |
|
|
Inception ResNet V2 |
|
|
ResNet V2 50 |
|
|
ResNet V2 101 |
|
|
ResNet V2 152 |
|
|
ResNet V1 50 |
|
|
ResNet V1 101 |
|
|
ResNet V1 152 |
|
|
ResNet 50 |
|
|
EfficientNet B0 |
|
|
EfficientNet B1 |
|
|
EfficientNet B2 |
|
|
EfficientNet B3 |
|
|
EfficientNet B4 |
|
|
EfficientNet B5 |
|
|
EfficientNet B6 |
|
|
EfficientNet B7 |
|
|
EfficientNet B0 Lite |
|
|
EfficientNet B1 Lite |
|
|
EfficientNet B2 Lite |
|
|
EfficientNet B3 Lite |
|
|
EfficientNet B4 Lite |
|
|
MobileNet V1 1.00 224 |
|
|
MobileNet V1 1.00 192 |
|
|
MobileNet V1 1.00 160 |
|
|
MobileNet V1 1.00 128 |
|
|
MobileNet V1 0.75 224 |
|
|
MobileNet V1 0.75 192 |
|
|
MobileNet V1 0.75 160 |
|
|
MobileNet V1 0.75 128 |
|
|
MobileNet V1 0.50 224 |
|
|
MobileNet V1 0.50 192 |
|
|
MobileNet V1 1.00 160 |
|
|
MobileNet V1 0.50 128 |
|
|
MobileNet V1 0.25 224 |
|
|
MobileNet V1 0.25 192 |
|
|
MobileNet V1 0.25 160 |
|
|
MobileNet V1 0.25 128 |
|
|
BiT-S R50x1 |
|
|
BiT-S R50x3 |
|
|
BiT-S R101x1 |
|
|
BiT-S R101x3 |
|
|
BiT-M R50x1 |
|
|
BiT-M R50x3 |
|
|
BiT-M R101x1 |
|
|
BiT-M R101x3 |
|
|
BiT-M R50x1 ImageNet-21k |
|
|
BiT-M R50x3 ImageNet-21k |
|
|
BiT-M R101x1 ImageNet-21k |
|
|
BiT-M R101x3 ImageNet-21k |
|
