blackfeather-wang / GFNet-Pytorch
A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.
☆181Updated last year
Related projects ⓘ
Alternatives and complementary repositories for GFNet-Pytorch
- Resolution adaptive network☆149Updated 2 years ago
- Code for "Searching for Efficient Multi-Stage Vision Transformers"☆62Updated 3 years ago
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers (CVPR21 Oral)☆139Updated 3 years ago
- [TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, …☆104Updated 2 years ago
- Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation, ECCV 2020 Oral☆66Updated 4 years ago
- [CVPR 2021] CondenseNet V2: Sparse Feature Reactivation for Deep Networks☆85Updated 2 years ago
- [ECCV'20 Oral] MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution☆158Updated 2 years ago
- Accelerating T2t-ViT by 1.6-3.6x.☆246Updated 2 years ago
- (CVPR 2021, Oral) Dynamic Slimmable Network☆228Updated 2 years ago
- ☆115Updated 3 years ago
- Matching Guided Distillation (ECCV 2020)☆64Updated 3 years ago
- ☆108Updated 3 years ago
- ☆98Updated 2 years ago
- A PyTorch toolkit for extremely fast ImageNet training with NVIDIA DALI.☆51Updated 3 years ago
- ☆270Updated 3 years ago
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆69Updated 2 years ago
- [NeurIPS 2020] Balanced Meta-Softmax for Long-Tailed Visual Recognition☆136Updated 2 years ago
- S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)☆63Updated 3 years ago
- [ECCV2020] Knowledge Distillation Meets Self-Supervision☆234Updated last year
- ☆191Updated 3 years ago
- Use lmdb to speed up imagenet dataset☆92Updated 3 years ago
- Official code for our ECCV'22 paper "A Fast Knowledge Distillation Framework for Visual Recognition"☆181Updated 6 months ago
- [ECCV 2020] DADA: Differentiable Automatic Data Augmentation☆189Updated last year
- Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better perfo…☆89Updated 2 years ago
- Implementation of momentum^2 teacher☆120Updated 3 years ago
- [CVPR 2021] Instance Localization for Self-supervised Detection Pretraining☆144Updated 3 years ago
- (ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search☆137Updated 2 years ago
- Official implementation for (Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation, CVPR-2021)☆96Updated 6 months ago
- ☆173Updated 4 years ago
- [CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning☆284Updated 2 years ago