Image classification and segmentation models for PyTorch
Project description
Computer vision models on PyTorch
This is a collection of image classification, segmentation, detection, and pose estimation models. Many of them are pretrained on
ImageNet1K, CIFAR10/100,
SVHN, CUB2002011,
Pascal VOC2012, ADE20K,
Cityscapes, and COCO datasets and loaded automatically
during use. All pretrained models require the same ordinary normalization. Scripts for training/evaluating/converting
models are in the imgclsmob
repo.
List of implemented models
 AlexNet ('One weird trick for parallelizing convolutional neural networks')
 ZFNet ('Visualizing and Understanding Convolutional Networks')
 VGG/BNVGG ('Very Deep Convolutional Networks for LargeScale Image Recognition')
 BNInception ('Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift')
 ResNet ('Deep Residual Learning for Image Recognition')
 PreResNet ('Identity Mappings in Deep Residual Networks')
 ResNeXt ('Aggregated Residual Transformations for Deep Neural Networks')
 SENet/SEResNet/SEPreResNet/SEResNeXt ('SqueezeandExcitation Networks')
 ResNeSt(A) ('ResNeSt: SplitAttention Networks')
 IBNResNet/IBNResNeXt/IBNDenseNet ('Two at Once: Enhancing Learning and Generalization Capacities via IBNNet')
 AirNet/AirNeXt ('Attention Inspiring ReceptiveFields Network for Learning Invariant Representations')
 BAMResNet ('BAM: Bottleneck Attention Module')
 CBAMResNet ('CBAM: Convolutional Block Attention Module')
 ResAttNet ('Residual Attention Network for Image Classification')
 SKNet ('Selective Kernel Networks')
 SCNet ('Improving Convolutional Networks with SelfCalibrated Convolutions')
 RegNet ('Designing Network Design Spaces')
 DIAResNet ('DIANet: DenseandImplicit Attention Network')
 PyramidNet ('Deep Pyramidal Residual Networks')
 DiracNetV2 ('DiracNets: Training Very Deep Neural Networks Without SkipConnections')
 ShaResNet ('ShaResNet: reducing residual network parameter number by sharing weights')
 DenseNet ('Densely Connected Convolutional Networks')
 CondenseNet ('CondenseNet: An Efficient DenseNet using Learned Group Convolutions')
 SparseNet ('Sparsely Aggregated Convolutional Networks')
 PeleeNet ('Pelee: A RealTime Object Detection System on Mobile Devices')
 OctResNet ('Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution')
 WRN ('Wide Residual Networks')
 WRN1bit ('Training wide residual networks for deployment using a single bit for each weight')
 DRNC/DRND ('Dilated Residual Networks')
 DPN ('Dual Path Networks')
 DarkNet Ref/Tiny/19 ('Darknet: Open source neural networks in c')
 DarkNet53 ('YOLOv3: An Incremental Improvement')
 ChannelNet ('ChannelNets: Compact and Efficient Convolutional Neural Networks via ChannelWise Convolutions')
 iSQRTCOVResNet ('Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization')
 RevNet ('The Reversible Residual Network: Backpropagation Without Storing Activations')
 iRevNet ('iRevNet: Deep Invertible Networks')
 BagNet ('Approximating CNNs with BagoflocalFeatures models works surprisingly well on ImageNet')
 DLA ('Deep Layer Aggregation')
 MSDNet ('MultiScale Dense Networks for Resource Efficient Image Classification')
 FishNet ('FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction')
 ESPNetv2 ('ESPNetv2: A Lightweight, Power Efficient, and General Purpose Convolutional Neural Network')
 HRNet ('Deep HighResolution Representation Learning for Visual Recognition')
 VoVNet ('An Energy and GPUComputation Efficient Backbone Network for RealTime Object Detection')
 SelecSLS ('XNect: Realtime Multiperson 3D Human Pose Estimation with a Single RGB Camera')
 HarDNet ('HarDNet: A Low Memory Traffic Network')
 XDenseNet ('Deep Expander Networks: Efficient Deep Networks from Graph Theory')
 SqueezeNet/SqueezeResNet ('SqueezeNet: AlexNetlevel accuracy with 50x fewer parameters and <0.5MB model size')
 SqueezeNext ('SqueezeNext: HardwareAware Neural Network Design')
 ShuffleNet ('ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices')
 ShuffleNetV2 ('ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design')
 MENet ('Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications')
 MobileNet ('MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications')
 FDMobileNet ('FDMobileNet: Improved MobileNet with A Fast Downsampling Strategy')
 MobileNetV2 ('MobileNetV2: Inverted Residuals and Linear Bottlenecks')
 MobileNetV3 ('Searching for MobileNetV3')
 IGCV3 ('IGCV3: Interleaved LowRank Group Convolutions for Efficient Deep Neural Networks')
 GhostNet ('GhostNet: More Features from Cheap Operations')
 MnasNet ('MnasNet: PlatformAware Neural Architecture Search for Mobile')
 DARTS ('DARTS: Differentiable Architecture Search')
 ProxylessNAS ('ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware')
 FBNet ('FBNet: HardwareAware Efficient ConvNet Design via Differentiable Neural Architecture Search')
 Xception ('Xception: Deep Learning with Depthwise Separable Convolutions')
 InceptionV3 ('Rethinking the Inception Architecture for Computer Vision')
 InceptionV4/InceptionResNetV2 ('Inceptionv4, InceptionResNet and the Impact of Residual Connections on Learning')
 PolyNet ('PolyNet: A Pursuit of Structural Diversity in Very Deep Networks')
 NASNet ('Learning Transferable Architectures for Scalable Image Recognition')
 PNASNet ('Progressive Neural Architecture Search')
 SPNASNet ('SinglePath NAS: Designing HardwareEfficient ConvNets in less than 4 Hours')
 EfficientNet ('EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks')
 MixNet ('MixConv: Mixed Depthwise Convolutional Kernels')
 NIN ('Network In Network')
 RoR3 ('Residual Networks of Residual Networks: Multilevel Residual Networks')
 RiR ('Resnet in Resnet: Generalizing Residual Architectures')
 ResDropResNet ('Deep Networks with Stochastic Depth')
 ShakeShakeResNet ('ShakeShake regularization')
 ShakeDropResNet ('ShakeDrop Regularization for Deep Residual Learning')
 FractalNet ('FractalNet: UltraDeep Neural Networks without Residuals')
 NTSNet ('Learning to Navigate for Finegrained Classification')
 PSPNet ('Pyramid Scene Parsing Network')
 DeepLabv3 ('Rethinking Atrous Convolution for Semantic Image Segmentation')
 FCN8s ('Fully Convolutional Networks for Semantic Segmentation')
 ICNet ('ICNet for RealTime Semantic Segmentation on HighResolution Images')
 FastSCNN ('FastSCNN: Fast Semantic Segmentation Network')
 SINet ('SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder')
 BiSeNet ('BiSeNet: Bilateral Segmentation Network for Realtime Semantic Segmentation')
 DANet ('Dual Attention Network for Scene Segmentation')
 CenterNet ('Objects as Points')
 LFFD ('LFFD: A Light and Fast Face Detector for Edge Devices')
 AlphaPose ('RMPE: Regional Multiperson Pose Estimation')
 SimplePose ('Simple Baselines for Human Pose Estimation and Tracking')
 Lightweight OpenPose ('Realtime 2D MultiPerson Pose Estimation on CPU: Lightweight OpenPose')
 IBPPose ('Simple Pose: Rethinking and Improving a Bottomup Approach for MultiPerson Pose Estimation')
 VOCA ('Capture, Learning, and Synthesis of 3D Speaking Styles')
 Neural Voice Puppetry AudiotoExpression net ('Neural Voice Puppetry: Audiodriven Facial Reenactment')
Installation
To use the models in your project, simply install the pytorchcv
package with torch
(>=0.4.1 is recommended):
pip install pytorchcv torch>=0.4.0
To enable/disable different hardware supports such as GPUs, check out PyTorch installation instructions.
Usage
Example of using a pretrained ResNet18 model:
from pytorchcv.model_provider import get_model as ptcv_get_model
import torch
from torch.autograd import Variable
net = ptcv_get_model("resnet18", pretrained=True)
x = Variable(torch.randn(1, 3, 224, 224))
y = net(x)
Pretrained models
ImageNet1K
Some remarks:
 Top1/Top5 are the standard 1crop Top1/Top5 errors (in percents) on the validation subset of the ImageNet1K dataset.
 FLOPs/2 is the number of FLOPs divided by two to be similar to the number of MACs.
 Remark
Converted from GL model
means that the model was trained onMXNet/Gluon
and then converted to PyTorch.  You may notice that quality estimations are quite different from ones for the corresponding models in other frameworks. This
is due to the fact that the quality is estimated on the standard TorchVision stack of image transformations. Using
OpenCV
Resize
transformation instead of PIL one quality evaluation results will be similar to ones for the Gluon models.  ResNet(A) is an average downsampled ResNet intended for use as an feature extractor in some pose estimation networks.
 ResNet(D) is a dilated ResNet intended for use as an feature extractor in some segmentation networks.
 Models with *suffix use nonstandard preprocessing (see the training log).
Model  Top1  Top5  Params  FLOPs/2  Remarks 

