This is a collection of image classification, segmentation, detection, and pose estimation models. Many of them are pretrained on
ImageNet-1K, CIFAR-10/100,
SVHN, CUB-200-2011,
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.
- AlexNet ('One weird trick for parallelizing convolutional neural networks')
- ZFNet ('Visualizing and Understanding Convolutional Networks')
- VGG/BN-VGG ('Very Deep Convolutional Networks for Large-Scale Image Recognition')
- BN-Inception ('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/SE-ResNet/SE-PreResNet/SE-ResNeXt ('Squeeze-and-Excitation Networks')
- ResNeSt(A) ('ResNeSt: Split-Attention Networks')
- IBN-ResNet/IBN-ResNeXt/IBN-DenseNet ('Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net')
- AirNet/AirNeXt ('Attention Inspiring Receptive-Fields Network for Learning Invariant Representations')
- BAM-ResNet ('BAM: Bottleneck Attention Module')
- CBAM-ResNet ('CBAM: Convolutional Block Attention Module')
- SCNet ('Improving Convolutional Networks with Self-Calibrated Convolutions')
- RegNet ('Designing Network Design Spaces')
- PyramidNet ('Deep Pyramidal Residual Networks')
- DiracNetV2 ('DiracNets: Training Very Deep Neural Networks Without Skip-Connections')
- DenseNet ('Densely Connected Convolutional Networks')
- PeleeNet ('Pelee: A Real-Time Object Detection System on Mobile Devices')
- WRN ('Wide Residual Networks')
- DRN-C/DRN-D ('Dilated Residual Networks')
- DPN ('Dual Path Networks')
- DarkNet Ref/Tiny/19 ('Darknet: Open source neural networks in c')
- DarkNet-53 ('YOLOv3: An Incremental Improvement')
- BagNet ('Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet')
- DLA ('Deep Layer Aggregation')
- DiCENet ('DiCENet: Dimension-wise Convolutions for Efficient Networks')
- HRNet ('Deep High-Resolution Representation Learning for Visual Recognition')
- VoVNet ('An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection')
- SelecSLS ('XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera')
- HarDNet ('HarDNet: A Low Memory Traffic Network')
- SqueezeNet/SqueezeResNet ('SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size')
- SqueezeNext ('SqueezeNext: Hardware-Aware 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')
- FD-MobileNet ('FD-MobileNet: Improved MobileNet with A Fast Downsampling Strategy')
- MobileNetV2 ('MobileNetV2: Inverted Residuals and Linear Bottlenecks')
- MobileNetV3 ('Searching for MobileNetV3')
- IGCV3 ('IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks')
- GhostNet ('GhostNet: More Features from Cheap Operations')
- MnasNet ('MnasNet: Platform-Aware Neural Architecture Search for Mobile')
- ProxylessNAS ('ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware')
- FBNet ('FBNet: Hardware-Aware 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/InceptionResNetV1/InceptionResNetV2 ('Inception-v4, Inception-ResNet 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 ('Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours')
- EfficientNet ('EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks')
- MixNet ('MixConv: Mixed Depthwise Convolutional Kernels')
- FCN-8s ('Fully Convolutional Networks for Semantic Segmentation')
- PSPNet ('Pyramid Scene Parsing Network')
- DeepLabv3 ('Rethinking Atrous Convolution for Semantic Image Segmentation')
- ICNet ('ICNet for Real-Time Semantic Segmentation on High-Resolution Images')
- Fast-SCNN ('Fast-SCNN: Fast Semantic Segmentation Network')
- CGNet ('CGNet: A Light-weight Context Guided Network for Semantic Segmentation')
- DABNet ('DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation')
- BiSeNet ('BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation')
- DANet ('Dual Attention Network for Scene Segmentation')
- FPENet ('Feature Pyramid Encoding Network for Real-time Semantic Segmentation')
- LEDNet ('LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation')
- CenterNet ('Objects as Points')
- LFFD ('LFFD: A Light and Fast Face Detector for Edge Devices')
- AlphaPose ('RMPE: Regional Multi-person Pose Estimation')
- SimplePose ('Simple Baselines for Human Pose Estimation and Tracking')
- Lightweight OpenPose ('Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose')
- IBPPose ('Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation')
- VOCA ('Capture, Learning, and Synthesis of 3D Speaking Styles')
- Neural Voice Puppetry Audio-to-Expression net ('Neural Voice Puppetry: Audio-driven Facial Reenactment')
- Jasper/JasperDR ('Jasper: An End-to-End Convolutional Neural Acoustic Model')
- QuartzNet ('QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions')
To use the models in your project, simply install the tf2cv package with tensorflow:
pip install tf2cv tensorflow>=2.0.0
To enable/disable different hardware supports, check out TensorFlow installation instructions.
Example of using a pretrained ResNet-18 model (with channels_first data format):
from tf2cv.model_provider import get_model as tf2cv_get_model
import tensorflow as tf
net = tf2cv_get_model("resnet18", pretrained=True, data_format="channels_last")
x = tf.random.normal((1, 224, 224, 3))
y_net = net(x)
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.
- Remark
Converted from GL modelmeans that the model was trained onMXNet/Gluonand then converted to TensorFlow. - 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 non-standard preprocessing (see the training log).
| Model | Top1 | Top5 | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|---|
| AlexNet | 38.06 | 16.09 | 62,378,344 | 1,132.33M | Converted from GL model (log) |
| AlexNet-b | 39.28 | 17.06 | 61,100,840 | 714.83M | Converted from GL model (log) |
| ZFNet | 395.0 | 17.17 | 62,357,608 | 1,170.33M | Converted from GL model (log) |
| ZFNet-b | 36.28 | 14.80 | 107,627,624 | 2,479.13M | Converted from GL model (log) |
| VGG-11 | 29.59 | 10.17 | 132,863,336 | 7,615.87M | Converted from GL model (log) |
| VGG-13 | 28.41 | 9.51 | 133,047,848 | 11,317.65M | Converted from GL model (log) |
| VGG-16 | 26.59 | 8.34 | 138,357,544 | 15,480.10M | Converted from GL model (log) |
| VGG-19 | 25.57 | 7.68 | 143,667,240 | 19,642.55M | Converted from GL model (log) |
| BN-VGG-11 | 28.57 | 9.36 | 132,866,088 | 7,630.21M | Converted from GL model (log) |
| BN-VGG-13 | 27.67 | 8.87 | 133,050,792 | 11,341.62M | Converted from GL model (log) |
| BN-VGG-16 | 25.46 | 7.59 | 138,361,768 | 15,506.38M | Converted from GL model (log) |
| BN-VGG-19 | 23.89 | 6.88 | 143,672,744 | 19,671.15M | Converted from GL model (log) |
| BN-VGG-11b | 29.31 | 9.75 | 132,868,840 | 7,630.72M | Converted from GL model (log) |
| BN-VGG-13b | 28.23 | 9.16 | 133,053,736 | 11,342.14M | Converted from GL model (log) |
| BN-VGG-16b | 25.80 | 7.76 | 138,365,992 | 15,507.20M | Converted from GL model (log) |
| BN-VGG-19b | 24.86 | 7.33 | 143,678,248 | 19,672.26M | Converted from GL model (log) |
| BN-Inception | 26.62 | 8.65 | 11,295,240 | 2,048.06M | Converted from GL model (log) |
