snap-research/EfficientFormer
EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
Combines lightweight convolution blocks with pure transformer layers optimized via latency-driven architecture search, eliminating the need for hybrid CNN designs while achieving MobileNet-level speed. Supports end-to-end deployment pipelines to CoreML and ONNX formats with built-in profiling tools, enabling direct iPhone benchmarking and real-time inference on resource-constrained mobile hardware.
1,109 stars. No commits in the last 6 months.
Stars
1,109
Forks
94
Language
Python
License
—
Last pushed
Aug 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/snap-research/EfficientFormer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
qubvel-org/segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
OSUPCVLab/SegFormer3D
Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image...
tue-mps/eomt
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
jeya-maria-jose/Medical-Transformer
Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image...
davidiommi/Pytorch--3D-Medical-Images-Segmentation--SALMON
Segmentation deep learning ALgorithm based on MONai toolbox: single and multi-label segmentation...