AlexNet  40.96  18.24  62,378,344  1,132.33M  Converted from GL model (log) 
AlexNetb  41.58  19.00  61,100,840  714.83M  Converted from GL model (log) 
ZFNet  39.79  17.27  62,357,608  1,170.33M  Converted from GL model (log) 
ZFNetb  36.37  14.90  107,627,624  2,479.13M  Converted from GL model (log) 
VGG11  29.90  10.36  132,863,336  7,615.87M  Converted from GL model (log) 
VGG13  28.76  9.75  133,047,848  11,317.65M  Converted from GL model (log) 
VGG16  26.98  8.65  138,357,544  15,480.10M  Converted from GL model (log) 
VGG19  25.74  7.90  143,667,240  19,642.55M  Converted from GL model (log) 
BNVGG11  29.01  9.61  132,866,088  7,630.21M  Converted from GL model (log) 
BNVGG13  27.83  9.13  133,050,792  11,341.62M  Converted from GL model (log) 
BNVGG16  25.72  7.79  138,361,768  15,506.38M  Converted from GL model (log) 
BNVGG19  24.13  7.12  143,672,744  19,671.15M  Converted from GL model (log) 
BNVGG11b  29.56  9.96  132,868,840  7,630.72M  Converted from GL model (log) 
BNVGG13b  28.41  9.63  133,053,736  11,342.14M  From dmlc/gluoncv (log) 
BNVGG16b  27.19  8.74  138,365,992  15,507.20M  From dmlc/gluoncv (log) 
BNVGG19b  26.06  8.40  143,678,248  19,672.26M  From dmlc/gluoncv (log) 
BNInception  25.37  7.74  11,295,240  2,048.06M  Converted from GL model (log) 
ResNet10  34.69  14.36  5,418,792  894.04M  Converted from GL model (log) 
ResNet12  33.62  13.28  5,492,776  1,126.25M  Converted from GL model (log) 
ResNet14  32.45  12.46  5,788,200  1,357.94M  Converted from GL model (log) 
ResNetBC14b  30.66  11.51  10,064,936  1,479.12M  Converted from GL model (log) 
ResNet16  30.49  11.18  6,968,872  1,589.34M  Converted from GL model (log) 
ResNet18 x0.25  39.62  17.85  3,937,400  270.94M  Converted from GL model (log) 
ResNet18 x0.5  33.80  13.27  5,804,296  608.70M  Converted from GL model (log) 
ResNet18 x0.75  30.40  11.06  8,476,056  1,129.45M  Converted from GL model (log) 
ResNet18  28.03  9.41  11,689,512  1,820.41M  Converted from GL model (log) 
ResNet26  26.30  8.54  17,960,232  2,746.79M  Converted from GL model (log) 
ResNetBC26b  25.09  7.97  15,995,176  2,356.67M  Converted from GL model (log) 
ResNet34  24.84  7.80  21,797,672  3,672.68M  Converted from GL model (log) 
ResNetBC38b  23.69  7.00  21,925,416  3,234.21M  Converted from GL model (log) 
ResNet50  22.28  6.33  25,557,032  3,877.95M  Converted from GL model (log) 
ResNet50b  22.39  6.38  25,557,032  4,110.48M  Converted from GL model (log) 
ResNet101  21.90  6.22  44,549,160  7,597.95M  From dmlc/gluoncv (log) 
ResNet101b  20.59  5.30  44,549,160  7,830.48M  Converted from GL model (log) 
ResNet152  21.01  5.50  60,192,808  11,321.85M  From dmlc/gluoncv (log) 
ResNet152b  19.92  4.99  60,192,808  11,554.38M  Converted from GL model (log) 
PreResNet10  35.11  14.21  5,417,128  894.19M  Converted from GL model (log) 
PreResNet12  33.86  13.48  5,491,112  1,126.40M  Converted from GL model (log) 
PreResNet14  32.64  12.39  5,786,536  1,358.09M  Converted from GL model (log) 
PreResNetBC14b  31.29  11.81  10,057,384  1,476.62M  Converted from GL model (log) 
PreResNet16  30.53  11.08  6,967,208  1,589.49M  Converted from GL model (log) 
PreResNet18 x0.25  40.06  18.11  3,935,960  270.93M  Converted from GL model (log) 
PreResNet18 x0.5  34.00  13.40  5,802,440  608.73M  Converted from GL model (log) 
PreResNet18 x0.75  30.23  11.05  8,473,784  1,129.51M  Converted from GL model (log) 
PreResNet18  28.43  9.72  11,687,848  1,820.56M  Converted from GL model (log) 
PreResNet26  26.33  8.51  17,958,568  2,746.94M  Converted from GL model (log) 
PreResNetBC26b  25.48  8.03  15,987,624  2,354.16M  Converted from GL model (log) 
PreResNet34  24.89  7.74  21,796,008  3,672.83M  Converted from GL model (log) 
PreResNetBC38b  22.92  6.57  21,917,864  3,231.70M  Converted from GL model (log) 
PreResNet50  22.40  6.47  25,549,480  3,875.44M  Converted from GL model (log) 
PreResNet50b  22.51  6.55  25,549,480  4,107.97M  Converted from GL model (log) 
PreResNet101  21.74  5.91  44,541,608  7,595.44M  From dmlc/gluoncv (log) 
PreResNet101b  21.04  5.56  44,541,608  7,827.97M  Converted from GL model (log) 
PreResNet152  20.94  5.55  60,185,256  11,319.34M  From dmlc/gluoncv (log) 
PreResNet152b  20.14  5.16  60,185,256  11,551.87M  Converted from GL model (log) 
PreResNet200b  21.33  5.88  64,666,280  15,068.63M  From tornadomeet/ResNet (log) 
PreResNet269b  20.92  5.81  102,065,832  20,101.11M  From soeaver/mxnetmodel (log) 
ResNeXt14 (16x4d)  31.94  12.48  7,127,336  1,045.77M  Converted from GL model (log) 
ResNeXt14 (32x2d)  32.58  12.81  7,029,416  1,031.32M  Converted from GL model (log) 
ResNeXt14 (32x4d)  30.32  11.46  9,411,880  1,603.46M  Converted from GL model (log) 
ResNeXt26 (32x2d)  26.63  8.87  9,924,136  1,461.06M  Converted from GL model (log) 
ResNeXt26 (32x4d)  24.14  7.46  15,389,480  2,488.07M  Converted from GL model (log) 
ResNeXt50 (32x4d)  20.78  5.58  25,028,904  4,255.86M  From dmlc/gluoncv (log) 
ResNeXt101 (32x4d)  19.98  5.23  44,177,704  8,003.45M  From dmlc/gluoncv (log) 
ResNeXt101 (64x4d)  19.58  5.09  83,455,272  15,500.27M  From dmlc/gluoncv (log) 
SEResNet10  33.89  13.66  5,463,332  894.27M  Converted from GL model (log) 
SEResNet18  28.18  9.61  11,778,592  1,820.88M  Converted from GL model (log) 
SEResNet26  25.67  8.24  18,093,852  2,747.49M  Converted from GL model (log) 
SEResNetBC26b  23.59  7.03  17,395,976  2,359.58M  Converted from GL model (log) 
SEResNetBC38b  21.60  5.95  24,026,616  3,238.58M  Converted from GL model (log) 
SEResNet50  21.22  5.75  28,088,024  3,883.25M  Converted from GL model (log) 
SEResNet50b  20.79  5.39  28,088,024  4,115.78M  Converted from GL model (log) 
SEResNet101  21.88  5.89  49,326,872  7,602.76M  From Cadene/pretrained...pytorch (log) 
SEResNet101b  19.70  4.87  49,326,872  7,839.75M  Converted from GL model (log) 
SEResNet152  21.48  5.76  66,821,848  11,328.52M  From Cadene/pretrained...pytorch (log) 
SEPreResNet10  34.03  13.38  5,461,668  894.42M  Converted from GL model (log) 
SEPreResNet18  28.09  9.63  11,776,928  1,821.03M  Converted from GL model (log) 
SEPreResNetBC26b  23.22  6.60  17,388,424  2,357.07M  Converted from GL model (log) 
SEPreResNetBC38b  21.60  5.78  24,019,064  3,236.07M  Converted from GL model (log) 
SEPreResNet50b  20.85  5.49  28,080,472  4,113.27M  Converted from GL model (log) 
SEResNeXt50 (32x4d)  20.29  5.21  27,559,896  4,261.16M  From dmlc/gluoncv (log) 
SEResNeXt101 (32x4d)  19.22  4.80  48,955,416  8,012.73M  From dmlc/gluoncv (log) 
SEResNeXt101 (64x4d)  19.28  4.76  88,232,984  15,509.54M  From dmlc/gluoncv (log) 
SENet16  25.65  8.20  31,366,168  5,081.30M  Converted from GL model (log) 
SENet28  21.94  5.98  36,453,768  5,732.71M  Converted from GL model (log) 
SENet154  18.62  4.61  115,088,984  20,745.78M  From Cadene/pretrained...pytorch (log) 
ResNeSt(A)BC14  24.50  7.49  10,611,688  2,767.37M  From dmlc/gluoncv (log) 
ResNeSt(A)18  24.92  7.49  12,763,784  2,587.50M  Converted from GL model (log) 
ResNeSt(A)BC26  21.52  5.71  17,069,448  3,646.57M  From dmlc/gluoncv (log) 
ResNeSt(A)50  19.04  4.62  27,483,240  5,403.11M  From dmlc/gluoncv (log) 
ResNeSt(A)101  17.83  4.03  48,275,016  10,247.88M  From dmlc/gluoncv (log) 
ResNeSt(A)200  16.87  3.39  70,201,544  22,857.88M  From dmlc/gluoncv (log) 
ResNeSt(A)269  16.47  3.38  110,929,480  46,012.95M  From dmlc/gluoncv (log) 
IBNResNet50  22.76  6.41  25,557,032  4,110.48M  From XingangPan/IBNNet (log) 
IBNResNet101  21.29  5.61  44,549,160  7,830.48M  From XingangPan/IBNNet (log) 
IBN(b)ResNet50  23.64  6.86  25,558,568  4,112.89M  From XingangPan/IBNNet (log) 
IBNResNeXt101 (32x4d)  20.88  5.42  44,177,704  8,003.45M  From XingangPan/IBNNet (log) 
IBNDenseNet121  24.47  7.25  7,978,856  2,872.13M  From XingangPan/IBNNet (log) 
IBNDenseNet169  23.25  6.51  14,149,480  3,403.89M  From XingangPan/IBNNet (log) 
AirNet501x64d (r=2)  21.84  5.90  27,425,864  4,772.11M  From soeaver/AirNetPyTorch (log) 
AirNet501x64d (r=16)  22.11  6.19  25,714,952  4,399.97M  From soeaver/AirNetPyTorch (log) 
AirNeXt5032x4d (r=2)  20.87  5.51  27,604,296  5,339.58M  From soeaver/AirNetPyTorch (log) 
BAMResNet50  23.14  6.58  25,915,099  4,196.09M  From Jongchan/attentionmodule (log) 
CBAMResNet50  22.38  6.05  28,089,624  4,116.97M  From Jongchan/attentionmodule (log) 
SCNet50  22.19  6.08  25,564,584  3,951.06M  From MCGNKU/SCNet (log) 
SCNet101  21.06  5.75  44,565,416  7,204.24M  From MCGNKU/SCNet (log) 
SCNet(A)50  19.53  4.68  25,583,816  4,715.84M  From MCGNKU/SCNet (log) 
RegNetX200MF  31.34  11.76  2,684,792  203.33M  From rwightman/pyt...models (log) 
RegNetX400MF  27.70  9.36  5,157,512  403.45M  From rwightman/pyt...models (log) 
RegNetX600MF  26.32  8.43  6,196,040  608.37M  From rwightman/pyt...models (log) 
RegNetX800MF  25.21  7.81  7,259,656  809.49M  From rwightman/pyt...models (log) 
RegNetX1.6GF  23.32  6.72  9,190,136  1,618.99M  From rwightman/pyt...models (log) 
RegNetX3.2GF  22.08  6.00  15,296,552  3,199.55M  From rwightman/pyt...models (log) 
RegNetX4.0GF  21.61  5.86  22,118,248  3,986.29M  From rwightman/pyt...models (log) 
RegNetX6.4GF  21.06  5.57  26,209,256  6,491.01M  From rwightman/pyt...models (log) 
RegNetX8.0GF  21.00  5.51  39,572,648  8,017.94M  From rwightman/pyt...models (log) 
RegNetX12GF  20.55  5.38  46,106,056  12,124.22M  From rwightman/pyt...models (log) 
RegNetX16GF  20.07  5.17  54,278,536  15,986.64M  From rwightman/pyt...models (log) 
RegNetX32GF  19.65  4.94  107,811,560  31,790.24M  From rwightman/pyt...models (log) 
RegNetY200MF  30.02  10.58  3,162,996  203.99M  From rwightman/pyt...models (log) 
RegNetY400MF  26.23  8.36  4,344,144  410.35M  From rwightman/pyt...models (log) 
RegNetY600MF  24.93  7.53  6,055,160  610.37M  From rwightman/pyt...models (log) 
RegNetY800MF  23.76  6.97  6,263,168  808.62M  From rwightman/pyt...models (log) 
RegNetY1.6GF  22.40  6.30  11,202,430  1,629.48M  From rwightman/pyt...models (log) 
RegNetY3.2GF  18.04  4.04  19,436,338  3,199.15M  From rwightman/pyt...models (log) 
RegNetY4.0GF  20.84  5.41  20,646,656  3,999.16M  From rwightman/pyt...models (log) 
RegNetY6.4GF  20.23  5.23  30,583,252  6,388.91M  From rwightman/pyt...models (log) 
RegNetY8.0GF  20.18  5.13  39,180,068  7,996.54M  From rwightman/pyt...models (log) 
RegNetY12GF  19.68  4.92  51,822,544  12,132.55M  From rwightman/pyt...models (log) 
RegNetY16GF  19.76  5.03  83,590,140  15,944.53M  From rwightman/pyt...models (log) 
RegNetY32GF  19.32  4.74  145,046,770  32,317.66M  From rwightman/pyt...models (log) 
PyramidNet101 (a=360)  21.98  6.20  42,455,070  8,743.54M  From dyhan0920/Pyramid...PyTorch (log) 
DiracNetV218  31.47  11.70  11,511,784  1,796.62M  From szagoruyko/diracnets (log) 
DiracNetV234  28.75  9.93  21,616,232  3,646.93M  From szagoruyko/diracnets (log) 
DenseNet121  23.48  7.04  7,978,856  2,872.13M  Converted from GL model (log) 
DenseNet161  21.91  6.06  28,681,000  7,793.16M  Converted from GL model (log) 
DenseNet169  22.42  6.29  14,149,480  3,403.89M  Converted from GL model (log) 
DenseNet201  21.78  6.12  20,013,928  4,347.15M  Converted from GL model (log) 
CondenseNet74 (C=G=4)  26.25  8.28  4,773,944  546.06M  From ShichenLiu/CondenseNet (log) 
CondenseNet74 (C=G=8)  28.93  10.06  2,935,416  291.52M  From ShichenLiu/CondenseNet (log) 
PeleeNet  31.81  11.51  2,802,248  514.87M  Converted from GL model (log) 
WRN502  22.53  6.41  68,849,128  11,405.42M  From szagoruyko/functionalzoo (log) 
DRNC26  24.86  7.55  21,126,584  16,993.90M  From fyu/drn (log) 
DRNC42  22.94  6.57  31,234,744  25,093.75M  From fyu/drn (log) 
DRNC58  21.73  6.01  40,542,008  32,489.94M  From fyu/drn (log) 
DRND22  25.80  8.23  16,393,752  13,051.33M  From fyu/drn (log) 
DRND38  23.79  6.95  26,501,912  21,151.19M  From fyu/drn (log) 
DRND54  21.22  5.86  35,809,176  28,547.38M  From fyu/drn (log) 
DRND105  20.62  5.48  54,801,304  43,442.43M  From fyu/drn (log) 
DPN68  23.24  6.79  12,611,602  2,351.84M  Converted from GL model (log) 
DPN98  20.81  5.53  61,570,728  11,716.51M  From Cadene/pretrained...pytorch (log) 
DPN131  20.54  5.48  79,254,504  16,076.15M  From Cadene/pretrained...pytorch (log) 