| ResNet-10 | 31.90 | 12.26 | 5,418,792 | 894.04M | Converted from GL model (log) |
| ResNet-12 | 31.63 | 12.01 | 5,492,776 | 1,126.25M | Converted from GL model (log) |
| ResNet-14 | 30.38 | 10.91 | 5,788,200 | 1,357.94M | Converted from GL model (log) |
| ResNet-BC-14b | 29.19 | 10.37 | 10,064,936 | 1,479.12M | Converted from GL model (log) |
| ResNet-16 | 28.54 | 9.77 | 6,968,872 | 1,589.34M | Converted from GL model (log) |
| ResNet-18 x0.25 | 39.30 | 17.45 | 3,937,400 | 270.94M | Converted from GL model (log) |
| ResNet-18 x0.5 | 33.40 | 12.83 | 5,804,296 | 608.70M | Converted from GL model (log) |
| ResNet-18 x0.75 | 29.98 | 10.67 | 8,476,056 | 1,129.45M | Converted from GL model (log) |
| ResNet-18 | 26.80 | 8.70 | 11,689,512 | 1,820.41M | Converted from GL model (log) |
| ResNet-26 | 25.97 | 8.24 | 17,960,232 | 2,746.79M | Converted from GL model (log) |
| ResNet-BC-26b | 24.80 | 7.57 | 15,995,176 | 2,356.67M | Converted from GL model (log) |
| ResNet-34 | 24.50 | 7.44 | 21,797,672 | 3,672.68M | Converted from GL model (log) |
| ResNet-BC-38b | 23.44 | 6.77 | 21,925,416 | 3,234.21M | Converted from GL model (log) |
| ResNet-50 | 22.09 | 6.04 | 25,557,032 | 3,877.95M | Converted from GL model (log) |
| ResNet-50b | 22.09 | 6.14 | 25,557,032 | 4,110.48M | Converted from GL model (log) |
| ResNet-101 | 20.52 | 5.18 | 44,549,160 | 7,597.95M | Converted from GL model (log) |
| ResNet-101b | 20.25 | 5.11 | 44,549,160 | 7,830.48M | Converted from GL model (log) |
| ResNet-152 | 19.15 | 4.44 | 60,192,808 | 11,321.85M | Converted from GL model (log) |
| ResNet-152b | 18.85 | 4.31 | 60,192,808 | 11,554.38M | Converted from GL model (log) |
| PreResNet-10 | 34.71 | 14.02 | 5,417,128 | 894.19M | Converted from GL model (log) |
| PreResNet-12 | 33.63 | 13.20 | 5,491,112 | 1,126.40M | Converted from GL model (log) |
| PreResNet-14 | 32.29 | 12.24 | 5,786,536 | 1,358.09M | Converted from GL model (log) |
| PreResNet-BC-14b | 30.73 | 11.52 | 10,057,384 | 1,476.62M | Converted from GL model (log) |
| PreResNet-16 | 30.17 | 10.80 | 6,967,208 | 1,589.49M | Converted from GL model (log) |
| PreResNet-18 x0.25 | 39.61 | 17.80 | 3,935,960 | 270.93M | Converted from GL model (log) |
| PreResNet-18 x0.5 | 33.70 | 13.14 | 5,802,440 | 608.73M | Converted from GL model (log) |
| PreResNet-18 x0.75 | 29.95 | 10.70 | 8,473,784 | 1,129.51M | Converted from GL model (log) |
| PreResNet-18 | 28.20 | 9.55 | 11,687,848 | 1,820.56M | Converted from GL model (log) |
| PreResNet-26 | 25.98 | 8.37 | 17,958,568 | 2,746.94M | Converted from GL model (log) |
| PreResNet-BC-26b | 25.22 | 7.88 | 15,987,624 | 2,354.16M | Converted from GL model (log) |
| PreResNet-34 | 24.60 | 7.54 | 21,796,008 | 3,672.83M | Converted from GL model (log) |
| PreResNet-BC-38b | 22.70 | 6.36 | 21,917,864 | 3,231.70M | Converted from GL model (log) |
| PreResNet-50 | 22.22 | 6.25 | 25,549,480 | 3,875.44M | Converted from GL model (log) |
| PreResNet-50b | 22.37 | 6.34 | 25,549,480 | 4,107.97M | Converted from GL model (log) |
| PreResNet-101 | 20.59 | 5.36 | 44,541,608 | 7,595.44M | Converted from GL model (log) |
| PreResNet-101b | 20.86 | 5.39 | 44,541,608 | 7,827.97M | Converted from GL model (log) |
| PreResNet-152 | 19.17 | 4.46 | 60,185,256 | 11,319.34M | Converted from GL model (log) |
| PreResNet-152b | 19.00 | 4.39 | 60,185,256 | 11,551.87M | Converted from GL model (log) |
| PreResNet-200b | 18.96 | 4.48 | 64,666,280 | 15,068.63M | Converted from GL model (log) |
| PreResNet-269b | 20.15 | 5.05 | 102,065,832 | 20,101.11M | Converted from GL model (log) |
| ResNeXt-14 (16x4d) | 31.69 | 12.22 | 7,127,336 | 1,045.77M | Converted from GL model (log) |
| ResNeXt-14 (32x2d) | 32.14 | 12.47 | 7,029,416 | 1,031.32M | Converted from GL model (log) |
| ResNeXt-14 (32x4d) | 29.94 | 11.15 | 9,411,880 | 1,603.46M | Converted from GL model (log) |
| ResNeXt-26 (32x2d) | 26.32 | 8.51 | 9,924,136 | 1,461.06M | Converted from GL model (log) |
| ResNeXt-26 (32x4d) | 23.94 | 7.18 | 15,389,480 | 2,488.07M | Converted from GL model (log) |
| ResNeXt-50 (32x4d) | 20.82 | 5.47 | 25,028,904 | 4,255.86M | Converted from GL model (log) |
| ResNeXt-101 (32x4d) | 18.50 | 4.18 | 44,177,704 | 8,003.45M | Converted from GL model (log) |
| ResNeXt-101 (64x4d) | 18.78 | 4.38 | 83,455,272 | 15,500.27M | Converted from GL model (log) |
| SE-ResNet-10 | 31.42 | 11.71 | 5,463,332 | 894.27M | Converted from GL model (log) |
| SE-ResNet-12 | 31.61 | 11.77 | 5,537,896 | 1,126.58M | Converted from GL model (log) |
| SE-ResNet-14 | 30.40 | 11.01 | 5,835,504 | 1,358.33M | Converted from GL model (log) |
| SE-ResNet-16 | 28.36 | 9.71 | 7,024,640 | 1,589.76M | Converted from GL model (log) |
| SE-ResNet-18 | 27.97 | 9.21 | 11,778,592 | 1,820.88M | Converted from GL model (log) |
| SE-ResNet-26 | 25.42 | 8.07 | 18,093,852 | 2,747.49M | Converted from GL model (log) |
| SE-ResNet-BC-26b | 23.39 | 6.84 | 17,395,976 | 2,359.58M | Converted from GL model (log) |
| SE-ResNet-BC-38b | 21.43 | 5.75 | 24,026,616 | 3,238.58M | Converted from GL model (log) |
| SE-ResNet-50 | 21.09 | 5.60 | 28,088,024 | 3,883.25M | Converted from GL model (log) |
| SE-ResNet-50b | 20.58 | 5.33 | 28,088,024 | 4,115.78M | Converted from GL model (log) |
| SE-ResNet-101 | 19.03 | 4.40 | 49,326,872 | 7,602.76M | Converted from GL model (log) |
| SE-ResNet-101b | 19.49 | 4.64 | 49,326,872 | 7,839.75M | Converted from GL model (log) |
| SE-ResNet-152 | 18.62 | 4.29 | 66,821,848 | 11,328.52M | Converted from GL model (log) |
| SE-PreResNet-10 | 32.37 | 12.21 | 5,461,668 | 894.42M | Converted from GL model (log) |
| SE-PreResNet-12 | 31.62 | 11.82 | 5,536,232 | 1,126.73M | Converted from GL model (log) |
| SE-PreResNet-16 | 28.38 | 9.56 | 7,022,976 | 1,589.91M | Converted from GL model (log) |
| SE-PreResNet-18 | 27.13 | 8.82 | 11,776,928 | 1,821.03M | Converted from GL model (log) |
| SE-PreResNet-26 | 25.92 | 8.05 | 18,092,188 | 2,747.64M | Converted from GL model (log) |
| SE-PreResNet-BC-26b | 22.95 | 6.40 | 17,388,424 | 2,357.07M | Converted from GL model (log) |
| SE-PreResNet-BC-38b | 21.44 | 5.67 | 24,019,064 | 3,236.07M | Converted from GL model (log) |
| SE-PreResNet-50b | 20.71 | 5.31 | 28,080,472 | 4,113.27M | Converted from GL model (log) |
| SE-ResNeXt-50 (32x4d) | 18.73 | 4.34 | 27,559,896 | 4,261.16M | Converted from GL model (log) |
| SE-ResNeXt-101 (32x4d) | 19.07 | 4.46 | 48,955,416 | 8,012.73M | Converted from GL model (log) |
| SE-ResNeXt-101 (64x4d) | 18.47 | 4.07 | 88,232,984 | 15,509.54M | Converted from GL model (log) |
| SENet-16 | 25.37 | 8.05 | 31,366,168 | 5,081.30M | Converted from GL model (log) |
| SENet-28 | 21.68 | 5.90 | 36,453,768 | 5,732.71M | Converted from GL model (log) |
| SENet-154 | 18.85 | 4.40 | 115,088,984 | 20,745.78M | Converted from GL model (log) |
| ResNeSt(A)-BC-14 | 22.27 | 6.35 | 10,611,688 | 2,767.37M | Converted from GL model (log) |
| ResNeSt(A)-18 | 23.42 | 6.90 | 12,763,784 | 2,587.50M | Converted from GL model (log) |
