Metadata-Version: 2.1
Name: gluoncv2
Version: 0.0.32
Summary: Image classification models for Gluon
Home-page: https://github.com/osmr/imgclsmob
Author: Oleg Sémery
Author-email: osemery@gmail.com
License: MIT
Description: # Image classification models on MXNet/Gluon
        
        [![PyPI](https://img.shields.io/pypi/v/gluoncv2.svg)](https://pypi.python.org/pypi/gluoncv2)
        [![Downloads](https://pepy.tech/badge/gluoncv2)](https://pepy.tech/project/gluoncv2)
        
        This is a collection of image classification models. Many of them are pretrained on ImageNet-1K and CIFAR-10
        datasets and loaded automatically during use. All pretrained models require the same ordinary normalization.
        Scripts for training/evaluating/converting models are in the [`imgclsmob`](https://github.com/osmr/imgclsmob) repo.
        
        ## List of implemented models
        
        - AlexNet (['One weird trick for parallelizing convolutional neural networks'](https://arxiv.org/abs/1404.5997))
        - ZFNet (['Visualizing and Understanding Convolutional Networks'](https://arxiv.org/abs/1311.2901))
        - VGG/BN-VGG (['Very Deep Convolutional Networks for Large-Scale Image Recognition'](https://arxiv.org/abs/1409.1556))
        - BN-Inception (['Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift'](https://arxiv.org/abs/1502.03167))
        - ResNet (['Deep Residual Learning for Image Recognition'](https://arxiv.org/abs/1512.03385))
        - PreResNet (['Identity Mappings in Deep Residual Networks'](https://arxiv.org/abs/1603.05027))
        - ResNeXt (['Aggregated Residual Transformations for Deep Neural Networks'](http://arxiv.org/abs/1611.05431))
        - SENet/SE-ResNet/SE-PreResNet/SE-ResNeXt (['Squeeze-and-Excitation Networks'](https://arxiv.org/abs/1709.01507))
        - IBN-ResNet/IBN-ResNeXt/IBN-DenseNet (['Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net'](https://arxiv.org/abs/1807.09441))
        - AirNet/AirNeXt (['Attention Inspiring Receptive-Fields Network for Learning Invariant Representations'](https://ieeexplore.ieee.org/document/8510896))
        - BAM-ResNet (['BAM: Bottleneck Attention Module'](https://arxiv.org/abs/1807.06514))
        - CBAM-ResNet (['CBAM: Convolutional Block Attention Module'](https://arxiv.org/abs/1807.06521))
        - ResAttNet (['Residual Attention Network for Image Classification'](https://arxiv.org/abs/1704.06904))
        - PyramidNet (['Deep Pyramidal Residual Networks'](https://arxiv.org/abs/1610.02915))
        - DiracNetV2 (['DiracNets: Training Very Deep Neural Networks Without Skip-Connections'](https://arxiv.org/abs/1706.00388))
        - DenseNet (['Densely Connected Convolutional Networks'](https://arxiv.org/abs/1608.06993))
        - CondenseNet (['CondenseNet: An Efficient DenseNet using Learned Group Convolutions'](https://arxiv.org/abs/1711.09224))
        - SparseNet (['Sparsely Aggregated Convolutional Networks'](https://arxiv.org/abs/1801.05895))
        - PeleeNet (['Pelee: A Real-Time Object Detection System on Mobile Devices'](https://arxiv.org/abs/1804.06882))
        - WRN (['Wide Residual Networks'](https://arxiv.org/abs/1605.07146))
        - DRN-C/DRN-D (['Dilated Residual Networks'](https://arxiv.org/abs/1705.09914))
        - DPN (['Dual Path Networks'](https://arxiv.org/abs/1707.01629))
        - DarkNet Ref/Tiny/19 (['Darknet: Open source neural networks in c'](https://github.com/pjreddie/darknet))
        - DarkNet-53 (['YOLOv3: An Incremental Improvement'](https://arxiv.org/abs/1804.02767))
        - ChannelNet (['ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions'](https://arxiv.org/abs/1809.01330))
        - MSDNet (['Multi-Scale Dense Networks for Resource Efficient Image Classification'](https://arxiv.org/abs/1703.09844))
        - FishNet (['FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction'](http://papers.nips.cc/paper/7356-fishnet-a-versatile-backbone-for-image-region-and-pixel-level-prediction.pdf))
        - SqueezeNet/SqueezeResNet (['SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size'](https://arxiv.org/abs/1602.07360))
        - SqueezeNext (['SqueezeNext: Hardware-Aware Neural Network Design'](https://arxiv.org/abs/1803.10615))
        - ShuffleNet (['ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices'](https://arxiv.org/abs/1707.01083))
        - ShuffleNetV2 (['ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design'](https://arxiv.org/abs/1807.11164))
        - MENet (['Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications'](https://arxiv.org/abs/1803.09127))
        - MobileNet (['MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications'](https://arxiv.org/abs/1704.04861))
        - FD-MobileNet (['FD-MobileNet: Improved MobileNet with A Fast Downsampling Strategy'](https://arxiv.org/abs/1802.03750))
        - MobileNetV2 (['MobileNetV2: Inverted Residuals and Linear Bottlenecks'](https://arxiv.org/abs/1801.04381))
        - IGCV3 (['IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks'](https://arxiv.org/abs/1806.00178))
        - MnasNet (['MnasNet: Platform-Aware Neural Architecture Search for Mobile'](https://arxiv.org/abs/1807.11626))
        - DARTS (['DARTS: Differentiable Architecture Search'](https://arxiv.org/abs/1806.09055))
        - Xception (['Xception: Deep Learning with Depthwise Separable Convolutions'](https://arxiv.org/abs/1610.02357))
        - InceptionV3 (['Rethinking the Inception Architecture for Computer Vision'](https://arxiv.org/abs/1512.00567))
        - InceptionV4/InceptionResNetV2 (['Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning'](https://arxiv.org/abs/1602.07261))
        - PolyNet (['PolyNet: A Pursuit of Structural Diversity in Very Deep Networks'](https://arxiv.org/abs/1611.05725))
        - NASNet (['Learning Transferable Architectures for Scalable Image Recognition'](https://arxiv.org/abs/1707.07012))
        - PNASNet (['Progressive Neural Architecture Search'](https://arxiv.org/abs/1712.00559))
        