DarkNet Tiny  40.74  17.84  1,042,104  500.85M  Converted from GL model (log) 
DarkNet Ref  38.58  17.18  7,319,416  367.59M  Converted from GL model (log) 
DarkNet53  21.75  5.64  41,609,928  7,133.86M  From dmlc/gluoncv (log) 
iRevNet301  25.98  8.41  125,120,356  14,453.87M  From jhjacobsen/pytorchirevnet (log) 
BagNet9  53.61  29.61  15,688,744  16,049.19M  From wielandbrendel/bag...models (log) 
BagNet17  41.20  18.84  16,213,032  15,768.77M  From wielandbrendel/bag...models (log) 
BagNet33  33.34  13.01  18,310,184  16,371.52M  From wielandbrendel/bag...models (log) 
DLA34  25.36  7.94  15,742,104  3,071.37M  From ucbdrive/dla (log) 
DLA46C  34.28  13.23  1,301,400  585.45M  Converted from GL model (log) 
DLAX46C  33.26  12.69  1,068,440  546.72M  Converted from GL model (log) 
DLA60  22.98  6.69  22,036,632  4,255.49M  From ucbdrive/dla (log) 
DLAX60  21.76  5.98  17,352,344  3,543.68M  From ucbdrive/dla (log) 
DLAX60C  30.98  10.91  1,319,832  596.06M  Converted from GL model (log) 
DLA102  21.97  6.05  33,268,888  7,190.95M  From ucbdrive/dla (log) 
DLAX102  21.49  5.77  26,309,272  5,884.94M  From ucbdrive/dla (log) 
DLAX2102  20.55  5.36  41,282,200  9,340.61M  From ucbdrive/dla (log) 
DLA169  21.29  5.66  53,389,720  11,593.20M  From ucbdrive/dla (log) 
FishNet150  21.97  6.04  24,959,400  6,435.05M  From kevinssy/FishNet (log) 
ESPNetv2 x0.5  42.32  20.15  1,241,332  35.36M  From sacmehta/ESPNetv2 (log) 
ESPNetv2 x1.0  33.92  13.45  1,670,072  98.09M  From sacmehta/ESPNetv2 (log) 
ESPNetv2 x1.25  32.06  12.18  1,965,440  138.18M  From sacmehta/ESPNetv2 (log) 
ESPNetv2 x1.5  30.83  11.29  2,314,856  185.77M  From sacmehta/ESPNetv2 (log) 
ESPNetv2 x2.0  27.94  9.61  3,498,136  306.93M  From sacmehta/ESPNetv2 (log) 
HRNetW18 Small V1  27.66  9.33  13,187,464  1,615.00M  From HRNet/HRNet...ation (log) 
HRNetW18 Small V2  24.87  7.58  15,597,464  2,618.84M  From HRNet/HRNet...ation (log) 
HRNetV2W18  23.24  6.56  21,299,004  4,323.07M  From HRNet/HRNet...ation (log) 
HRNetV2W30  21.80  5.78  37,712,220  8,156.82M  From HRNet/HRNet...ation (log) 
HRNetV2W32  21.55  5.81  41,232,680  8,974.04M  From HRNet/HRNet...ation (log) 
HRNetV2W40  21.07  5.53  57,557,160  12,752.26M  From HRNet/HRNet...ation (log) 
HRNetV2W44  21.11  5.63  67,064,984  14,946.96M  From HRNet/HRNet...ation (log) 
HRNetV2W48  20.69  5.48  77,469,864  17,345.39M  From HRNet/HRNet...ation (log) 
HRNetV2W64  20.53  5.35  128,059,944  28,976.42M  From HRNet/HRNet...ation (log) 
VoVNet39  23.22  6.57  22,600,296  7,086.16M  From stigma0617/VoVNet.pytorch (log) 
VoVNet57  22.27  6.28  36,640,296  8,943.09M  From stigma0617/VoVNet.pytorch (log) 
SelecSLS42b  22.89  6.59  32,458,248  2,980.62M  From rwightman/pyt...models (log) 
SelecSLS60  22.10  6.12  30,670,768  3,591.78M  From rwightman/pyt...models (log) 
SelecSLS60b  21.62  5.84  32,774,064  3,629.14M  From rwightman/pyt...models (log) 
HarDNet39DS  27.92  9.57  3,488,228  437.52M  From PingoLH/PytorchHarDNet (log) 
HarDNet68DS  25.71  8.13  4,180,602  788.86M  From PingoLH/PytorchHarDNet (log) 
HarDNet68  23.51  6.99  17,565,348  4,256.32M  From PingoLH/PytorchHarDNet (log) 
HarDNet85  21.96  6.11  36,670,212  9,088.58M  From PingoLH/PytorchHarDNet (log) 
SqueezeNet v1.0  39.29  17.66  1,248,424  823.67M  Converted from GL model (log) 
SqueezeNet v1.1  39.31  17.72  1,235,496  352.02M  Converted from GL model (log) 
SqueezeResNet v1.0  39.77  18.09  1,248,424  823.67M  Converted from GL model (log) 
SqueezeResNet v1.1  40.09  18.21  1,235,496  352.02M  Converted from GL model (log) 
1.0SqNxt23  42.51  19.06  724,056  287.28M  Converted from GL model (log) 
1.0SqNxt23v5  40.77  17.85  921,816  285.82M  Converted from GL model (log) 
1.5SqNxt23  34.89  13.50  1,511,824  552.39M  Converted from GL model (log) 
1.5SqNxt23v5  33.81  13.01  1,953,616  550.97M  Converted from GL model (log) 
2.0SqNxt23  30.62  11.00  2,583,752  898.48M  Converted from GL model (log) 
2.0SqNxt23v5  29.63  10.66  3,366,344  897.60M  Converted from GL model (log) 
ShuffleNet x0.25 (g=1)  62.44  37.29  209,746  12.35M  Converted from GL model (log) 
ShuffleNet x0.25 (g=3)  61.74  36.53  305,902  13.09M  Converted from GL model (log) 
ShuffleNet x0.5 (g=1)  46.59  22.61  534,484  41.16M  Converted from GL model (log) 
ShuffleNet x0.5 (g=3)  44.16  20.80  718,324  41.70M  Converted from GL model (log) 
ShuffleNet x0.75 (g=1)  39.58  17.11  975,214  86.42M  Converted from GL model (log) 
ShuffleNet x0.75 (g=3)  38.20  16.50  1,238,266  85.82M  Converted from GL model (log) 
ShuffleNet x1.0 (g=1)  34.93  13.89  1,531,936  148.13M  Converted from GL model (log) 
ShuffleNet x1.0 (g=2)  34.25  13.63  1,733,848  147.60M  Converted from GL model (log) 
ShuffleNet x1.0 (g=3)  34.39  13.48  1,865,728  145.46M  Converted from GL model (log) 
ShuffleNet x1.0 (g=4)  34.19  13.35  1,968,344  143.33M  Converted from GL model (log) 
ShuffleNet x1.0 (g=8)  34.06  13.42  2,434,768  150.76M  Converted from GL model (log) 
ShuffleNetV2 x0.5  40.99  18.65  1,366,792  43.31M  Converted from GL model (log) 
ShuffleNetV2 x1.0  31.44  11.63  2,278,604  149.72M  Converted from GL model (log) 
ShuffleNetV2 x1.5  27.47  9.42  4,406,098  320.77M  Converted from GL model (log) 
ShuffleNetV2 x2.0  25.94  8.45  7,601,686  595.84M  Converted from GL model (log) 
ShuffleNetV2b x0.5  40.29  18.22  1,366,792  43.31M  Converted from GL model (log) 
ShuffleNetV2b x1.0  30.62  11.25  2,279,760  150.62M  Converted from GL model (log) 
ShuffleNetV2b x1.5  27.31  9.11  4,410,194  323.98M  Converted from GL model (log) 
ShuffleNetV2b x2.0  25.58  8.34  7,611,290  603.37M  Converted from GL model (log) 
108MENet8x1 (g=3)  43.94  20.76  654,516  42.68M  Converted from GL model (log) 
128MENet8x1 (g=4)  42.43  19.59  750,796  45.98M  Converted from GL model (log) 
160MENet8x1 (g=8)  43.84  20.84  850,120  45.63M  Converted from GL model (log) 
228MENet12x1 (g=3)  34.11  13.16  1,806,568  152.93M  Converted from GL model (log) 
256MENet12x1 (g=4)  32.65  12.52  1,888,240  150.65M  Converted from GL model (log) 
348MENet12x1 (g=3)  28.24  9.58  3,368,128  312.00M  Converted from GL model (log) 
352MENet12x1 (g=8)  31.56  12.00  2,272,872  157.35M  Converted from GL model (log) 
456MENet24x1 (g=3)  25.32  7.99  5,304,784  567.90M  Converted from GL model (log) 
MobileNet x0.25  46.26  22.49  470,072  44.09M  Converted from GL model (log) 
MobileNet x0.5  34.15  13.55  1,331,592  155.42M  Converted from GL model (log) 
MobileNet x0.75  30.14  10.76  2,585,560  333.99M  Converted from GL model (log) 
MobileNet x1.0  26.61  8.95  4,231,976  579.80M  Converted from GL model (log) 
FDMobileNet x0.25  55.86  30.98  383,160  12.95M  Converted from GL model (log) 
FDMobileNet x0.5  43.13  20.15  993,928  41.84M  Converted from GL model (log) 
FDMobileNet x0.75  38.42  16.41  1,833,304  86.68M  Converted from GL model (log) 
FDMobileNet x1.0  34.23  13.38  2,901,288  147.46M  Converted from GL model (log) 
MobileNetV2 x0.25  48.34  24.51  1,516,392  34.24M  Converted from GL model (log) 
MobileNetV2 x0.5  35.98  14.93  1,964,736  100.13M  Converted from GL model (log) 
MobileNetV2 x0.75  30.17  10.82  2,627,592  198.50M  Converted from GL model (log) 
MobileNetV2 x1.0  26.97  8.87  3,504,960  329.36M  Converted from GL model (log) 
MobileNetV2b x0.25  48.63  25.30  1,516,312  33.18M  From dmlc/gluoncv (log) 
MobileNetV2b x0.5  35.98  14.98  1,964,448  96.42M  From dmlc/gluoncv (log) 
MobileNetV2b x0.75  31.07  11.78  2,626,968  190.52M  From dmlc/gluoncv (log) 
MobileNetV2b x1.0  28.47  9.75  3,503,872  315.51M  From dmlc/gluoncv (log) 
MobileNetV3 L/224/1.0  24.86  7.79  5,481,752  227.09M  From dmlc/gluoncv (log) 
IGCV3 x0.25  53.70  28.71  1,534,020  41.29M  Converted from GL model (log) 
IGCV3 x0.5  39.75  17.32  1,985,528  111.12M  Converted from GL model (log) 
IGCV3 x0.75  31.05  11.40  2,638,084  210.95M  Converted from GL model (log) 
IGCV3 x1.0  27.91  9.20  3,491,688  340.79M  Converted from GL model (log) 
MnasNetB1  25.38  7.85  4,383,312  326.30M  From rwightman/pyt...models (log) 
MnasNetA1  24.67  7.44  3,887,038  326.07M  From rwightman/pyt...models (log) 
DARTS  26.70  8.74  4,718,752  539.86M  From quark0/darts (log) 
ProxylessNAS CPU  24.71  7.61  4,361,648  459.96M  From MITHANLAB/ProxylessNAS (log) 
ProxylessNAS GPU  24.79  7.45  7,119,848  476.08M  Converted from GL model (log) 
ProxylessNAS Mobile  25.41  7.80  4,080,512  332.46M  From MITHANLAB/ProxylessNAS (log) 
ProxylessNAS Mob14  23.29  6.62  6,857,568  597.10M  Converted from GL model (log) 
FBNetCb  24.89  7.62  5,572,200  399.26M  From rwightman/pyt...models (log) 
Xception  20.97  5.49  22,855,952  8,403.63M  From Cadene/pretrained...pytorch (log) 
InceptionV3  21.12  5.65  23,834,568  5,743.06M  From dmlc/gluoncv (log) 
InceptionV4  20.64  5.29  42,679,816  12,304.93M  From Cadene/pretrained...pytorch (log) 
InceptionResNetV2  19.93  4.90  55,843,464  13,188.64M  From Cadene/pretrained...pytorch (log) 
PolyNet  19.10  4.52  95,366,600  34,821.34M  From Cadene/pretrained...pytorch (log) 
NASNetA 4@1056  25.68  8.16  5,289,978  584.90M  From Cadene/pretrained...pytorch (log) 
NASNetA 6@4032  18.14  4.21  88,753,150  23,976.44M  From Cadene/pretrained...pytorch (log) 
PNASNet5Large  17.88  4.28  86,057,668  25,140.77M  From Cadene/pretrained...pytorch (log) 
SPNASNet  25.92  8.17  4,421,616  346.73M  From rwightman/pyt...models (log) 
EfficientNetB0  24.77  7.52  5,288,548  414.31M  Converted from GL model (log) 
EfficientNetB1  23.08  6.38  7,794,184  732.54M  Converted from GL model (log) 
EfficientNetB0b  23.88  7.02  5,288,548  414.31M  From rwightman/pyt...models (log) 
EfficientNetB1b  21.60  5.94  7,794,184  732.54M  From rwightman/pyt...models (log) 
EfficientNetB2b  20.31  5.27  9,109,994  1,051.98M  From rwightman/pyt...models (log) 
EfficientNetB3b  18.83  4.45  12,233,232  1,928.55M  From rwightman/pyt...models (log) 
EfficientNetB4b  17.45  3.89  19,341,616  4,607.46M  From rwightman/pyt...models (log) 
EfficientNetB5b  16.56  3.37  30,389,784  10,695.20M  From rwightman/pyt...models (log) 
EfficientNetB6b  16.29  3.23  43,040,704  19,796.24M  From rwightman/pyt...models (log) 
EfficientNetB7b  15.94  3.22  66,347,960  39,010.98M  From rwightman/pyt...models (log) 
EfficientNetB0c*  22.92  6.75  5,288,548  414.31M  From rwightman/pyt...models (log) 
EfficientNetB1c*  20.73  5.69  7,794,184  732.54M  From rwightman/pyt...models (log) 
EfficientNetB2c*  19.85  5.03  9,109,994  1,051.98M  From rwightman/pyt...models (log) 
EfficientNetB3c*  18.26  4.42  12,233,232  1,928.55M  From rwightman/pyt...models (log) 
EfficientNetB4c*  16.82  3.69  19,341,616  4,607.46M  From rwightman/pyt...models (log) 
EfficientNetB5c*  15.91  3.10  30,389,784  10,695.20M  From rwightman/pyt...models (log) 
EfficientNetB6c*  15.47  2.96  43,040,704  19,796.24M  From rwightman/pyt...models (log) 
EfficientNetB7c*  15.13  2.88  66,347,960  39,010.98M  From rwightman/pyt...models (log) 
EfficientNetB8c*  14.85  2.76  87,413,142  64,541.66M  From rwightman/pyt...models (log) 
EfficientNetEdgeSmallb*  22.74  6.40  5,438,392  2,378.12M  From rwightman/pyt...models (log) 
EfficientNetEdgeMediumb*  21.18  5.63  6,899,496  3,700.12M  From rwightman/pyt...models (log) 
EfficientNetEdgeLargeb*  19.66  4.91  10,589,712  9,747.66M  From rwightman/pyt...models (log) 
MixNetS  23.99  7.19  4,134,606  260.76M  From rwightman/pyt...models (log) 
MixNetM  22.93  6.60  5,014,382  366.68M  From rwightman/pyt...models (log) 
MixNetL  21.12  5.82  7,329,252  591.34M  From rwightman/pyt...models (log) 
ResNet(A)18  27.05  8.87  11,708,744  2,062.24M  Converted from GL model (log) 
ResNet(A)50b  21.13  5.63  25,576,264  4,352.93M  From dmlc/gluoncv (log) 
ResNet(A)101b  19.78  5.03  44,568,392  8,072.93M  From dmlc/gluoncv (log) 
ResNet(A)152b  19.62  4.82  60,212,040  11,796.83M  From dmlc/gluoncv (log) 
ResNet(D)50b  21.04  5.65  25,680,808  20,497.60M  From dmlc/gluoncv (log) 
ResNet(D)101b  19.59  4.73  44,672,936  35,392.65M  From dmlc/gluoncv (log) 
ResNet(D)152b  19.42  4.82  60,316,584  47,662.18M  From dmlc/gluoncv (log) 
CIFAR10
Model  Error, %  Params  FLOPs/2  Remarks 

