You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
pytorch-image-models/docs/models.md

12 KiB

Model Architectures

The model architectures included come from a wide variety of sources. Sources, including papers, original impl ("reference code") that I rewrote / adapted, and PyTorch impl that I leveraged directly ("code") are listed below.

Most included models have pretrained weights. The weights are either:

  1. from their original sources
  2. ported by myself from their original impl in a different framework (e.g. Tensorflow models)
  3. trained from scratch using the included training script

The validation results for the pretrained weights can be found here

Big Transfer ResNetV2 (BiT) [resnetv2.py]

Cross-Stage Partial Networks [cspnet.py]

DenseNet [densenet.py]

DLA [dla.py]

Dual-Path Networks [dpn.py]

GPU-Efficient Networks [byobnet.py]

HRNet [hrnet.py]

Inception-V3 [inception_v3.py]

Inception-V4 [inception_v4.py]

Inception-ResNet-V2 [inception_resnet_v2.py]

NASNet-A [nasnet.py]

PNasNet-5 [pnasnet.py]

EfficientNet [efficientnet.py]

MobileNet-V3 [mobilenetv3.py]

RegNet [regnet.py]

RepVGG [byobnet.py]

ResNet, ResNeXt [resnet.py]

Res2Net [res2net.py]

ResNeSt [resnest.py]

ReXNet [rexnet.py]

Selective-Kernel Networks [sknet.py]

SelecSLS [selecsls.py]

Squeeze-and-Excitation Networks [senet.py]

NOTE: I am deprecating this version of the networks, the new ones are part of resnet.py

TResNet [tresnet.py]

VGG [vgg.py]

Vision Transformer [vision_transformer.py]

VovNet V2 and V1 [vovnet.py]

Xception [xception.py]

Xception (Modified Aligned, Gluon) [gluon_xception.py]

Xception (Modified Aligned, TF) [aligned_xception.py]