        ## Installation
        
        To use the models in your project, simply install the `gluoncv2` package with `mxnet`:
        ```
        pip install gluoncv2 mxnet>=1.2.1
        ```
        To enable different hardware supports such as GPUs, check out [MXNet variants](https://pypi.org/project/mxnet).
        For example, you can install with CUDA-9.2 supported MXNet:
        ```
        pip install gluoncv2 mxnet-cu92>=1.2.1
        ```
        
        ## Usage
        
        Example of using the pretrained ResNet-18 model:
        ```
        from gluoncv2.model_provider import get_model as glcv2_get_model
        import mxnet as mx
        
        net = glcv2_get_model("resnet18", pretrained=True)
        x = mx.nd.zeros((1, 3, 224, 224), ctx=mx.cpu())
        y = net(x)
        ```
        
        ## Pretrained models
        
        ### Imagenet-1K
        
        Some remarks:
        - Top1/Top5 are the standard 1-crop Top-1/Top-5 errors (in percents) on the validation subset of the ImageNet-1K dataset.
        - FLOPs/2 is the number of FLOPs divided by two to be similar to the number of MACs.
        - ResNet/PreResNet with b-suffix is a version of the networks with the stride in the second convolution of the
        bottleneck block. Respectively a network without b-suffix has the stride in the first convolution.
        - ResNet/PreResNet models do not use biases in convolutions at all.
        - CondenseNet models are only so-called converted versions.
        - ShuffleNetV2/ShuffleNetV2b/ShuffleNetV2c are different implementations of the same architecture.
        