NIN  7.43  966,986  222.97M  Converted from GL model (log) 
ResNet20  5.97  272,474  41.29M  Converted from GL model (log) 
ResNet56  4.52  855,770  127.06M  Converted from GL model (log) 
ResNet110  3.69  1,730,714  255.70M  Converted from GL model (log) 
ResNet164(BN)  3.68  1,704,154  255.31M  Converted from GL model (log) 
ResNet272(BN)  3.33  2,816,986  420.61M  Converted from GL model (log) 
ResNet542(BN)  3.43  5,599,066  833.87M  Converted from GL model (log) 
ResNet1001  3.28  10,328,602  1,536.40M  Converted from GL model (log) 
ResNet1202  3.53  19,424,026  2,857.17M  Converted from GL model (log) 
PreResNet20  6.51  272,282  41.27M  Converted from GL model (log) 
PreResNet56  4.49  855,578  127.03M  Converted from GL model (log) 
PreResNet110  3.86  1,730,522  255.68M  Converted from GL model (log) 
PreResNet164(BN)  3.64  1,703,258  255.08M  Converted from GL model (log) 
PreResNet272(BN)  3.25  2,816,090  420.38M  Converted from GL model (log) 
PreResNet542(BN)  3.14  5,598,170  833.64M  Converted from GL model (log) 
PreResNet1001  2.65  10,327,706  1,536.18M  Converted from GL model (log) 
PreResNet1202  3.39  19,423,834  2,857.14M  Converted from GL model (log) 
ResNeXt29 (32x4d)  3.15  4,775,754  780.55M  Converted from GL model (log) 
ResNeXt29 (16x64d)  2.41  68,155,210  10,709.34M  Converted from GL model (log) 
ResNeXt272 (1x64d)  2.55  44,540,746  6,565.15M  Converted from GL model (log) 
ResNeXt272 (2x32d)  2.74  32,928,586  4,867.11M  Converted from GL model (log) 
SEResNet20  6.01  274,847  41.34M  Converted from GL model (log) 
SEResNet56  4.13  862,889  127.19M  Converted from GL model (log) 
SEResNet110  3.63  1,744,952  255.98M  Converted from GL model (log) 
SEResNet164(BN)  3.39  1,906,258  256.55M  Converted from GL model (log) 
SEResNet272(BN)  3.39  3,153,826  422.68M  Converted from GL model (log) 
SEResNet542(BN)  3.47  6,272,746  838.01M  Converted from GL model (log) 
SEPreResNet20  6.18  274,559  41.35M  Converted from GL model (log) 
SEPreResNet56  4.51  862,601  127.20M  Converted from GL model (log) 
SEPreResNet110  4.54  1,744,664  255.98M  Converted from GL model (log) 
SEPreResNet164(BN)  3.73  1,904,882  256.32M  Converted from GL model (log) 
SEPreResNet272(BN)  3.39  3,152,450  422.45M  Converted from GL model (log) 
SEPreResNet542(BN)  3.08  6,271,370  837.78M  Converted from GL model (log) 
PyramidNet110 (a=48)  3.72  1,772,706  408.37M  Converted from GL model (log) 
PyramidNet110 (a=84)  2.98  3,904,446  778.15M  Converted from GL model (log) 
PyramidNet110 (a=270)  2.51  28,485,477  4,730.60M  Converted from GL model (log) 
PyramidNet164 (a=270, BN)  2.42  27,216,021  4,608.81M  Converted from GL model (log) 
PyramidNet200 (a=240, BN)  2.44  26,752,702  4,563.40M  Converted from GL model (log) 
PyramidNet236 (a=220, BN)  2.47  26,969,046  4,631.32M  Converted from GL model (log) 
PyramidNet272 (a=200, BN)  2.39  26,210,842  4,541.36M  Converted from GL model (log) 
DenseNet40 (k=12)  5.61  599,050  210.80M  Converted from GL model (log) 
DenseNetBC40 (k=12)  6.43  176,122  74.89M  Converted from GL model (log) 
DenseNetBC40 (k=24)  4.52  690,346  293.09M  Converted from GL model (log) 
DenseNetBC40 (k=36)  4.04  1,542,682  654.60M  Converted from GL model (log) 
DenseNet100 (k=12)  3.66  4,068,490  1,353.55M  Converted from GL model (log) 
DenseNet100 (k=24)  3.13  16,114,138  5,354.19M  Converted from GL model (log) 
DenseNetBC100 (k=12)  4.16  769,162  298.45M  Converted from GL model (log) 
DenseNetBC190 (k=40)  2.52  25,624,430  9,400.45M  Converted from GL model (log) 
DenseNetBC250 (k=24)  2.67  15,324,406  5,519.54M  Converted from GL model (log) 
XDenseNetBC402 (k=24)  5.31  690,346  293.09M  Converted from GL model (log) 
XDenseNetBC402 (k=36)  4.37  1,542,682  654.60M  Converted from GL model (log) 
WRN1610  2.93  17,116,634  2,414.04M  Converted from GL model (log) 
WRN2810  2.39  36,479,194  5,246.98M  Converted from GL model (log) 
WRN408  2.37  35,748,314  5,176.90M  Converted from GL model (log) 
WRN20101bit  3.26  26,737,140  4,019.14M  Converted from GL model (log) 
WRN201032bit  3.14  26,737,140  4,019.14M  Converted from GL model (log) 
RoR356  5.43  762,746  113.43M  Converted from GL model (log) 
RoR3110  4.35  1,637,690  242.07M  Converted from GL model (log) 
RoR3164  3.93  2,512,634  370.72M  Converted from GL model (log) 
RiR  3.28  9,492,980  1,281.08M  Converted from GL model (log) 
ShakeShakeResNet202x16d  5.15  541,082  81.78M  Converted from GL model (log) 
ShakeShakeResNet262x32d  3.17  2,923,162  428.89M  Converted from GL model (log) 
DIAResNet20  6.22  286,866  41.54M  Converted from GL model (log) 
DIAResNet56  5.05  870,162  129.31M  Converted from GL model (log) 
DIAResNet110  4.10  1,745,106  264.71M  Converted from GL model (log) 
DIAResNet164(BN)  3.50  1,923,002  343.60M  Converted from GL model (log) 
DIAPreResNet20  6.42  286,674  41.52M  Converted from GL model (log) 
DIAPreResNet56  4.83  869,970  129.28M  Converted from GL model (log) 
DIAPreResNet110  4.25  1,744,914  264.69M  Converted from GL model (log) 
DIAPreResNet164(BN)  3.56  1,922,106  343.37M  Converted from GL model (log) 
CIFAR100
Model  Error, %  Params  FLOPs/2  Remarks 