| ResNeSt(A)-BC-26 | 19.58 | 4.70 | 17,069,448 | 3,646.57M | Converted from GL model (log) |
| ResNeSt(A)-50 | 18.92 | 4.39 | 27,483,240 | 5,403.11M | Converted from GL model (log) |
| ResNeSt(A)-101 | 17.71 | 4.00 | 48,275,016 | 10,247.88M | From dmlc/gluon-cv (log) |
| ResNeSt(A)-152 | 18.71 | 4.50 | 65,316,040 | 13,976.34M | Converted from GL model (log) |
| ResNeSt(A)-200 | 16.81 | 3.38 | 70,201,544 | 22,857.88M | From dmlc/gluon-cv (log) |
| ResNeSt(A)-269 | 16.37 | 3.36 | 110,929,480 | 46,012.95M | From dmlc/gluon-cv (log) |
| IBN-ResNet-50 | 21.47 | 5.62 | 25,557,032 | 4,110.48M | Converted from GL model (log) |
| IBN-ResNet-101 | 19.69 | 4.89 | 44,549,160 | 7,830.48M | Converted from GL model (log) |
| IBN(b)-ResNet-50 | 21.69 | 5.80 | 25,558,568 | 4,112.89M | Converted from GL model (log) |
| IBN-ResNeXt-101 (32x4d) | 19.78 | 4.90 | 44,177,704 | 8,003.45M | Converted from GL model (log) |
| IBN-DenseNet-121 | 23.34 | 6.47 | 7,978,856 | 2,872.13M | Converted from GL model (log) |
| IBN-DenseNet-169 | 22.13 | 6.07 | 14,149,480 | 3,403.89M | Converted from GL model (log) |
| AirNet50-1x64d (r=2) | 20.55 | 5.28 | 27,425,864 | 4,772.11M | Converted from GL model (log) |
| AirNet50-1x64d (r=16) | 21.12 | 5.50 | 25,714,952 | 4,399.97M | Converted from GL model (log) |
| AirNeXt50-32x4d (r=2) | 19.90 | 5.14 | 27,604,296 | 5,339.58M | Converted from GL model (log) |
| BAM-ResNet-50 | 20.60 | 5.37 | 25,915,099 | 4,196.09M | Converted from GL model (log) |
| CBAM-ResNet-50 | 19.97 | 4.86 | 28,089,624 | 4,116.97M | Converted from GL model (log) |
| SCNet-50 | 21.18 | 5.39 | 25,564,584 | 3,951.06M | Converted from GL model (log) |
| SCNet-101 | 19.82 | 4.73 | 44,565,416 | 7,204.24M | Converted from GL model (log) |
| SCNet(A)-50 | 19.61 | 4.65 | 25,583,816 | 4,715.84M | From MCG-NKU/SCNet (log) |
| RegNetX-200MF | 29.94 | 10.37 | 2,684,792 | 203.33M | Converted from GL model (log) |
| RegNetX-400MF | 26.28 | 8.52 | 5,157,512 | 403.45M | Converted from GL model (log) |
| RegNetX-600MF | 24.69 | 7.59 | 6,196,040 | 608.37M | Converted from GL model (log) |
| RegNetX-800MF | 24.11 | 7.27 | 7,259,656 | 809.49M | Converted from GL model (log) |
| RegNetX-1.6GF | 22.13 | 6.13 | 9,190,136 | 1,618.99M | Converted from GL model (log) |
| RegNetX-3.2GF | 21.31 | 5.68 | 15,296,552 | 3,199.55M | Converted from GL model (log) |
| RegNetX-4.0GF | 19.51 | 4.70 | 22,118,248 | 3,986.29M | Converted from GL model (log) |
| RegNetX-6.4GF | 19.21 | 4.57 | 26,209,256 | 6,491.01M | Converted from GL model (log) |
| RegNetX-8.0GF | 19.62 | 4.66 | 39,572,648 | 8,017.94M | Converted from GL model (log) |
| RegNetX-12GF | 19.96 | 5.21 | 46,106,056 | 12,124.22M | Converted from GL model (log) |
| RegNetX-16GF | 19.11 | 4.58 | 54,278,536 | 15,986.64M | Converted from GL model (log) |
| RegNetX-32GF | 17.86 | 3.95 | 107,811,560 | 31,790.24M | Converted from GL model (log) |
| RegNetY-200MF | 28.49 | 9.53 | 3,162,996 | 203.99M | Converted from GL model (log) |
| RegNetY-400MF | 24.82 | 7.50 | 4,344,144 | 410.35M | Converted from GL model (log) |
| RegNetY-600MF | 23.58 | 7.00 | 6,055,160 | 610.37M | Converted from GL model (log) |
| RegNetY-800MF | 22.53 | 6.46 | 6,263,168 | 808.62M | Converted from GL model (log) |
| RegNetY-1.6GF | 21.25 | 5.69 | 11,202,430 | 1,629.48M | Converted from GL model (log) |
| RegNetY-3.2GF | 18.31 | 4.11 | 19,436,338 | 3,199.15M | From rwightman/pyt...models (log) |
| RegNetY-4.0GF | 19.55 | 4.68 | 20,646,656 | 3,999.16M | Converted from GL model (log) |
| RegNetY-6.4GF | 18.96 | 4.42 | 30,583,252 | 6,388.91M | Converted from GL model (log) |
| RegNetY-8.0GF | 18.77 | 4.39 | 39,180,068 | 7,996.54M | Converted from GL model (log) |
| RegNetY-12GF | 18.49 | 4.29 | 51,822,544 | 12,132.55M | Converted from GL model (log) |
| RegNetY-16GF | 18.67 | 4.29 | 83,590,140 | 15,944.53M | Converted from GL model (log) |
| RegNetY-32GF | 17.79 | 3.73 | 145,046,770 | 32,317.66M | Converted from GL model (log) |
| PyramidNet-101 (a=360) | 20.42 | 5.20 | 42,455,070 | 8,743.54M | Converted from GL model (log) |
| DiracNetV2-18 | 30.59 | 11.13 | 11,511,784 | 1,796.62M | From szagoruyko/diracnets (log) |
| DiracNetV2-34 | 27.92 | 9.50 | 21,616,232 | 3,646.93M | From szagoruyko/diracnets (log) |
| DenseNet-121 | 23.23 | 6.84 | 7,978,856 | 2,872.13M | Converted from GL model (log) |
| DenseNet-161 | 21.84 | 5.91 | 28,681,000 | 7,793.16M | Converted from GL model (log) |
| DenseNet-169 | 22.13 | 6.06 | 14,149,480 | 3,403.89M | Converted from GL model (log) |
| DenseNet-201 | 21.57 | 5.91 | 20,013,928 | 4,347.15M | Converted from GL model (log) |
| PeleeNet | 29.39 | 9.82 | 2,802,248 | 514.87M | Converted from GL model (log) |
| WRN-50-2 | 22.03 | 6.08 | 68,849,128 | 11,405.42M | Converted from GL model (log) |
| DRN-C-26 | 24.36 | 7.10 | 21,126,584 | 16,993.90M | Converted from GL model (log) |
| DRN-C-42 | 22.27 | 6.12 | 31,234,744 | 25,093.75M | Converted from GL model (log) |
| DRN-C-58 | 20.44 | 5.17 | 40,542,008 | 32,489.94M | Converted from GL model (log) |
| DRN-D-22 | 24.71 | 7.47 | 16,393,752 | 13,051.33M | Converted from GL model (log) |
| DRN-D-38 | 22.82 | 6.23 | 26,501,912 | 21,151.19M | Converted from GL model (log) |
| DRN-D-54 | 20.29 | 4.98 | 35,809,176 | 28,547.38M | Converted from GL model (log) |
| DRN-D-105 | 19.78 | 4.89 | 54,801,304 | 43,442.43M | Converted from GL model (log) |
| DPN-68 | 22.92 | 6.58 | 12,611,602 | 2,351.84M | Converted from GL model (log) |
| DPN-98 | 18.30 | 4.26 | 61,570,728 | 11,716.51M | Converted from GL model (log) |
| DPN-131 | 19.39 | 4.77 | 79,254,504 | 16,076.15M | Converted from GL model (log) |
| DarkNet Tiny | 40.34 | 17.45 | 1,042,104 | 500.85M | Converted from GL model (log) |
| DarkNet Ref | 38.10 | 16.71 | 7,319,416 | 367.59M | Converted from GL model (log) |
| DarkNet-53 | 21.26 | 5.54 | 41,609,928 | 7,133.86M | Converted from GL model (log) |
| BagNet-9 | 48.78 | 25.41 | 15,688,744 | 16,049.19M | Converted from GL model (log) |
| BagNet-17 | 36.56 | 15.23 | 16,213,032 | 15,768.77M | Converted from GL model (log) |
| BagNet-33 | 29.44 | 10.41 | 18,310,184 | 16,371.52M | Converted from GL model (log) |
| DLA-34 | 24.37 | 7.05 | 15,742,104 | 3,071.37M | Converted from GL model (log) |
| DLA-46-C | 33.83 | 12.87 | 1,301,400 | 585.45M | Converted from GL model (log) |
| DLA-X-46-C | 32.90 | 12.29 | 1,068,440 | 546.72M | Converted from GL model (log) |
| DLA-60 | 21.26 | 5.53 | 22,036,632 | 4,255.49M | Converted from GL model (log) |
| DLA-X-60 | 20.72 | 5.50 | 17,352,344 | 3,543.68M | Converted from GL model (log) |
| DLA-X-60-C | 30.66 | 10.75 | 1,319,832 | 596.06M | Converted from GL model (log) |
| DLA-102 | 20.57 | 5.17 | 33,268,888 | 7,190.95M | Converted from GL model (log) |
| DLA-X-102 | 19.59 | 4.74 | 26,309,272 | 5,884.94M | Converted from GL model (log) |
| DLA-X2-102 | 18.69 | 4.28 | 41,282,200 | 9,340.61M | Converted from GL model (log) |