        | Model | Top1 | Top5 | Params | FLOPs/2 | Remarks |
        | --- | ---: | ---: | ---: | ---: | --- |
        | AlexNet | 44.12 | 21.26 | 61,100,840 | 714.83M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.108/alexnet-2126-9cb87ebd.params.log)) |
        | VGG-11 | 31.91 | 11.76 | 132,863,336 | 7,615.87M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.109/vgg11-1176-95dd287d.params.log)) |
        | VGG-13 | 31.06 | 11.12 | 133,047,848 | 11,317.65M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.109/vgg13-1112-a0db3c6c.params.log)) |
        | VGG-16 | 26.78 | 8.69 | 138,357,544 | 15,480.10M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.109/vgg16-0869-57a2556f.params.log)) |
        | VGG-19 | 25.88 | 8.23 | 143,667,240 | 19,642.55M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.109/vgg19-0823-0e2a1e0a.params.log)) |
        | BN-VGG-11b | 30.34 | 10.57 | 132,868,840 | 7,630.72M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.110/bn_vgg11b-1057-b2d8f382.params.log)) |
        | BN-VGG-13b | 29.48 | 10.16 | 133,053,736 | 11,342.14M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.110/bn_vgg13b-1016-f384ff52.params.log)) |
        | BN-VGG-16b | 26.89 | 8.65 | 138,365,992 | 15,507.20M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.110/bn_vgg16b-0865-b5e33db8.params.log)) |
        | BN-VGG-19b | 25.66 | 8.15 | 143,678,248 | 19,672.26M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.110/bn_vgg19b-0815-3a0e43e6.params.log)) |
        | BN-Inception | 25.09 | 7.76 | 11,295,240 | 2,048.06M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.139/bninception-0776-8314001b.params.log)) |
        | ResNet-10 | 37.09 | 15.55 | 5,418,792 | 894.04M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.1/resnet10-1555-cfb0a76d.params.log)) |
        | ResNet-12 | 35.86 | 14.46 | 5,492,776 | 1,126.25M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.30/resnet12-1446-9ce715b0.params.log)) |
        | ResNet-14 | 32.85 | 12.41 | 5,788,200 | 1,357.94M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.40/resnet14-1241-a8955ff3.params.log)) |
        | ResNet-16 | 30.68 | 11.10 | 6,968,872 | 1,589.34M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.41/resnet16-1110-1be996d1.params.log)) |
        | ResNet-18 x0.25 | 49.16 | 24.45 | 831,096 | 137.32M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.47/resnet18_wd4-2445-28d15cf4.params.log)) |
        | ResNet-18 x0.5 | 36.54 | 14.96 | 3,055,880 | 486.49M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.46/resnet18_wd2-1496-d839c509.params.log)) |
        | ResNet-18 x0.75 | 33.25 | 12.54 | 6,675,352 | 1,047.53M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.18/resnet18_w3d4-1254-d6548612.params.log)) |
        | ResNet-18 | 28.09 | 9.51 | 11,689,512 | 1,820.41M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.153/resnet18-0951-98a2545b.params.log)) |
        | ResNet-34 | 25.34 | 7.92 | 21,797,672 | 3,672.68M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.1/resnet34-0792-5b875f49.params.log)) |
        | ResNet-50 | 22.65 | 6.41 | 25,557,032 | 3,877.95M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.147/resnet50-0641-1eaa883b.params.log)) |
        | ResNet-50b | 22.32 | 6.18 | 25,557,032 | 4,110.48M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.146/resnet50b-0618-8e2541fb.params.log)) |
        | ResNet-101 | 21.66 | 5.99 | 44,549,160 | 7,597.95M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.1/resnet101-0599-a6d3a5f4.params.log)) |
        | ResNet-101b | 20.79 | 5.39 | 44,549,160 | 7,830.48M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.145/resnet101b-0539-7406d858.params.log)) |
        | ResNet-152 | 20.76 | 5.35 | 60,192,808 | 11,321.85M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.144/resnet152-0535-bbdd7ed1.params.log)) |
        | ResNet-152b | 20.31 | 5.25 | 60,192,808 | 11,554.38M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.143/resnet152b-0525-6f30d0d9.params.log)) |
        | PreResNet-18 | 28.16 | 9.51 | 11,687,848 | 1,820.56M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.140/preresnet18-0951-71279a0b.params.log)) |
        | PreResNet-34 | 25.88 | 8.11 | 21,796,008 | 3,672.83M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet34-0811-f8fe98a2.params.log)) |