NIN  28.39  984,356  224.08M  Converted from GL model (log) 
ResNet20  29.64  278,324  41.30M  Converted from GL model (log) 
ResNet56  24.88  861,620  127.06M  Converted from GL model (log) 
ResNet110  22.80  1,736,564  255.71M  Converted from GL model (log) 
ResNet164(BN)  20.44  1,727,284  255.33M  Converted from GL model (log) 
ResNet272(BN)  20.07  2,840,116  420.63M  Converted from GL model (log) 
ResNet542(BN)  19.32  5,622,196  833.89M  Converted from GL model (log) 
ResNet1001  19.79  10,351,732  1,536.43M  Converted from GL model (log) 
ResNet1202  21.56  19,429,876  2,857.17M  Converted from GL model (log) 
PreResNet20  30.22  278,132  41.28M  Converted from GL model (log) 
PreResNet56  25.05  861,428  127.04M  Converted from GL model (log) 
PreResNet110  22.67  1,736,372  255.68M  Converted from GL model (log) 
PreResNet164(BN)  20.18  1,726,388  255.10M  Converted from GL model (log) 
PreResNet272(BN)  19.63  2,839,220  420.40M  Converted from GL model (log) 
PreResNet542(BN)  18.71  5,621,300  833.66M  Converted from GL model (log) 
PreResNet1001  18.41  10,350,836  1,536.20M  Converted from GL model (log) 
ResNeXt29 (32x4d)  19.50  4,868,004  780.64M  Converted from GL model (log) 
ResNeXt29 (16x64d)  16.93  68,247,460  10,709.43M  Converted from GL model (log) 
ResNeXt272 (1x64d)  19.11  44,632,996  6,565.25M  Converted from GL model (log) 
ResNeXt272 (2x32d)  18.34  33,020,836  4,867.20M  Converted from GL model (log) 
SEResNet20  28.54  280,697  41.35M  Converted from GL model (log) 
SEResNet56  22.94  868,739  127.07M  Converted from GL model (log) 
SEResNet110  20.86  1,750,802  255.98M  Converted from GL model (log) 
SEResNet164(BN)  19.95  1,929,388  256.57M  Converted from GL model (log) 
SEResNet272(BN)  19.07  3,176,956  422.70M  Converted from GL model (log) 
SEResNet542(BN)  18.87  6,295,876  838.03M  Converted from GL model (log) 
SEPreResNet20  28.31  280,409  41.35M  Converted from GL model (log) 
SEPreResNet56  23.05  868,451  127.21M  Converted from GL model (log) 
SEPreResNet110  22.61  1,750,514  255.99M  Converted from GL model (log) 
SEPreResNet164(BN)  20.05  1,928,012  256.34M  Converted from GL model (log) 
SEPreResNet272(BN)  19.13  3,175,580  422.47M  Converted from GL model (log) 
SEPreResNet542(BN)  19.45  6,294,500  837.80M  Converted from GL model (log) 
PyramidNet110 (a=48)  20.95  1,778,556  408.38M  Converted from GL model (log) 
PyramidNet110 (a=84)  18.87  3,913,536  778.16M  Converted from GL model (log) 
PyramidNet110 (a=270)  17.10  28,511,307  4,730.62M  Converted from GL model (log) 
PyramidNet164 (a=270, BN)  16.70  27,319,071  4,608.91M  Converted from GL model (log) 
PyramidNet200 (a=240, BN)  16.09  26,844,952  4,563.49M  Converted from GL model (log) 
PyramidNet236 (a=220, BN)  16.34  27,054,096  4,631.41M  Converted from GL model (log) 
PyramidNet272 (a=200, BN)  16.19  26,288,692  4,541.43M  Converted from GL model (log) 
DenseNet40 (k=12)  24.90  622,360  210.82M  Converted from GL model (log) 
DenseNetBC40 (k=12)  28.41  188,092  74.90M  Converted from GL model (log) 
DenseNetBC40 (k=24)  22.67  714,196  293.11M  Converted from GL model (log) 
DenseNetBC40 (k=36)  20.50  1,578,412  654.64M  Converted from GL model (log) 
DenseNet100 (k=12)  19.64  4,129,600  1,353.62M  Converted from GL model (log) 
DenseNet100 (k=24)  18.08  16,236,268  5,354.32M  Converted from GL model (log) 
DenseNetBC100 (k=12)  21.19  800,032  298.48M  Converted from GL model (log) 
DenseNetBC250 (k=24)  17.39  15,480,556  5,519.69M  Converted from GL model (log) 
XDenseNetBC402 (k=24)  23.96  714,196  293.11M  Converted from GL model (log) 
XDenseNetBC402 (k=36)  21.65  1,578,412  654.64M  Converted from GL model (log) 
WRN1610  18.95  17,174,324  2,414.09M  Converted from GL model (log) 
WRN2810  17.88  36,536,884  5,247.04M  Converted from GL model (log) 
WRN408  18.03  35,794,484  5,176.95M  Converted from GL model (log) 
WRN20101bit  19.04  26,794,920  4,022.81M  Converted from GL model (log) 
WRN201032bit  18.12  26,794,920  4,022.81M  Converted from GL model (log) 
RoR356  25.49  768,596  113.43M  Converted from GL model (log) 
RoR3110  23.64  1,643,540  242.08M  Converted from GL model (log) 
RoR3164  22.34  2,518,484  370.72M  Converted from GL model (log) 
RiR  19.23  9,527,720  1,283.29M  Converted from GL model (log) 
ShakeShakeResNet202x16d  29.22  546,932  81.79M  Converted from GL model (log) 
ShakeShakeResNet262x32d  18.80  2,934,772  428.90M  Converted from GL model (log) 
DIAResNet20  27.71  292,716  41.55M  Converted from GL model (log) 
DIAResNet56  24.35  876,012  129.32M  Converted from GL model (log) 
DIAResNet110  22.11  1,750,956  264.72M  Converted from GL model (log) 
DIAResNet164(BN)  19.53  1,946,132  343.62M  Converted from GL model (log) 
DIAPreResNet20  28.37  292,524  41.53M  Converted from GL model (log) 
DIAPreResNet56  25.05  875,820  129.29M  Converted from GL model (log) 
DIAPreResNet110  22.69  1,750,764  264.69M  Converted from GL model (log) 
DIAPreResNet164(BN)  19.99  1,945,236  343.39M  Converted from GL model (log) 
SVHN
Model  Error, %  Params  FLOPs/2  Remarks 