| DLA-169 | 19.27 | 4.62 | 53,389,720 | 11,593.20M | Converted from GL model (log) |
| DiCENet x0.2 | 55.84 | 31.16 | 1,130,704 | 18.76M | From sacmehta/EdgeNets (log) |
| DiCENet x0.5 | 47.54 | 23.41 | 1,214,120 | 30.48M | Converted from GL model (log) |
| DiCENet x0.75 | 38.11 | 16.66 | 1,495,676 | 55.80M | Converted from GL model (log) |
| DiCENet x1.0 | 35.47 | 14.39 | 1,805,604 | 82.17M | Converted from GL model (log) |
| DiCENet x1.25 | 33.66 | 12.86 | 2,162,888 | 111.87M | Converted from GL model (log) |
| DiCENet x1.5 | 31.34 | 11.73 | 2,652,200 | 151.81M | Converted from GL model (log) |
| DiCENet x1.75 | 30.74 | 11.31 | 3,264,932 | 201.26M | Converted from GL model (log) |
| DiCENet x2.0 | 28.31 | 9.55 | 3,979,044 | 257.95M | Converted from GL model (log) |
| HRNet-W18 Small V1 | 26.23 | 8.71 | 13,187,464 | 1,614.87M | Converted from GL model (log) |
| HRNet-W18 Small V2 | 21.69 | 6.02 | 15,597,464 | 2,618.54M | Converted from GL model (log) |
| HRNetV2-W18 | 20.17 | 5.04 | 21,299,004 | 4,322.66M | Converted from GL model (log) |
| HRNetV2-W30 | 20.33 | 5.08 | 37,712,220 | 8,156.14M | Converted from GL model (log) |
| HRNetV2-W32 | 19.94 | 4.95 | 41,232,680 | 8,973.31M | Converted from GL model (log) |
| HRNetV2-W40 | 19.67 | 4.80 | 57,557,160 | 12,751.34M | Converted from GL model (log) |
| HRNetV2-W44 | 19.63 | 4.88 | 67,064,984 | 14,945.95M | Converted from GL model (log) |
| HRNetV2-W48 | 19.44 | 4.81 | 77,469,864 | 17,344.29M | Converted from GL model (log) |
| HRNetV2-W64 | 19.50 | 4.79 | 128,059,944 | 28,974.95M | Converted from GL model (log) |
| VoVNet-27-slim | 31.86 | 11.54 | 3,525,736 | 2,187.25M | Converted from GL model (log) |
| VoVNet-39 | 23.75 | 6.94 | 22,600,296 | 7,086.16M | Converted from GL model (log) |
| VoVNet-57 | 22.42 | 6.23 | 36,640,296 | 8,943.09M | Converted from GL model (log) |
| SelecSLS-42b | 21.79 | 5.98 | 32,458,248 | 2,980.62M | Converted from GL model (log) |
| SelecSLS-60 | 20.17 | 5.13 | 30,670,768 | 3,591.78M | Converted from GL model (log) |
| SelecSLS-60b | 20.61 | 5.38 | 32,774,064 | 3,629.14M | Converted from GL model (log) |
| HarDNet-39DS | 26.49 | 8.71 | 3,488,228 | 437.52M | Converted from GL model (log) |
| HarDNet-68DS | 24.24 | 7.41 | 4,180,602 | 788.86M | Converted from GL model (log) |
| HarDNet-68 | 24.00 | 7.04 | 17,565,348 | 4,256.32M | Converted from GL model (log) |
| HarDNet-85 | 21.84 | 5.69 | 36,670,212 | 9,088.58M | Converted from GL model (log) |
| SqueezeNet v1.0 | 39.23 | 17.60 | 1,248,424 | 823.67M | Converted from GL model (log) |
| SqueezeNet v1.1 | 39.12 | 17.42 | 1,235,496 | 352.02M | Converted from GL model (log) |
| SqueezeResNet v1.0 | 39.38 | 17.83 | 1,248,424 | 823.67M | Converted from GL model (log) |
| SqueezeResNet v1.1 | 39.85 | 17.89 | 1,235,496 | 352.02M | Converted from GL model (log) |
| 1.0-SqNxt-23 | 42.31 | 18.61 | 724,056 | 287.28M | Converted from GL model (log) |
| 1.0-SqNxt-23v5 | 40.44 | 17.62 | 921,816 | 285.82M | Converted from GL model (log) |
| 1.5-SqNxt-23 | 34.62 | 13.34 | 1,511,824 | 552.39M | Converted from GL model (log) |
| 1.5-SqNxt-23v5 | 33.55 | 12.84 | 1,953,616 | 550.97M | Converted from GL model (log) |
| 2.0-SqNxt-23 | 30.12 | 10.69 | 2,583,752 | 898.48M | Converted from GL model (log) |
| 2.0-SqNxt-23v5 | 29.40 | 10.26 | 3,366,344 | 897.60M | Converted from GL model (log) |
| ShuffleNet x0.25 (g=1) | 62.05 | 36.81 | 209,746 | 12.35M | Converted from GL model (log) |
| ShuffleNet x0.25 (g=3) | 61.31 | 36.18 | 305,902 | 13.09M | Converted from GL model (log) |
| ShuffleNet x0.5 (g=1) | 46.25 | 22.36 | 534,484 | 41.16M | Converted from GL model (log) |
| ShuffleNet x0.5 (g=3) | 43.84 | 20.59 | 718,324 | 41.70M | Converted from GL model (log) |
| ShuffleNet x0.75 (g=1) | 39.24 | 16.79 | 975,214 | 86.42M | Converted from GL model (log) |
| ShuffleNet x0.75 (g=3) | 37.80 | 16.11 | 1,238,266 | 85.82M | Converted from GL model (log) |
| ShuffleNet x1.0 (g=1) | 34.48 | 13.48 | 1,531,936 | 148.13M | Converted from GL model (log) |
| ShuffleNet x1.0 (g=2) | 33.95 | 13.33 | 1,733,848 | 147.60M | Converted from GL model (log) |
| ShuffleNet x1.0 (g=3) | 33.93 | 13.32 | 1,865,728 | 145.46M | Converted from GL model (log) |
| ShuffleNet x1.0 (g=4) | 33.88 | 13.13 | 1,968,344 | 143.33M | Converted from GL model (log) |
| ShuffleNet x1.0 (g=8) | 33.71 | 13.22 | 2,434,768 | 150.76M | Converted from GL model (log) |
| ShuffleNetV2 x0.5 | 40.75 | 18.43 | 1,366,792 | 43.31M | Converted from GL model (log) |
| ShuffleNetV2 x1.0 | 31.00 | 11.35 | 2,278,604 | 149.72M | Converted from GL model (log) |
| ShuffleNetV2 x1.5 | 27.41 | 9.23 | 4,406,098 | 320.77M | Converted from GL model (log) |
| ShuffleNetV2 x2.0 | 25.83 | 8.21 | 7,601,686 | 595.84M | Converted from GL model (log) |
| ShuffleNetV2b x0.5 | 39.80 | 17.84 | 1,366,792 | 43.31M | Converted from GL model (log) |
| ShuffleNetV2b x1.0 | 30.36 | 11.04 | 2,279,760 | 150.62M | Converted from GL model (log) |
| ShuffleNetV2b x1.5 | 26.90 | 8.77 | 4,410,194 | 323.98M | Converted from GL model (log) |
| ShuffleNetV2b x2.0 | 25.24 | 8.08 | 7,611,290 | 603.37M | Converted from GL model (log) |
| 108-MENet-8x1 (g=3) | 43.64 | 20.39 | 654,516 | 42.68M | Converted from GL model (log) |
| 128-MENet-8x1 (g=4) | 42.04 | 19.18 | 750,796 | 45.98M | Converted from GL model (log) |
| 160-MENet-8x1 (g=8) | 43.48 | 20.34 | 850,120 | 45.63M | Converted from GL model (log) |
| 228-MENet-12x1 (g=3) | 33.80 | 12.91 | 1,806,568 | 152.93M | Converted from GL model (log) |
| 256-MENet-12x1 (g=4) | 32.28 | 12.17 | 1,888,240 | 150.65M | Converted from GL model (log) |
| 348-MENet-12x1 (g=3) | 27.81 | 9.37 | 3,368,128 | 312.00M | Converted from GL model (log) |
| 352-MENet-12x1 (g=8) | 31.33 | 11.67 | 2,272,872 | 157.35M | Converted from GL model (log) |
| 456-MENet-24x1 (g=3) | 25.02 | 7.79 | 5,304,784 | 567.90M | Converted from GL model (log) |
| MobileNet x0.25 | 45.84 | 22.13 | 470,072 | 44.09M | Converted from GL model (log) |
| MobileNet x0.5 | 33.86 | 13.33 | 1,331,592 | 155.42M | Converted from GL model (log) |
| MobileNet x0.75 | 29.88 | 10.51 | 2,585,560 | 333.99M | Converted from GL model (log) |
| MobileNet x1.0 | 26.45 | 8.66 | 4,231,976 | 579.80M | Converted from GL model (log) |
| MobileNetb x0.25 | 45.22 | 21.69 | 467,592 | 42.88M | Converted from GL model (log) |
| MobileNetb x0.5 | 32.90 | 12.69 | 1,326,632 | 153.00M | Converted from GL model (log) |
| MobileNetb x0.75 | 29.08 | 10.18 | 2,578,120 | 330.37M | Converted from GL model (log) |
| MobileNetb x1.0 | 25.04 | 7.89 | 4,222,056 | 574.97M | Converted from GL model (log) |
| FD-MobileNet x0.25 | 55.42 | 30.62 | 383,160 | 12.95M | Converted from GL model (log) |
| FD-MobileNet x0.5 | 42.66 | 19.77 | 993,928 | 41.84M | Converted from GL model (log) |
| FD-MobileNet x0.75 | 37.97 | 15.97 | 1,833,304 | 86.68M | Converted from GL model (log) |
| FD-MobileNet x1.0 | 33.90 | 13.12 | 2,901,288 | 147.46M | Converted from GL model (log) |
