metadata
library_name: pytorch
EfficientNetV2 proposes improved scaling rules and training-aware architectural optimizations, including fused-MBConv blocks, to achieve faster training and better accuracy–efficiency trade-offs than prior EfficientNet models.
Original paper: EfficientNetV2: Smaller Models and Faster Training
EfficientNetV2-S
This model uses the EfficientNetV2-S variant, a compact configuration that balances accuracy, inference latency, and training speed. It is well suited for production image classification and as a backbone in vision pipelines where fast convergence and efficient deployment are important.
Model Configuration:
- Reference implementation: torchvision.models.efficientnet_v2_s
- Original Weight: EfficientNet_V2_S_Weights.IMAGENET1K_V1
- Resolution: 3x384x384
- Support Cooper version:
- Cooper SDK: [2.5.4]
- Cooper Foundry: [2.3]
| Model | Device | compression | Model Link |
|---|---|---|---|
| EfficientNetV2 | N1-655 | Activation_fp16 | Model_Link |
| EfficientNetV2 | CV7 | Activation_fp16 | Model_Link |
| EfficientNetV2 | CV72 | Activation_fp16 | Model_Link |
| EfficientNetV2 | CV75 | Activation_fp16 | Model_Link |