NIN  3.76  966,986  222.97M  Converted from GL model (log) 
ResNet20  3.43  272,474  41.29M  Converted from GL model (log) 
ResNet56  2.75  855,770  127.06M  Converted from GL model (log) 
ResNet110  2.45  1,730,714  255.70M  Converted from GL model (log) 
ResNet164(BN)  2.42  1,704,154  255.31M  Converted from GL model (log) 
ResNet272(BN)  2.43  2,816,986  420.61M  Converted from GL model (log) 
ResNet542(BN)  2.34  5,599,066  833.87M  Converted from GL model (log) 
ResNet1001  2.41  10,328,602  1,536.40M  Converted from GL model (log) 
PreResNet20  3.22  272,282  41.27M  Converted from GL model (log) 
PreResNet56  2.80  855,578  127.03M  Converted from GL model (log) 
PreResNet110  2.79  1,730,522  255.68M  Converted from GL model (log) 
PreResNet164(BN)  2.58  1,703,258  255.08M  Converted from GL model (log) 
PreResNet272(BN)  2.34  2,816,090  420.38M  Converted from GL model (log) 
PreResNet542(BN)  2.36  5,598,170  833.64M  Converted from GL model (log) 
ResNeXt29 (32x4d)  2.80  4,775,754  780.55M  Converted from GL model (log) 
ResNeXt29 (16x64d)  2.68  68,155,210  10,709.34M  Converted from GL model (log) 
ResNeXt272 (1x64d)  2.35  44,540,746  6,565.15M  Converted from GL model (log) 
ResNeXt272 (2x32d)  2.44  32,928,586  4,867.11M  Converted from GL model (log) 
SEResNet20  3.23  274,847  41.34M  Converted from GL model (log) 
SEResNet56  2.64  862,889  127.19M  Converted from GL model (log) 
SEResNet110  2.35  1,744,952  255.98M  Converted from GL model (log) 
SEResNet164(BN)  2.45  1,906,258  256.55M  Converted from GL model (log) 
SEResNet272(BN)  2.38  3,153,826  422.68M  Converted from GL model (log) 
SEResNet542(BN)  2.26  6,272,746  838.01M  Converted from GL model (log) 
SEPreResNet20  3.24  274,559  41.35M  Converted from GL model (log) 
SEPreResNet56  2.71  862,601  127.20M  Converted from GL model (log) 
SEPreResNet110  2.59  1,744,664  255.98M  Converted from GL model (log) 
SEPreResNet164(BN)  2.56  1,904,882  256.32M  Converted from GL model (log) 
SEPreResNet272(BN)  2.49  3,152,450  422.45M  Converted from GL model (log) 
SEPreResNet542(BN)  2.47  6,271,370  837.78M  Converted from GL model (log) 
PyramidNet110 (a=48)  2.47  1,772,706  408.37M  Converted from GL model (log) 
PyramidNet110 (a=84)  2.43  3,904,446  778.15M  Converted from GL model (log) 
PyramidNet110 (a=270)  2.38  28,485,477  4,730.60M  Converted from GL model (log) 
PyramidNet164 (a=270, BN)  2.33  27,216,021  4,608.81M  Converted from GL model (log) 
PyramidNet200 (a=240, BN)  2.32  26,752,702  4,563.40M  Converted from GL model (log) 
PyramidNet236 (a=220, BN)  2.35  26,969,046  4,631.32M  Converted from GL model (log) 
PyramidNet272 (a=200, BN)  2.40  26,210,842  4,541.36M  Converted from GL model (log) 
DenseNet40 (k=12)  3.05  599,050  210.80M  Converted from GL model (log) 
DenseNetBC40 (k=12)  3.20  176,122  74.89M  Converted from GL model (log) 
DenseNetBC40 (k=24)  2.90  690,346  293.09M  Converted from GL model (log) 
DenseNetBC40 (k=36)  2.60  1,542,682  654.60M  Converted from GL model (log) 
DenseNet100 (k=12)  2.60  4,068,490  1,353.55M  Converted from GL model (log) 
XDenseNetBC402 (k=24)  2.87  690,346  293.09M  Converted from GL model (log) 
XDenseNetBC402 (k=36)  2.74  1,542,682  654.60M  Converted from GL model (log) 
WRN1610  2.78  17,116,634  2,414.04M  Converted from GL model (log) 
WRN2810  2.71  36,479,194  5,246.98M  Converted from GL model (log) 
WRN408  2.54  35,748,314  5,176.90M  Converted from GL model (log) 
WRN20101bit  2.73  26,737,140  4,019.14M  Converted from GL model (log) 
WRN201032bit  2.59  26,737,140  4,019.14M  Converted from GL model (log) 
RoR356  2.69  762,746  113.43M  Converted from GL model (log) 
RoR3110  2.57  1,637,690  242.07M  Converted from GL model (log) 
RoR3164  2.73  2,512,634  370.72M  Converted from GL model (log) 
RiR  2.68  9,492,980  1,281.08M  Converted from GL model (log) 
ShakeShakeResNet202x16d  3.17  541,082  81.78M  Converted from GL model (log) 
ShakeShakeResNet262x32d  2.62  2,923,162  428.89M  Converted from GL model (log) 
DIAResNet20  3.23  286,866  41.54M  Converted from GL model (log) 
DIAResNet56  2.68  870,162  129.31M  Converted from GL model (log) 
DIAResNet110  2.47  1,745,106  264.71M  Converted from GL model (log) 
DIAResNet164(BN)  2.44  1,923,002  343.60M  Converted from GL model (log) 
DIAPreResNet20  3.03  286,674  41.52M  Converted from GL model (log) 
DIAPreResNet56  2.80  869,970  129.28M  Converted from GL model (log) 
DIAPreResNet110  2.42  1,744,914  264.69M  Converted from GL model (log) 
DIAPreResNet164(BN)  2.56  1,922,106  343.37M  Converted from GL model (log) 
CUB2002011
Model  Error, %  Params  FLOPs/2  Remarks 