        | PreResNet-50 | 23.39 | 6.68 | 25,549,480 | 3,875.44M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet50-0668-4940c94b.params.log)) |
        | PreResNet-50b | 23.16 | 6.64 | 25,549,480 | 4,107.97M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet50b-0664-2fcfddb1.params.log)) |
        | PreResNet-101 | 21.45 | 5.75 | 44,541,608 | 7,595.44M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet101-0575-e2887e53.params.log)) |
        | PreResNet-101b | 21.73 | 5.88 | 44,541,608 | 7,827.97M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet101b-0588-1015145a.params.log)) |
        | PreResNet-152 | 20.70 | 5.32 | 60,185,256 | 11,319.34M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.14/preresnet152-0532-31505f71.params.log)) |
        | PreResNet-152b | 21.00 | 5.75 | 60,185,256 | 11,551.87M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet152b-0575-dc303191.params.log)) |
        | PreResNet-200b | 21.10 | 5.64 | 64,666,280 | 15,068.63M | From [tornadomeet/ResNet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.45/preresnet200b-0564-38f849a6.params.log)) |
        | ResNeXt-101 (32x4d) | 21.32 | 5.79 | 44,177,704 | 8,003.45M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.10/resnext101_32x4d-0579-9afbfdbc.params.log)) |
        | ResNeXt-101 (64x4d) | 20.60 | 5.41 | 83,455,272 | 15,500.27M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.10/resnext101_64x4d-0541-0d4fd87b.params.log)) |
        | SE-ResNet-50 | 22.51 | 6.44 | 28,088,024 | 3,880.49M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.11/seresnet50-0644-10954a84.params.log)) |
        | SE-ResNet-101 | 21.92 | 5.89 | 49,326,872 | 7,602.76M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.11/seresnet101-0589-4c10238d.params.log)) |
        | SE-ResNet-152 | 21.48 | 5.77 | 66,821,848 | 11,328.52M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.11/seresnet152-0577-de6f099d.params.log)) |
        | SE-ResNeXt-50 (32x4d) | 21.06 | 5.58 | 27,559,896 | 4,258.40M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.12/seresnext50_32x4d-0558-a49f8fb0.params.log)) |
        | SE-ResNeXt-101 (32x4d) | 19.99 | 5.00 | 48,955,416 | 8,008.26M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.12/seresnext101_32x4d-0500-cf161260.params.log)) |
        | SENet-154 | 18.84 | 4.65 | 115,088,984 | 20,745.78M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.13/senet154-0465-dd244507.params.log)) |
        | IBN-ResNet-50 | 23.56 | 6.68 | 25,557,032 | 4,110.48M | From [XingangPan/IBN-Net] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.127/ibn_resnet50-0668-db527596.params.log)) |
        | IBN-ResNet-101 | 21.89 | 5.87 | 44,549,160 | 7,830.48M | From [XingangPan/IBN-Net] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.127/ibn_resnet101-0587-946e7f10.params.log)) |
        | IBN(b)-ResNet-50 | 23.91 | 6.97 | 25,558,568 | 4,112.89M | From [XingangPan/IBN-Net] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.127/ibnb_resnet50-0697-0aea51d2.params.log)) |
        | IBN-ResNeXt-101 (32x4d) | 21.43 | 5.62 | 44,177,704 | 8,003.45M | From [XingangPan/IBN-Net] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.127/ibn_resnext101_32x4d-0562-05ddba79.params.log)) |
        | IBN-DenseNet-121 | 24.98 | 7.47 | 7,978,856 | 2,872.13M | From [XingangPan/IBN-Net] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.127/ibn_densenet121-0747-1434d379.params.log)) |
        | IBN-DenseNet-169 | 23.78 | 6.82 | 14,149,480 | 3,403.89M | From [XingangPan/IBN-Net] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.127/ibn_densenet169-0682-6d7c48c5.params.log)) |
        | AirNet50-1x64d (r=2) | 22.48 | 6.21 | 27,425,864 | 4,772.11M | From [soeaver/AirNet-PyTorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.120/airnet50_1x64d_r2-0621-347358cc.params.log)) |
        | AirNet50-1x64d (r=16) | 22.91 | 6.46 | 25,714,952 | 4,399.97M | From [soeaver/AirNet-PyTorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.120/airnet50_1x64d_r16-0646-0b847b99.params.log)) |
        | AirNeXt50-32x4d (r=2) | 21.51 | 5.75 | 27,604,296 | 5,339.58M | From [soeaver/AirNet-PyTorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.120/airnext50_32x4d_r2-0575-ab104fb5.params.log)) |