| MobileNetV2 x0.25 | 48.10 | 24.13 | 1,516,392 | 34.24M | Converted from GL model (log) |
| MobileNetV2 x0.5 | 35.62 | 14.46 | 1,964,736 | 100.13M | Converted from GL model (log) |
| MobileNetV2 x0.75 | 29.75 | 10.44 | 2,627,592 | 198.50M | Converted from GL model (log) |
| MobileNetV2 x1.0 | 26.80 | 8.63 | 3,504,960 | 329.36M | Converted from GL model (log) |
| MobileNetV2b x0.25 | 46.77 | 23.41 | 1,516,312 | 33.18M | Converted from GL model (log) |
| MobileNetV2b x0.5 | 34.26 | 13.75 | 1,964,448 | 96.42M | Converted from GL model (log) |
| MobileNetV2b x0.75 | 30.14 | 10.66 | 2,626,968 | 190.52M | Converted from GL model (log) |
| MobileNetV2b x1.0 | 27.16 | 8.91 | 3,503,872 | 315.51M | Converted from GL model (log) |
| MobileNetV3 L/224/1.0 | 24.36 | 7.32 | 5,481,752 | 226.80M | Converted from GL model (log) |
| IGCV3 x0.25 | 53.38 | 28.28 | 1,534,020 | 41.29M | Converted from GL model (log) |
| IGCV3 x0.5 | 39.36 | 17.01 | 1,985,528 | 111.12M | Converted from GL model (log) |
| IGCV3 x0.75 | 30.74 | 11.00 | 2,638,084 | 210.95M | Converted from GL model (log) |
| IGCV3 x1.0 | 27.70 | 8.99 | 3,491,688 | 340.79M | Converted from GL model (log) |
| MnasNet-B1 | 24.70 | 7.22 | 4,383,312 | 326.30M | Converted from GL model (log) |
| MnasNet-A1 | 24.08 | 7.05 | 3,887,038 | 326.07M | Converted from GL model (log) |
| ProxylessNAS CPU | 24.77 | 7.51 | 4,361,648 | 459.96M | Converted from GL model (log) |
| ProxylessNAS GPU | 24.65 | 7.26 | 7,119,848 | 476.08M | Converted from GL model (log) |
| ProxylessNAS Mobile | 25.29 | 7.83 | 4,080,512 | 332.46M | Converted from GL model (log) |
| ProxylessNAS Mob-14 | 22.93 | 6.53 | 6,857,568 | 597.10M | Converted from GL model (log) |
| FBNet-Cb | 24.82 | 7.65 | 5,572,200 | 399.26M | Converted from GL model (log) |
| Xception | 20.41 | 5.20 | 22,855,952 | 8,403.63M | Converted from GL model (log) |
| InceptionV3 | 20.44 | 5.36 | 23,834,568 | 5,743.06M | Converted from GL model (log) |
| InceptionV4 | 19.94 | 5.06 | 42,679,816 | 12,304.93M | Converted from GL model (log) |
| InceptionResNetV1 | 19.57 | 4.80 | 23,995,624 | 6,329.60M | Converted from GL model (log) |
| InceptionResNetV2 | 19.43 | 4.70 | 55,843,464 | 13,188.64M | Converted from GL model (log) |
| PolyNet | 19.09 | 4.51 | 95,366,600 | 34,821.34M | From Cadene/pretrained...pytorch (log) |
| NASNet-A 4@1056 | 25.67 | 8.15 | 5,289,978 | 584.90M | Converted from GL model (log) |
| NASNet-A 6@4032 | 18.24 | 4.27 | 88,753,150 | 23,976.44M | From Cadene/pretrained...pytorch (log) |
| PNASNet-5-Large | 18.02 | 4.27 | 86,057,668 | 25,140.77M | From Cadene/pretrained...pytorch (log) |
| SPNASNet | 25.06 | 7.77 | 4,421,616 | 346.73M | Converted from GL model (log) |
| EfficientNet-B0 | 24.49 | 7.25 | 5,288,548 | 413.13M | Converted from GL model (log) |
| EfficientNet-B1 | 22.93 | 6.30 | 7,794,184 | 730.44M | Converted from GL model (log) |
| EfficientNet-B0b | 23.05 | 6.68 | 5,288,548 | 413.13M | From rwightman/pyt...models (log) |
| EfficientNet-B1b | 21.17 | 5.77 | 7,794,184 | 730.44M | From rwightman/pyt...models (log) |
| EfficientNet-B2b | 20.22 | 5.30 | 9,109,994 | 1,049.29M | From rwightman/pyt...models (log) |
| EfficientNet-B3b | 19.14 | 4.69 | 12,233,232 | 1,923.98M | From rwightman/pyt...models (log) |
| EfficientNet-B4b | 17.52 | 3.99 | 19,341,616 | 4,597.56M | From rwightman/pyt...models (log) |
| EfficientNet-B5b | 16.43 | 3.43 | 30,389,784 | 10,674.67M | From rwightman/pyt...models (log) |
| EfficientNet-B6b | 15.96 | 3.12 | 43,040,704 | 19,761.35M | From rwightman/pyt...models (log) |
| EfficientNet-B7b | 15.85 | 3.15 | 66,347,960 | 38,949.07M | From rwightman/pyt...models (log) |
| EfficientNet-B0c* | 22.62 | 6.46 | 5,288,548 | 414.31M | From rwightman/pyt...models (log) |
| EfficientNet-B1c* | 20.98 | 5.82 | 7,794,184 | 732.54M | From rwightman/pyt...models (log) |
| EfficientNet-B2c* | 20.21 | 5.33 | 9,109,994 | 1,051.98M | From rwightman/pyt...models (log) |
| EfficientNet-B3c* | 18.80 | 4.64 | 12,233,232 | 1,928.55M | From rwightman/pyt...models (log) |
| EfficientNet-B4c* | 17.29 | 3.90 | 19,341,616 | 4,607.46M | From rwightman/pyt...models (log) |
| EfficientNet-B5c* | 15.87 | 3.10 | 30,389,784 | 10,695.20M | From rwightman/pyt...models (log) |
| EfficientNet-B6c* | 15.29 | 2.86 | 43,040,704 | 19,796.24M | From rwightman/pyt...models (log) |
| EfficientNet-B7c* | 14.96 | 2.76 | 66,347,960 | 39,010.98M | From rwightman/pyt...models (log) |
| EfficientNet-B8c* | 14.64 | 2.70 | 87,413,142 | 64,541.66M | From rwightman/pyt...models (log) |
| EfficientNet-Edge-Small-b* | 22.66 | 6.42 | 5,438,392 | 2,378.12M | From rwightman/pyt...models (log) |
| EfficientNet-Edge-Medium-b* | 21.38 | 5.65 | 6,899,496 | 3,700.12M | From rwightman/pyt...models (log) |
| EfficientNet-Edge-Large-b* | 19.86 | 4.96 | 10,589,712 | 9,747.66M | From rwightman/pyt...models (log) |
| MixNet-S | 23.86 | 7.07 | 4,134,606 | 260.26M | Converted from GL model (log) |
| MixNet-M | 22.39 | 6.32 | 5,014,382 | 366.05M | Converted from GL model (log) |
| MixNet-L | 21.44 | 5.56 | 7,329,252 | 590.45M | Converted from GL model (log) |
| ResNet(A)-10 | 30.89 | 11.61 | 5,438,024 | 1,135.86M | Converted from GL model (log) |
| ResNet(A)-BC-14 | 27.72 | 9.60 | 10,084,168 | 1,721.57M | Converted from GL model (log) |
| ResNet(A)-18 | 25.40 | 8.04 | 11,708,744 | 2,062.24M | Converted from GL model (log) |
| ResNet(A)-50b | 20.79 | 5.38 | 25,576,264 | 4,352.93M | Converted from GL model (log) |
| ResNet(A)-101b | 18.99 | 4.45 | 44,568,392 | 8,072.93M | Converted from GL model (log) |
| ResNet(A)-152b | 18.59 | 4.26 | 60,212,040 | 11,796.83M | Converted from GL model (log) |
| ResNet(D)-50b | 20.80 | 5.49 | 25,680,808 | 20,497.60M | From dmlc/gluon-cv (log) |
| ResNet(D)-101b | 19.51 | 4.59 | 44,672,936 | 35,392.65M | From dmlc/gluon-cv (log) |
| ResNet(D)-152b | 19.37 | 4.68 | 60,316,584 | 47,662.18M | From dmlc/gluon-cv (log) |
| Model | Error, % | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|
| ResNet-20 | 5.97 | 272,474 | 41.29M | Converted from GL model (log) |
| ResNet-56 | 4.52 | 855,770 | 127.06M | Converted from GL model (log) |
| ResNet-110 | 3.69 | 1,730,714 | 255.70M | Converted from GL model (log) |
| ResNet-164(BN) | 3.68 | 1,704,154 | 255.31M | Converted from GL model (log) |
| ResNet-272(BN) | 3.33 | 2,816,986 | 420.61M | Converted from GL model (log) |
| ResNet-542(BN) | 3.43 | 5,599,066 | 833.87M | Converted from GL model (log) |
| ResNet-1001 | 3.28 | 10,328,602 | 1,536.40M | Converted from GL model (log) |
| ResNet-1202 | 3.53 | 19,424,026 | 2,857.17M | Converted from GL model (log) |
| PreResNet-20 | 6.51 | 272,282 | 41.27M | Converted from GL model (log) |
| PreResNet-56 | 4.49 | 855,578 | 127.03M | Converted from GL model (log) |
| PreResNet-110 | 3.86 | 1,730,522 | 255.68M | Converted from GL model (log) |
| PreResNet-164(BN) | 3.64 | 1,703,258 | 255.08M | Converted from GL model (log) |
| PreResNet-272(BN) | 3.25 | 2,816,090 | 420.38M | Converted from GL model (log) |