ResNet10  27.77  5,008,392  893.63M  Converted from GL model (log) 
ResNet12  27.27  5,082,376  1,125.84M  Converted from GL model (log) 
ResNet14  24.77  5,377,800  1,357.53M  Converted from GL model (log) 
ResNet16  23.65  6,558,472  1,588.93M  Converted from GL model (log) 
ResNet18  23.33  11,279,112  1,820.00M  Converted from GL model (log) 
ResNet26  23.16  17,549,832  2,746.38M  Converted from GL model (log) 
SEResNet10  27.72  5,052,932  893.86M  Converted from GL model (log) 
SEResNet12  26.51  5,127,496  1,126.17M  Converted from GL model (log) 
SEResNet14  24.16  5,425,104  1,357.92M  Converted from GL model (log) 
SEResNet16  23.32  6,614,240  1,589.35M  Converted from GL model (log) 
SEResNet18  23.52  11,368,192  1,820.47M  Converted from GL model (log) 
SEResNet26  22.99  17,683,452  2,747.08M  Converted from GL model (log) 
MobileNet x1.0  23.77  3,411,976  578.98M  Converted from GL model (log) 
ProxylessNAS Mobile  22.66  3,055,712  331.44M  Converted from GL model (log) 
NTSNet  12.77  28,623,333  33,361.79M  From yangze0930/NTSNet (log) 
Pascal VOC20102
Model  Extractor  Pix.Acc.,%  mIoU,%  Params  FLOPs/2  Remarks 