        | BAM-ResNet-50 | 23.68 | 6.96 | 25,915,099 | 4,196.09M | From [Jongchan/attention-module] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.124/bam_resnet50-0696-7e573b61.params.log)) |
        | CBAM-ResNet-50 | 23.02 | 6.38 | 28,089,624 | 4,116.97M | From [Jongchan/attention-module] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.125/cbam_resnet50-0638-78be5665.params.log)) |
        | PyramidNet-101 (a=360) | 22.72 | 6.52 | 42,455,070 | 8,743.54M | From [dyhan0920/Pyramid...PyTorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.104/pyramidnet101_a360-0652-08d5a5d1.params.log)) |
        | DiracNetV2-18 | 30.61 | 11.17 | 11,511,784 | 1,796.62M | From [szagoruyko/diracnets] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.111/diracnet18v2-1117-27601f6f.params.log)) |
        | DiracNetV2-34 | 27.93 | 9.46 | 21,616,232 | 3,646.93M | From [szagoruyko/diracnets] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.111/diracnet34v2-0946-1faa6f12.params.log)) |
        | DenseNet-121 | 25.11 | 7.80 | 7,978,856 | 2,872.13M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.3/densenet121-0780-49b72d04.params.log)) |
        | DenseNet-161 | 22.40 | 6.18 | 28,681,000 | 7,793.16M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.3/densenet161-0618-52e30516.params.log)) |
        | DenseNet-169 | 23.89 | 6.89 | 14,149,480 | 3,403.89M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.3/densenet169-0689-281ec06b.params.log)) |
        | DenseNet-201 | 22.71 | 6.36 | 20,013,928 | 4,347.15M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.3/densenet201-0636-65b5d389.params.log)) |
        | CondenseNet-74 (C=G=4) | 26.82 | 8.64 | 4,773,944 | 546.06M | From [ShichenLiu/CondenseNet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.4/condensenet74_c4_g4-0864-cde68fa2.params.log)) |
        | CondenseNet-74 (C=G=8) | 29.76 | 10.49 | 2,935,416 | 291.52M | From [ShichenLiu/CondenseNet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.4/condensenet74_c8_g8-1049-4cf4a08e.params.log)) |
        | PeleeNet | 31.71 | 11.25 | 2,802,248 | 514.87M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.141/peleenet-1125-38d4fb24.params.log)) |
        | WRN-50-2 | 22.15 | 6.12 | 68,849,128 | 11,405.42M | From [szagoruyko/functional-zoo] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.113/wrn50_2-0612-f8013e68.params.log)) |
        | DRN-C-26 | 25.68 | 7.89 | 21,126,584 | 16,993.90M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnc26-0789-ee56ffab.params.log)) |
        | DRN-C-42 | 23.80 | 6.92 | 31,234,744 | 25,093.75M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnc42-0692-f89c26d6.params.log)) |
        | DRN-C-58 | 22.35 | 6.27 | 40,542,008 | 32,489.94M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnc58-0627-44cbf15c.params.log)) |
        | DRN-D-22 | 26.67 | 8.52 | 16,393,752 | 13,051.33M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnd22-0852-08574752.params.log)) |
        | DRN-D-38 | 24.51 | 7.36 | 26,501,912 | 21,151.19M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnd38-0736-c7d53bc0.params.log)) |
        | DRN-D-54 | 22.05 | 6.27 | 35,809,176 | 28,547.38M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnd54-0627-87d44c87.params.log)) |
        | DRN-D-105 | 21.31 | 5.81 | 54,801,304 | 43,442.43M | From [fyu/drn] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.116/drnd105-0581-ab12d662.params.log)) |
        | DPN-68 | 23.57 | 7.00 | 12,611,602 | 2,351.84M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.17/dpn68-0700-3114719d.params.log)) |
        | DPN-98 | 20.23 | 5.28 | 61,570,728 | 11,716.51M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.17/dpn98-0528-fa5d6fca.params.log)) |
        | DPN-131 | 20.03 | 5.22 | 79,254,504 | 16,076.15M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.17/dpn131-0522-35ac2f82.params.log)) |
        | DarkNet Tiny | 40.31 | 17.46 | 1,042,104 | 500.85M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.69/darknet_tiny-1746-16501793.params.log)) |
        | DarkNet Ref | 38.00 | 16.68 | 7,319,416 | 367.59M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.64/darknet_ref-1668-3011b4e1.params.log)) |