| PreResNet-542(BN) | 3.14 | 5,598,170 | 833.64M | Converted from GL model (log) |
| PreResNet-1001 | 2.65 | 10,327,706 | 1,536.18M | Converted from GL model (log) |
| PreResNet-1202 | 3.39 | 19,423,834 | 2,857.14M | Converted from GL model (log) |
| ResNeXt-20 (1x64d) | 4.33 | 3,446,602 | 538.36M | Converted from GL model (log) |
| ResNeXt-20 (2x32d) | 4.53 | 2,672,458 | 425.15M | Converted from GL model (log) |
| ResNeXt-20 (4x16d) | 4.70 | 2,285,386 | 368.55M | Converted from GL model (log) |
| ResNeXt-20 (8x8d) | 4.66 | 2,091,850 | 340.25M | Converted from GL model (log) |
| ResNeXt-20 (16x4d) | 4.04 | 1,995,082 | 326.10M | Converted from GL model (log) |
| ResNeXt-20 (32x2d) | 4.61 | 1,946,698 | 319.03M | Converted from GL model (log) |
| ResNeXt-20 (64x1d) | 4.93 | 1,922,506 | 315.49M | Converted from GL model (log) |
| ResNeXt-20 (2x64d) | 4.03 | 6,198,602 | 987.98M | Converted from GL model (log) |
| ResNeXt-20 (4x32d) | 3.73 | 4,650,314 | 761.57M | Converted from GL model (log) |
| ResNeXt-20 (8x16d) | 4.04 | 3,876,170 | 648.37M | Converted from GL model (log) |
| ResNeXt-20 (16x8d) | 3.94 | 3,489,098 | 591.77M | Converted from GL model (log) |
| ResNeXt-20 (32x4d) | 4.20 | 3,295,562 | 563.47M | Converted from GL model (log) |
| ResNeXt-20 (64x2d) | 4.38 | 3,198,794 | 549.32M | Converted from GL model (log) |
| ResNeXt-56 (1x64d) | 2.87 | 9,317,194 | 1,399.33M | Converted from GL model (log) |
| ResNeXt-56 (2x32d) | 3.01 | 6,994,762 | 1,059.72M | Converted from GL model (log) |
| ResNeXt-56 (4x16d) | 3.11 | 5,833,546 | 889.91M | Converted from GL model (log) |
| ResNeXt-56 (8x8d) | 3.07 | 5,252,938 | 805.01M | Converted from GL model (log) |
| ResNeXt-56 (16x4d) | 3.12 | 4,962,634 | 762.56M | Converted from GL model (log) |
| ResNeXt-56 (32x2d) | 3.14 | 4,817,482 | 741.34M | Converted from GL model (log) |
| ResNeXt-56 (64x1d) | 3.41 | 4,744,906 | 730.72M | Converted from GL model (log) |
| ResNeXt-29 (32x4d) | 3.15 | 4,775,754 | 780.55M | Converted from GL model (log) |
| ResNeXt-29 (16x64d) | 2.41 | 68,155,210 | 10,709.34M | Converted from GL model (log) |
| ResNeXt-272 (1x64d) | 2.55 | 44,540,746 | 6,565.15M | Converted from GL model (log) |
| ResNeXt-272 (2x32d) | 2.74 | 32,928,586 | 4,867.11M | Converted from GL model (log) |
| SE-ResNet-20 | 6.01 | 274,847 | 41.34M | Converted from GL model (log) |
| SE-ResNet-56 | 4.13 | 862,889 | 127.19M | Converted from GL model (log) |
| SE-ResNet-110 | 3.63 | 1,744,952 | 255.98M | Converted from GL model (log) |
| SE-ResNet-164(BN) | 3.39 | 1,906,258 | 256.55M | Converted from GL model (log) |
| SE-ResNet-272(BN) | 3.39 | 3,153,826 | 422.68M | Converted from GL model (log) |
| SE-ResNet-542(BN) | 3.47 | 6,272,746 | 838.01M | Converted from GL model (log) |
| SE-PreResNet-20 | 6.18 | 274,559 | 41.35M | Converted from GL model (log) |
| SE-PreResNet-56 | 4.51 | 862,601 | 127.20M | Converted from GL model (log) |
| SE-PreResNet-110 | 4.54 | 1,744,664 | 255.98M | Converted from GL model (log) |
| SE-PreResNet-164(BN) | 3.73 | 1,904,882 | 256.32M | Converted from GL model (log) |
| SE-PreResNet-272(BN) | 3.39 | 3,152,450 | 422.45M | Converted from GL model (log) |
| SE-PreResNet-542(BN) | 3.09 | 6,271,370 | 837.78M | Converted from GL model (log) |
| PyramidNet-110 (a=48) | 3.72 | 1,772,706 | 408.37M | Converted from GL model (log) |
| PyramidNet-110 (a=84) | 2.98 | 3,904,446 | 778.15M | Converted from GL model (log) |
| PyramidNet-110 (a=270) | 2.51 | 28,485,477 | 4,730.60M | Converted from GL model (log) |
| PyramidNet-164 (a=270, BN) | 2.42 | 27,216,021 | 4,608.81M | Converted from GL model (log) |
| PyramidNet-200 (a=240, BN) | 2.44 | 26,752,702 | 4,563.40M | Converted from GL model (log) |
| PyramidNet-236 (a=220, BN) | 2.47 | 26,969,046 | 4,631.32M | Converted from GL model (log) |
| PyramidNet-272 (a=200, BN) | 2.39 | 26,210,842 | 4,541.36M | Converted from GL model (log) |
| DenseNet-40 (k=12) | 5.61 | 599,050 | 210.80M | Converted from GL model (log) |
| DenseNet-BC-40 (k=12) | 6.43 | 176,122 | 74.89M | Converted from GL model (log) |
| DenseNet-BC-40 (k=24) | 4.52 | 690,346 | 293.09M | Converted from GL model (log) |
| DenseNet-BC-40 (k=36) | 4.04 | 1,542,682 | 654.60M | Converted from GL model (log) |
| DenseNet-100 (k=12) | 3.66 | 4,068,490 | 1,353.55M | Converted from GL model (log) |
| DenseNet-100 (k=24) | 3.13 | 16,114,138 | 5,354.19M | Converted from GL model (log) |
| DenseNet-BC-100 (k=12) | 4.16 | 769,162 | 298.45M | Converted from GL model (log) |
| DenseNet-BC-190 (k=40) | 2.52 | 25,624,430 | 9,400.45M | Converted from GL model (log) |
| DenseNet-BC-250 (k=24) | 2.67 | 15,324,406 | 5,519.54M | Converted from GL model (log) |
| Model | Error, % | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|
| ResNet-20 | 29.64 | 278,324 | 41.30M | Converted from GL model (log) |
| ResNet-56 | 24.88 | 861,620 | 127.06M | Converted from GL model (log) |
| ResNet-110 | 22.80 | 1,736,564 | 255.71M | Converted from GL model (log) |
| ResNet-164(BN) | 20.44 | 1,727,284 | 255.33M | Converted from GL model (log) |
| ResNet-272(BN) | 20.07 | 2,840,116 | 420.63M | Converted from GL model (log) |
| ResNet-542(BN) | 19.32 | 5,622,196 | 833.89M | Converted from GL model (log) |
| ResNet-1001 | 19.79 | 10,351,732 | 1,536.43M | Converted from GL model (log) |
| ResNet-1202 | 21.56 | 19,429,876 | 2,857.17M | Converted from GL model (log) |
| PreResNet-20 | 30.22 | 278,132 | 41.28M | Converted from GL model (log) |
| PreResNet-56 | 25.05 | 861,428 | 127.04M | Converted from GL model (log) |
| PreResNet-110 | 22.67 | 1,736,372 | 255.68M | Converted from GL model (log) |
| PreResNet-164(BN) | 20.18 | 1,726,388 | 255.10M | Converted from GL model (log) |
| PreResNet-272(BN) | 19.63 | 2,839,220 | 420.40M | Converted from GL model (log) |
| PreResNet-542(BN) | 18.71 | 5,621,300 | 833.66M | Converted from GL model (log) |
| PreResNet-1001 | 18.41 | 10,350,836 | 1,536.20M | Converted from GL model (log) |
| ResNeXt-20 (1x64d) | 21.97 | 3,538,852 | 538.45M | Converted from GL model (log) |
| ResNeXt-20 (2x32d) | 22.55 | 2,764,708 | 425.25M | Converted from GL model (log) |
| ResNeXt-20 (4x16d) | 23.04 | 2,377,636 | 368.65M | Converted from GL model (log) |
| ResNeXt-20 (8x8d) | 22.82 | 2,184,100 | 340.34M | Converted from GL model (log) |
| ResNeXt-20 (16x4d) | 22.82 | 2,087,332 | 326.19M | Converted from GL model (log) |
| ResNeXt-20 (32x2d) | 21.73 | 2,038,948 | 319.12M | Converted from GL model (log) |
| ResNeXt-20 (64x1d) | 23.53 | 2,014,756 | 315.58M | Converted from GL model (log) |
| ResNeXt-20 (2x64d) | 20.60 | 6,290,852 | 988.07M | Converted from GL model (log) |
| ResNeXt-20 (4x32d) | 21.31 | 4,742,564 | 761.66M | Converted from GL model (log) |
| ResNeXt-20 (8x16d) | 21.72 | 3,968,420 | 648.46M | Converted from GL model (log) |
| ResNeXt-20 (16x8d) | 21.73 | 3,581,348 | 591.86M | Converted from GL model (log) |
| ResNeXt-20 (32x4d) | 22.13 | 3,387,812 | 563.56M | Converted from GL model (log) |