PSPNet  ResNet(D)101b  98.09  81.44  65,708,501  230,771.01M  From dmlc/gluoncv (log) 
DeepLabv3  ResNet(D)101b  97.95  80.24  58,754,773  47,625.34M  From dmlc/gluoncv (log) 
DeepLabv3  ResNet(D)152b  98.11  81.20  74,398,421  59,894.87M  From dmlc/gluoncv (log) 
FCN8s(d)  ResNet(D)101b  97.80  80.40  52,072,917  196,562.96M  From dmlc/gluoncv (log) 
ADE20K
Model  Extractor  Pix.Acc.,%  mIoU,%  Params  FLOPs/2  Remarks 

PSPNet  ResNet(D)50b  79.37  36.87  46,782,550  162,595.14M  From dmlc/gluoncv (log) 
PSPNet  ResNet(D)101b  79.93  37.97  65,774,678  231,008.79M  From dmlc/gluoncv (log) 
DeepLabv3  ResNet(D)50b  79.72  37.13  39,795,798  32,756.18M  From dmlc/gluoncv (log) 
DeepLabv3  ResNet(D)101b  80.21  37.84  58,787,926  47,651.23M  From dmlc/gluoncv (log) 
FCN8s(d)  ResNet(D)50b  76.92  33.39  33,146,966  128,387.08M  From dmlc/gluoncv (log) 
FCN8s(d)  ResNet(D)101b  79.01  35.88  52,139,094  196,800.73M  From dmlc/gluoncv (log) 
Cityscapes
Model  Extractor  Pix.Acc.,%  mIoU,%  Params  FLOPs/2  Remarks 

PSPNet  ResNet(D)101b  96.17  71.72  65,707,475  230,767.33M  From dmlc/gluoncv (log) 
ICNet  ResNet(D)50b  95.50  64.02  47,489,184  14,253.43M  From dmlc/gluoncv (log) 
SINet    94.08  61.72  119,418  1,419.90M  From clovaai/c3_sinet (log) 
FastSCNN    95.14  65.76  1,138,051  3493.33M  From dmlc/gluoncv (log) 
DANet  ResNet(D)50b  95.91  67.99  47,586,427  180,397.43M  From dmlc/gluoncv (log) 
DANet  ResNet(D)101b  96.03  68.10  66,578,555  248,811.08M  From dmlc/gluoncv (log) 
COCO Semantic Segmentation
Model  Extractor  Pix.Acc.,%  mIoU,%  Params  FLOPs/2  Remarks 

PSPNet  ResNet(D)101b  92.05  67.41  65,708,501  230,771.01M  From dmlc/gluoncv (log) 
DeepLabv3  ResNet(D)101b  92.19  67.73  58,754,773  47,625.34M  From dmlc/gluoncv (log) 
DeepLabv3  ResNet(D)152b  92.24  68.99  74,398,421  275,087.91M  From dmlc/gluoncv (log) 
FCN8s(d)  ResNet(D)101b  91.44  60.11  52,072,917  196,562.96M  From dmlc/gluoncv (log) 
CelebAMaskHQ
Model  Extractor  Params  FLOPs/2  Remarks 

BiSeNet  ResNet18  13,300,416    From zllrunning/face...Torch (log) 
COCO Keypoints Detection
Model  Extractor  OKS AP, %  Params  FLOPs/2  Remarks 

AlphaPose  FastSEResNet101b  74.15/91.59/80.68  59,569,873  9,553.89M  From dmlc/gluoncv (log) 
SimplePose  ResNet18  66.31/89.20/73.41  15,376,721  1,799.25M  From dmlc/gluoncv (log) 
SimplePose  ResNet50b  71.02/91.23/78.57  33,999,697  4,041.06M  From dmlc/gluoncv (log) 
SimplePose  ResNet101b  72.44/92.18/79.76  52,991,825  7,685.04M  From dmlc/gluoncv (log) 
SimplePose  ResNet152b  72.53/92.14/79.61  68,635,473  11,332.86M  From dmlc/gluoncv (log) 
SimplePose  ResNet(A)50b  71.70/91.31/78.66  34,018,929  4,278.56M  From dmlc/gluoncv (log) 
SimplePose  ResNet(A)101b  72.97/92.24/80.81  53,011,057  7,922.54M  From dmlc/gluoncv (log) 
SimplePose  ResNet(A)152b  73.44/92.27/80.72  68,654,705  11,570.36M  From dmlc/gluoncv (log) 
SimplePose(Mobile)  ResNet18  66.25/89.17/74.32  12,858,208  1,960.96M  From dmlc/gluoncv (log) 
SimplePose(Mobile)  ResNet50b  71.10/91.28/78.67  25,582,944  4,221.30M  From dmlc/gluoncv (log) 
SimplePose(Mobile)  1.0 MobileNet224  64.10/88.06/71.23  5,019,744  751.36M  From dmlc/gluoncv (log) 
SimplePose(Mobile)  1.0 MobileNetV2b224  63.74/88.12/71.06  4,102,176  495.95M  From dmlc/gluoncv (log) 
SimplePose(Mobile)  MobileNetV3 Small 224/1.0  54.34/83.67/59.35  2,625,088  236.51M  From dmlc/gluoncv (log) 
SimplePose(Mobile)  MobileNetV3 Large 224/1.0  63.67/88.91/70.82  4,768,336  403.97M  From dmlc/gluoncv (log) 
Lightweight OpenPose 2D  MobileNet  39.99/65.95/40.70  4,091,698  8,948.96M  From DaniilOsokin/lighw...ch (log) 
Lightweight OpenPose 3D  MobileNet  39.99/65.95/40.70  5,085,983  11,049.43M  From DaniilOsokin/li...3d...ch (log) 
IBPPose    64.87/83.62/70.13  95,827,784  57,195.91M  From jialee93/Improved...Parts (log) 
Project details
Release history Release notifications  RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Filename, size  File type  Python version  Upload date  Hashes 

Filename, size pytorchcv0.0.60py2.py3noneany.whl (466.0 kB)  File type Wheel  Python version py2.py3  Upload date  Hashes View 
Filename, size pytorchcv0.0.60.tar.gz (318.9 kB)  File type Source  Python version None  Upload date  Hashes View 
Hashes for pytorchcv0.0.60py2.py3noneany.whl
Algorithm  Hash digest  

SHA256  6452284084a7a0ee897c3e5035069f7c77fa76d9f3ba9794b824f250a7e7cbdf 

MD5  e684ec648baa27ac6a9db92a5b0deaf1 

BLAKE2256  dfa82eca120c1ac44730ac3f36547f405536f3da66674940deb94ae4b457cd7c 