        | DarkNet-53 | 21.44 | 5.56 | 41,609,928 | 7,133.86M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.150/darknet53-0556-e9486353.params.log)) |
        | FishNet-150 | 22.85 | 6.38 | 24,959,400 | 6,435.02M | From [kevin-ssy/FishNet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.168/fishnet150-0638-5cbd08ec.params.log)) |
        | SqueezeNet v1.0 | 38.73 | 17.34 | 1,248,424 | 823.67M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.128/squeezenet_v1_0-1734-e6f8b0e8.params.log)) |
        | SqueezeNet v1.1 | 39.09 | 17.39 | 1,235,496 | 352.02M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.88/squeezenet_v1_1-1739-d7a1483a.params.log)) |
        | SqueezeResNet v1.1 | 39.83 | 17.84 | 1,235,496 | 352.02M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.70/squeezeresnet_v1_1-1784-26064b82.params.log)) |
        | 1.0-SqNxt-23 | 42.25 | 18.66 | 724,056 | 287.28M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.171/sqnxt23_w1-1866-73b700c4.params.log)) |
        | 1.0-SqNxt-23v5 | 40.43 | 17.43 | 921,816 | 285.82M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.172/sqnxt23v5_w1-1743-7a83722e.params.log)) |
        | ShuffleNet x0.25 (g=1) | 62.00 | 36.77 | 209,746 | 12.35M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.134/shufflenet_g1_wd4-3677-ee58f368.params.log)) |
        | ShuffleNet x0.25 (g=3) | 61.34 | 36.17 | 305,902 | 13.09M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.135/shufflenet_g3_wd4-3617-bd08e3ed.params.log)) |
        | ShuffleNet x0.5 (g=3) | 43.83 | 20.60 | 718,324 | 41.70M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.167/shufflenet_g3_wd2-2060-ea6737a5.params.log)) |
        | ShuffleNetV2 x0.5 | 40.61 | 18.30 | 1,366,792 | 43.31M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.90/shufflenetv2_wd2-1830-156953de.params.log)) |
        | ShuffleNetV2 x1.0 | 30.94 | 11.23 | 2,278,604 | 149.72M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.133/shufflenetv2_w1-1123-27435039.params.log)) |
        | ShuffleNetV2 x1.5 | 32.38 | 12.37 | 4,406,098 | 320.77M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.65/shufflenetv2_w3d2-1237-08c01388.params.log)) |
        | ShuffleNetV2 x2.0 | 32.04 | 12.10 | 7,601,686 | 595.84M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.84/shufflenetv2_w2-1210-544b55d9.params.log)) |
        | ShuffleNetV2b x0.5 | 39.81 | 17.82 | 1,366,792 | 43.31M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.157/shufflenetv2b_wd2-1782-845a9c43.params.log)) |
        | ShuffleNetV2b x1.0 | 30.39 | 11.01 | 2,279,760 | 150.62M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.161/shufflenetv2b_w1-1101-f679702f.params.log)) |
        | ShuffleNetV2c x0.5 | 39.87 | 18.11 | 1,366,792 | 43.31M | From [tensorpack/tensorpack] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.91/shufflenetv2c_wd2-1811-979ce7d9.params.log)) |
        | ShuffleNetV2c x1.0 | 30.74 | 11.38 | 2,279,760 | 150.62M | From [tensorpack/tensorpack] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.95/shufflenetv2c_w1-1138-646f3b78.params.log)) |
        | 108-MENet-8x1 (g=3) | 43.62 | 20.30 | 654,516 | 42.68M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.89/menet108_8x1_g3-2030-aa07f925.params.log)) |
        | 128-MENet-8x1 (g=4) | 42.10 | 19.13 | 750,796 | 45.98M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.103/menet128_8x1_g4-1913-0c890a76.params.log)) |
        | 128-MENet-8x1 (g=4) | 42.10 | 19.13 | 750,796 | 45.98M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.103/menet128_8x1_g4-1913-0c890a76.params.log)) |
        | 160-MENet-8x1 (g=8) | 43.47 | 20.28 | 850,120 | 45.63M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.154/menet160_8x1_g8-2028-4f28279a.params.log)) |
        | 256-MENet-12x1 (g=4) | 32.23 | 12.16 | 1,888,240 | 150.65M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.152/menet256_12x1_g4-1216-7caf63d1.params.log)) |
        | 348-MENet-12x1 (g=3) | 31.17 | 11.41 | 3,368,128 | 312.00M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.6/menet348_12x1_g3-1141-ac69b246.params.log)) |
        | 352-MENet-12x1 (g=8) | 34.70 | 13.75 | 2,272,872 | 157.35M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.6/menet352_12x1_g8-1375-85779b8a.params.log)) |