| ResNeXt-20 (64x2d) | 22.35 | 3,291,044 | 549.41M | Converted from GL model (log) |
| ResNeXt-56 (1x64d) | 18.25 | 9,409,444 | 1,399.42M | Converted from GL model (log) |
| ResNeXt-56 (2x32d) | 17.86 | 7,087,012 | 1,059.81M | Converted from GL model (log) |
| ResNeXt-56 (4x16d) | 18.09 | 5,925,796 | 890.01M | Converted from GL model (log) |
| ResNeXt-56 (8x8d) | 18.06 | 5,345,188 | 805.10M | Converted from GL model (log) |
| ResNeXt-56 (16x4d) | 18.24 | 5,054,884 | 762.65M | Converted from GL model (log) |
| ResNeXt-56 (32x2d) | 18.60 | 4,909,732 | 741.43M | Converted from GL model (log) |
| ResNeXt-56 (64x1d) | 18.16 | 4,837,156 | 730.81M | Converted from GL model (log) |
| ResNeXt-29 (32x4d) | 19.50 | 4,868,004 | 780.64M | Converted from GL model (log) |
| ResNeXt-29 (16x64d) | 16.93 | 68,247,460 | 10,709.43M | Converted from GL model (log) |
| ResNeXt-272 (1x64d) | 19.11 | 44,632,996 | 6,565.25M | Converted from GL model (log) |
| ResNeXt-272 (2x32d) | 18.34 | 33,020,836 | 4,867.20M | Converted from GL model (log) |
| SE-ResNet-20 | 28.54 | 280,697 | 41.35M | Converted from GL model (log) |
| SE-ResNet-56 | 22.94 | 868,739 | 127.07M | Converted from GL model (log) |
| SE-ResNet-110 | 20.86 | 1,750,802 | 255.98M | Converted from GL model (log) |
| SE-ResNet-164(BN) | 19.95 | 1,929,388 | 256.57M | Converted from GL model (log) |
| SE-ResNet-272(BN) | 19.07 | 3,176,956 | 422.70M | Converted from GL model (log) |
| SE-ResNet-542(BN) | 18.87 | 6,295,876 | 838.03M | Converted from GL model (log) |
| SE-PreResNet-20 | 28.31 | 280,409 | 41.35M | Converted from GL model (log) |
| SE-PreResNet-56 | 23.05 | 868,451 | 127.21M | Converted from GL model (log) |
| SE-PreResNet-110 | 22.61 | 1,750,514 | 255.99M | Converted from GL model (log) |
| SE-PreResNet-164(BN) | 20.05 | 1,928,012 | 256.34M | Converted from GL model (log) |
| SE-PreResNet-272(BN) | 19.13 | 3,175,580 | 422.47M | Converted from GL model (log) |
| SE-PreResNet-542(BN) | 19.45 | 6,294,500 | 837.80M | Converted from GL model (log) |
| PyramidNet-110 (a=48) | 20.95 | 1,778,556 | 408.38M | Converted from GL model (log) |
| PyramidNet-110 (a=84) | 18.87 | 3,913,536 | 778.16M | Converted from GL model (log) |
| PyramidNet-110 (a=270) | 17.10 | 28,511,307 | 4,730.62M | Converted from GL model (log) |
| PyramidNet-164 (a=270, BN) | 16.70 | 27,319,071 | 4,608.91M | Converted from GL model (log) |
| PyramidNet-200 (a=240, BN) | 16.09 | 26,844,952 | 4,563.49M | Converted from GL model (log) |
| PyramidNet-236 (a=220, BN) | 16.34 | 27,054,096 | 4,631.41M | Converted from GL model (log) |
| PyramidNet-272 (a=200, BN) | 16.19 | 26,288,692 | 4,541.43M | Converted from GL model (log) |
| DenseNet-40 (k=12) | 24.90 | 622,360 | 210.82M | Converted from GL model (log) |
| DenseNet-BC-40 (k=12) | 28.41 | 188,092 | 74.90M | Converted from GL model (log) |
| DenseNet-BC-40 (k=24) | 22.67 | 714,196 | 293.11M | Converted from GL model (log) |
| DenseNet-BC-40 (k=36) | 20.50 | 1,578,412 | 654.64M | Converted from GL model (log) |
| DenseNet-100 (k=12) | 19.65 | 4,129,600 | 1,353.62M | Converted from GL model (log) |
| DenseNet-100 (k=24) | 18.08 | 16,236,268 | 5,354.32M | Converted from GL model (log) |
| DenseNet-BC-100 (k=12) | 21.19 | 800,032 | 298.48M | Converted from GL model (log) |
| DenseNet-BC-250 (k=24) | 17.39 | 15,480,556 | 5,519.69M | Converted from GL model (log) |
| Model | Error, % | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|
| ResNet-20 | 3.43 | 272,474 | 41.29M | Converted from GL model (log) |
| ResNet-56 | 2.75 | 855,770 | 127.06M | Converted from GL model (log) |
| ResNet-110 | 2.45 | 1,730,714 | 255.70M | Converted from GL model (log) |
| ResNet-164(BN) | 2.42 | 1,704,154 | 255.31M | Converted from GL model (log) |
| ResNet-272(BN) | 2.43 | 2,816,986 | 420.61M | Converted from GL model (log) |
| ResNet-542(BN) | 2.34 | 5,599,066 | 833.87M | Converted from GL model (log) |
| ResNet-1001 | 2.41 | 10,328,602 | 1,536.40M | Converted from GL model (log) |
| PreResNet-20 | 3.22 | 272,282 | 41.27M | Converted from GL model (log) |
| PreResNet-56 | 2.80 | 855,578 | 127.03M | Converted from GL model (log) |
| PreResNet-110 | 2.79 | 1,730,522 | 255.68M | Converted from GL model (log) |
| PreResNet-164(BN) | 2.58 | 1,703,258 | 255.08M | Converted from GL model (log) |
| PreResNet-272(BN) | 2.34 | 2,816,090 | 420.38M | Converted from GL model (log) |
| PreResNet-542(BN) | 2.36 | 5,598,170 | 833.64M | Converted from GL model (log) |
| ResNeXt-20 (1x64d) | 2.98 | 3,446,602 | 538.36M | Converted from GL model (log) |
| ResNeXt-20 (2x32d) | 2.96 | 2,672,458 | 425.15M | Converted from GL model (log) |
| ResNeXt-20 (4x16d) | 3.17 | 2,285,386 | 368.55M | Converted from GL model (log) |
| ResNeXt-20 (8x8d) | 3.18 | 2,091,850 | 340.25M | Converted from GL model (log) |
| ResNeXt-20 (16x4d) | 3.21 | 1,995,082 | 326.10M | Converted from GL model (log) |
| ResNeXt-20 (32x2d) | 3.27 | 1,946,698 | 319.03M | Converted from GL model (log) |
| ResNeXt-20 (64x1d) | 3.42 | 1,922,506 | 315.49M | Converted from GL model (log) |
| ResNeXt-20 (2x64d) | 2.83 | 6,198,602 | 987.98M | Converted from GL model (log) |
| ResNeXt-20 (4x32d) | 2.98 | 4,650,314 | 761.57M | Converted from GL model (log) |
| ResNeXt-20 (8x16d) | 3.01 | 3,876,170 | 648.37M | Converted from GL model (log) |
| ResNeXt-20 (16x8d) | 2.93 | 3,489,098 | 591.77M | Converted from GL model (log) |
| ResNeXt-20 (32x4d) | 3.09 | 3,295,562 | 563.47M | Converted from GL model (log) |
| ResNeXt-20 (64x2d) | 3.14 | 3,198,794 | 549.32M | Converted from GL model (log) |
| ResNeXt-56 (1x64d) | 2.42 | 9,317,194 | 1,399.33M | Converted from GL model (log) |
| ResNeXt-56 (2x32d) | 2.46 | 6,994,762 | 1,059.72M | Converted from GL model (log) |
| ResNeXt-56 (4x16d) | 2.44 | 5,833,546 | 889.91M | Converted from GL model (log) |
| ResNeXt-56 (8x8d) | 2.47 | 5,252,938 | 805.01M | Converted from GL model (log) |
| ResNeXt-56 (16x4d) | 2.56 | 4,962,634 | 762.56M | Converted from GL model (log) |
| ResNeXt-56 (32x2d) | 2.53 | 4,817,482 | 741.34M | Converted from GL model (log) |
| ResNeXt-56 (64x1d) | 2.55 | 4,744,906 | 730.72M | Converted from GL model (log) |
| ResNeXt-29 (32x4d) | 2.80 | 4,775,754 | 780.55M | Converted from GL model (log) |
| ResNeXt-29 (16x64d) | 2.68 | 68,155,210 | 10,709.34M | Converted from GL model (log) |
| ResNeXt-272 (1x64d) | 2.34 | 44,540,746 | 6,565.15M | Converted from GL model (log) |
| ResNeXt-272 (2x32d) | 2.44 | 32,928,586 | 4,867.11M | Converted from GL model (log) |
| SE-ResNet-20 | 3.23 | 274,847 | 41.34M | Converted from GL model (log) |
| SE-ResNet-56 | 2.64 | 862,889 | 127.19M | Converted from GL model (log) |
| SE-ResNet-110 | 2.35 | 1,744,952 | 255.98M | Converted from GL model (log) |
| SE-ResNet-164(BN) | 2.45 | 1,906,258 | 256.55M | Converted from GL model (log) |
| SE-ResNet-272(BN) | 2.38 | 3,153,826 | 422.68M | Converted from GL model (log) |
| SE-ResNet-542(BN) | 2.26 | 6,272,746 | 838.01M | Converted from GL model (log) |
