Skip to content

Latest commit

 

History

History
45 lines (37 loc) · 2.73 KB

rexnet.md

File metadata and controls

45 lines (37 loc) · 2.73 KB
Raw

ReXNet

  • Paper：ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network

  • Origin Repo：clovaai/rexnet

  • Code：rexnet.py

  • Evaluate Transforms：

    # backend: pil
# input_size: 224x224
transforms = T.Compose([
    T.Resize(256, interpolation='bicubic'),
    T.CenterCrop(224),
    T.ToTensor(),
    T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

  • Model Details：

    Model Model Name Params (M) FLOPs (G) Top-1 (%) Top-5 (%) Pretrained Model
    ReXNet-1.0 rexnet_1_0 4.8 0.4 77.86 93.87 Download
    ReXNet-1.3 rexnet_1_3 7.6 0.7 79.50 94.68 Download
    ReXNet-1.5 rexnet_1_5 7.6 0.7 80.32 95.17 Download
    ReXNet-2.0 rexnet_2_0 16.0 1.5 81.64 95.66 Download
    ReXNet-3.0 rexnet_3_0 34.0 3.4 82.45 96.26 Download

  • Citation：

    @article{han2020rexnet,
    title = {ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network},
    author = {Han, Dongyoon and Yun, Sangdoo and Heo, Byeongho and Yoo, YoungJoon},
    journal = {arXiv preprint arXiv:2007.00992},
    year = {2020},
}