        | 456-MENet-24x1 (g=3) | 29.57 | 10.43 | 5,304,784 | 567.90M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.6/menet456_24x1_g3-1043-6e777068.params.log)) |
        | MobileNet x0.25 | 45.78 | 22.18 | 470,072 | 44.09M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.62/mobilenet_wd4-2218-3185cdd2.params.log)) |
        | MobileNet x0.5 | 33.94 | 13.30 | 1,331,592 | 155.42M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.156/mobilenet_wd2-1330-94f13ae1.params.log)) |
        | MobileNet x0.75 | 29.85 | 10.51 | 2,585,560 | 333.99M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.130/mobilenet_w3d4-1051-6361d4b4.params.log)) |
        | MobileNet x1.0 | 26.43 | 8.65 | 4,231,976 | 579.80M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.155/mobilenet_w1-0865-eafd91e9.params.log)) |
        | FD-MobileNet x0.25 | 56.19 | 31.38 | 383,160 | 12.95M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.68/fdmobilenet_wd4-3138-2fe432fd.params.log)) |
        | FD-MobileNet x0.5 | 42.62 | 19.69 | 993,928 | 41.84M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.83/fdmobilenet_wd2-1969-242b9fa8.params.log)) |
        | FD-MobileNet x0.75 | 37.91 | 16.01 | 1,833,304 | 86.68M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.159/fdmobilenet_w3d4-1601-cb10c3e1.params.log)) |
        | FD-MobileNet x1.0 | 33.80 | 13.12 | 2,901,288 | 147.46M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.162/fdmobilenet_w1-1312-95fa0092.params.log)) |
        | MobileNetV2 x0.25 | 48.08 | 24.12 | 1,516,392 | 34.24M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.137/mobilenetv2_wd4-2412-d92b5b2d.params.log)) |
        | MobileNetV2 x0.5 | 35.63 | 14.42 | 1,964,736 | 100.13M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.170/mobilenetv2_wd2-1442-d7c586c7.params.log)) |
        | MobileNetV2 x0.75 | 30.82 | 11.26 | 2,627,592 | 198.50M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.9/mobilenetv2_w3d4-1126-152672f5.params.log)) |
        | MobileNetV2 x1.0 | 28.51 | 9.90 | 3,504,960 | 329.36M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.9/mobilenetv2_w1-0990-4e1a3878.params.log)) |
        | IGCV3 x0.25 | 53.43 | 28.30 | 1,534,020 | 41.29M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.142/igcv3_wd4-2830-71abf6e0.params.log)) |
        | IGCV3 x0.5 | 39.41 | 17.03 | 1,985,528 | 111.12M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.132/igcv3_wd2-1703-145b7089.params.log)) |
        | IGCV3 x1.0 | 28.22 | 9.54 | 3,491,688 | 340.79M | From [homles11/IGCV3] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.126/igcv3_w1-0954-ae026c8c.params.log)) |
        | MnasNet | 31.32 | 11.44 | 4,308,816 | 317.67M | From [zeusees/Mnasnet...Model] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.117/mnasnet-1144-c972fec0.params.log)) |
        | DARTS | 27.23 | 8.97 | 4,718,752 | 539.86M | From [quark0/darts] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.118/darts-0897-aafd6452.params.log)) |
        | Xception | 20.99 | 5.56 | 22,855,952 | 8,403.63M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.115/xception-0556-bd2c1684.params.log)) |
        | InceptionV3 | 21.22 | 5.59 | 23,834,568 | 5,743.06M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.92/inceptionv3-0559-6c087967.params.log)) |
        | InceptionV4 | 20.60 | 5.25 | 42,679,816 | 12,304.93M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.105/inceptionv4-0525-f7aa9536.params.log)) |
        | InceptionResNetV2 | 19.96 | 4.94 | 55,843,464 | 13,188.64M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.107/inceptionresnetv2-0494-3328f7fa.params.log)) |
        | PolyNet | 19.09 | 4.53 | 95,366,600 | 34,821.34M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.96/polynet-0453-74280314.params.log)) |
        | NASNet-A 4@1056 | 25.37 | 7.95 | 5,289,978 | 584.90M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.97/nasnet_4a1056-0795-5c78908e.params.log)) |
        | NASNet-A 6@4032 | 18.17 | 4.24 | 88,753,150 | 23,976.44M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.101/nasnet_6a4032-0424-73cca5fe.params.log)) |
        | PNASNet-5-Large | 17.90 | 4.28 | 86,057,668 | 25,140.77M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.114/pnasnet5large-0428-998a548f.params.log)) |
        