| SE-PreResNet-20 | 3.24 | 274,559 | 41.35M | Converted from GL model (log) |
| SE-PreResNet-56 | 2.71 | 862,601 | 127.20M | Converted from GL model (log) |
| SE-PreResNet-110 | 2.59 | 1,744,664 | 255.98M | Converted from GL model (log) |
| SE-PreResNet-164(BN) | 2.56 | 1,904,882 | 256.32M | Converted from GL model (log) |
| SE-PreResNet-272(BN) | 2.49 | 3,152,450 | 422.45M | Converted from GL model (log) |
| SE-PreResNet-542(BN) | 2.47 | 6,271,370 | 837.78M | Converted from GL model (log) |
| PyramidNet-110 (a=48) | 2.47 | 1,772,706 | 408.37M | Converted from GL model (log) |
| PyramidNet-110 (a=84) | 2.43 | 3,904,446 | 778.15M | Converted from GL model (log) |
| PyramidNet-110 (a=270) | 2.38 | 28,485,477 | 4,730.60M | Converted from GL model (log) |
| PyramidNet-164 (a=270, BN) | 2.34 | 27,216,021 | 4,608.81M | Converted from GL model (log) |
| PyramidNet-200 (a=240, BN) | 2.32 | 26,752,702 | 4,563.40M | Converted from GL model (log) |
| PyramidNet-236 (a=220, BN) | 2.35 | 26,969,046 | 4,631.32M | Converted from GL model (log) |
| PyramidNet-272 (a=200, BN) | 2.40 | 26,210,842 | 4,541.36M | Converted from GL model (log) |
| DenseNet-40 (k=12) | 3.05 | 599,050 | 210.80M | Converted from GL model (log) |
| DenseNet-BC-40 (k=12) | 3.20 | 176,122 | 74.89M | Converted from GL model (log) |
| DenseNet-BC-40 (k=24) | 2.90 | 690,346 | 293.09M | Converted from GL model (log) |
| DenseNet-BC-40 (k=36) | 2.60 | 1,542,682 | 654.60M | Converted from GL model (log) |
| DenseNet-100 (k=12) | 2.60 | 4,068,490 | 1,353.55M | Converted from GL model (log) |
| Model | Error, % | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|
| ResNet-10 | 27.58 | 5,008,392 | 893.63M | Training (log) |
| ResNet-12 | 26.68 | 5,082,376 | 1,125.84M | Training (log) |
| ResNet-14 | 24.35 | 5,377,800 | 1,357.53M | Training (log) |
| ResNet-16 | 23.28 | 6,558,472 | 1,588.93M | Training (log) |
| ResNet-18 | 23.35 | 11,279,112 | 1,820.00M | Training (log) |
| ResNet-26 | 22.64 | 17,549,832 | 2,746.38M | Training (log) |
| SE-ResNet-10 | 27.49 | 5,052,932 | 893.67M | Training (log) |
| SE-ResNet-12 | 26.11 | 5,127,496 | 1,125.88M | Training (log) |
| SE-ResNet-14 | 23.75 | 5,425,104 | 1,357.58M | Training (log) |
| SE-ResNet-16 | 23.21 | 6,614,240 | 1,588.99M | Training (log) |
| SE-ResNet-18 | 23.09 | 11,368,192 | 1,820.10M | Training (log) |
| SE-ResNet-26 | 22.58 | 17,683,452 | 2,746.52M | Training (log) |
| MobileNet x1.0 | 23.46 | 3,411,976 | 578.98M | Training (log) |
| ProxylessNAS Mobile | 22.02 | 3,055,712 | 331.44M | Training (log) |
| Model | Extractor | Pix.Acc.,% | mIoU,% | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|---|---|
| PSPNet | ResNet(D)-101b | 96.28 | 75.99 | 65,708,501 | 230,771.01M | From dmlc/gluon-cv (log) |
| DeepLabv3 | ResNet(D)-101b | 96.32 | 75.60 | 58,754,773 | 47,625.34M | From dmlc/gluon-cv (log) |
| DeepLabv3 | ResNet(D)-152b | 96.95 | 77.91 | 74,398,421 | 59,894.87M | From dmlc/gluon-cv (log) |
| FCN-8s(d) | ResNet(D)-101b | 97.53 | 80.39 | 52,072,917 | 196,562.96M | From dmlc/gluon-cv (log) |
| Model | Extractor | Pix.Acc.,% | mIoU,% | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|---|---|
| PSPNet | ResNet(D)-50b | 68.46 | 27.12 | 46,782,550 | 162,595.14M | From dmlc/gluon-cv (log) |
| PSPNet | ResNet(D)-101b | 74.76 | 32.59 | 65,774,678 | 231,008.79M | From dmlc/gluon-cv (log) |
| DeepLabv3 | ResNet(D)-50b | 74.34 | 31.72 | 39,795,798 | 32,756.18M | From dmlc/gluon-cv (log) |
| DeepLabv3 | ResNet(D)-101b | 77.50 | 34.88 | 58,787,926 | 47,651.23M | From dmlc/gluon-cv (log) |
| FCN-8s(d) | ResNet(D)-50b | 76.70 | 33.10 | 33,146,966 | 128,387.08M | From dmlc/gluon-cv (log) |
| FCN-8s(d) | ResNet(D)-101b | 78.72 | 35.50 | 52,139,094 | 196,800.73M | From dmlc/gluon-cv (log) |
| Model | Extractor | Pix.Acc.,% | mIoU,% | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|---|---|
| PSPNet | ResNet(D)-101b | 92.80 | 57.60 | 65,707,475 | 230,767.33M | From dmlc/gluon-cv (log) |
| ICNet | ResNet(D)-50b | 95.37 | 60.60 | 47,489,184 | 14,253.43M | From dmlc/gluon-cv (log) |
| Fast-SCNN | - | 94.98 | 65.05 | 1,138,051 | 3493.33M | From dmlc/gluon-cv (log) |
| DANet | ResNet(D)-50b | 95.96 | 68.06 | 47,586,427 | 180,397.43M | From dmlc/gluon-cv (log) |
| DANet | ResNet(D)-101b | 96.01 | 67.90 | 66,578,555 | 248,811.08M | From dmlc/gluon-cv (log) |
| Model | Extractor | Pix.Acc.,% | mIoU,% | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|---|---|
| PSPNet | ResNet(D)-101b | 88.91 | 54.38 | 65,708,501 | 230,771.01M | From dmlc/gluon-cv (log) |
| DeepLabv3 | ResNet(D)-101b | 89.98 | 58.65 | 58,754,773 | 47,625.34M | From dmlc/gluon-cv (log) |
| DeepLabv3 | ResNet(D)-152b | 90.40 | 60.67 | 74,398,421 | 275,087.91M | From dmlc/gluon-cv (log) |
| FCN-8s(d) | ResNet(D)-101b | 91.36 | 59.68 | 52,072,917 | 196,562.96M | From dmlc/gluon-cv (log) |
| Model | Extractor | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|
| BiSeNet | ResNet-18 | 13,300,416 | - | From zllrunning/face...Torch (log) |
| Model | Extractor | OKS AP, % | Params | FLOPs/2 | Remarks |
|---|---|---|---|---|---|
| AlphaPose | Fast-SE-ResNet-101b | 74.15/91.59/80.68 | 59,569,873 | 9,553.89M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet-18 | 66.31/89.20/73.41 | 15,376,721 | 1,799.25M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet-50b | 71.02/91.23/78.57 | 33,999,697 | 4,041.06M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet-101b | 72.44/92.18/79.76 | 52,991,825 | 7,685.04M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet-152b | 72.53/92.14/79.61 | 68,635,473 | 11,332.86M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet(A)-50b | 71.70/91.31/78.66 | 34,018,929 | 4,278.56M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet(A)-101b | 72.97/92.24/80.81 | 53,011,057 | 7,922.54M | From dmlc/gluon-cv (log) |
| SimplePose | ResNet(A)-152b | 73.44/92.27/80.72 | 68,654,705 | 11,570.36M | From dmlc/gluon-cv (log) |
| SimplePose(Mobile) | ResNet-18 | 66.25/89.17/74.32 | 12,858,208 | 1,960.96M | From dmlc/gluon-cv (log) |
| SimplePose(Mobile) | ResNet-50b | 71.10/91.28/78.67 | 25,582,944 | 4,221.30M | From dmlc/gluon-cv (log) |
| SimplePose(Mobile) | 1.0 MobileNet-224 | 64.10/88.06/71.23 | 5,019,744 | 751.36M | From dmlc/gluon-cv (log) |
| SimplePose(Mobile) | 1.0 MobileNetV2b-224 | 63.74/88.12/71.06 | 4,102,176 | 495.95M | From dmlc/gluon-cv (log) |
| SimplePose(Mobile) | MobileNetV3 Small 224/1.0 | 54.34/83.67/59.35 | 2,625,088 | 236.51M | From dmlc/gluon-cv (log) |
| SimplePose(Mobile) | MobileNetV3 Large 224/1.0 | 63.67/88.91/70.82 | 4,768,336 | 403.97M | From dmlc/gluon-cv (log) |
| Lightweight OpenPose 2D | MobileNet | 39.99/65.95/40.70 | 4,091,698 | 8,948.96M | From Daniil-Osokin/lighw...ch (log) |
| Lightweight OpenPose 3D | MobileNet | 39.99/65.95/40.70 | 5,085,983 | 11,049.43M | From Daniil-Osokin/li...3d...ch (log) |
| IBPPose | - | 64.87/83.62/70.13 | 95,827,784 | 57,195.91M | From jialee93/Improved...Parts (log) |