        ### CIFAR-10
        
        Some remarks:
        - Testing subset is used for validation purpose.
        
        | Model | Error, % | Params | FLOPs/2 | Remarks |
        | --- | ---: | ---: | ---: | --- |
        | ResNet-20 | 5.97 | 272,474 | 41.29M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.163/resnet20_cifar10-0597-13c5ab19.params.log)) |
        | ResNet-56 | 4.52 | 855,770 | 127.06M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.163/resnet56_cifar10-0452-a73e63e9.params.log)) |
        | ResNet-110 | 3.69 | 1,730,714 | 255.70M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.163/resnet110_cifar10-0369-f89f1c4d.params.log)) |
        | PreResNet-20 | 6.51 | 272,282 | 41.27M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.164/preresnet20_cifar10-0651-daa89573.params.log)) |
        | PreResNet-56 | 4.49 | 855,578 | 127.03M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.164/preresnet56_cifar10-0449-cb37cb9d.params.log)) |
        | PreResNet-110 | 3.86 | 1,730,522 | 255.68M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.164/preresnet110_cifar10-0386-d6d4b7bd.params.log)) |
        | ResNeXt-29 (32x4d) | 3.15 | 4,775,754 | 780.55M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.169/resnext29_32x4d_cifar10-0315-c8a1beda.params.log)) |
        | ResNeXt-29 (16x64d) | 2.75 | 68,155,210 | 10,709.34M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.165/resnext29_16x64d_cifar10-0275-13e5b172.params.log)) |
        | WRN-16-10 | 2.93 | 17,116,634 | 2,414.04M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.166/wrn16_10_cifar10-0293-ecf1c17c.params.log)) |
        | WRN-28-10 | 2.39 | 36,479,194 | 5,246.98M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.166/wrn28_10_cifar10-0239-16f3c8a2.params.log)) |
        | WRN-40-8 | 2.37 | 35,748,314 | 5,176.90M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.166/wrn40_8_cifar10-0237-3b81d261.params.log)) |
        
        [dmlc/gluon-cv]: https://github.com/dmlc/gluon-cv
        [tornadomeet/ResNet]: https://github.com/tornadomeet/ResNet
        [Cadene/pretrained...pytorch]: https://github.com/Cadene/pretrained-models.pytorch
        [ShichenLiu/CondenseNet]: https://github.com/ShichenLiu/CondenseNet
        [clavichord93/MENet]: https://github.com/clavichord93/MENet
        [clavichord93/FD-MobileNet]: https://github.com/clavichord93/FD-MobileNet
        [tensorpack/tensorpack]: https://github.com/tensorpack/tensorpack
        [dyhan0920/Pyramid...PyTorch]: https://github.com/dyhan0920/PyramidNet-PyTorch
        [zeusees/Mnasnet...Model]: https://github.com/zeusees/Mnasnet-Pretrained-Model
        [szagoruyko/diracnets]: https://github.com/szagoruyko/diracnets
        [szagoruyko/functional-zoo]: https://github.com/szagoruyko/functional-zoo
        [fyu/drn]: https://github.com/fyu/drn
        [quark0/darts]: https://github.com/quark0/darts
        [homles11/IGCV3]: https://github.com/homles11/IGCV3
        [soeaver/AirNet-PyTorch]: https://github.com/soeaver/AirNet-PyTorch
        [Jongchan/attention-module]: https://github.com/Jongchan/attention-module
        [XingangPan/IBN-Net]: https://github.com/XingangPan/IBN-Net
        [cypw/CRU-Net]: https://github.com/cypw/CRU-Net
        [kevin-ssy/FishNet]: https://github.com/kevin-ssy/FishNet
        
Keywords: machine-learning deep-learning neuralnetwork image-classification imagenet mxnet gluon vgg resnet pyramidnet diracnet densenet condensenet wrn drn dpn darknet fishnet squeezenet squeezenext shufflenet menet mobilenet igcv3 mnasnet darts xception inception polynet nasnet pnasnet
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Description-Content-Type: text/markdown
