AltHub

Cadene/pretrained-models.pytorch Alternatives

pretrained image classification models

A PyTorch collection of pretrained ConvNet models (NASNet, ResNeXt, ResNet, Inception, Xception, DPN, etc.) with a unified API for transfer learning.

9.1kPythonBSD-3-Clausedormant · last push 4.5y agoGitHub

Same job, different approach

Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.

qubvel/classification_modelsGitHub

Choose if you need Keras-compatible pretrained classification models; different framework, so not drop-in for PyTorch.

Classification models trained on ImageNet. Keras.

1.2k
Python
MIT
dormant4.2y ago
taehoonlee/tensornetsGitHub

Choose if you need pretrained models in TensorFlow; different framework and API.

High level network definitions with pre-trained weights in TensorFlow

996
Python
MIT
dormant5.8y ago

Older generation, or narrower

An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.

alexandonian/pretorched-xGitHub

Stale PyTorch zoo; choose if you also need video/GAN models, but expect no maintenance.

Pretrained Image & Video ConvNets and GANs for PyTorch: NASNet, ResNeXt (2D + 3D), ResNet (2D + 3D), InceptionV4, InceptionResnetV2, Xception, DPN, NonLocalNets, R(2+1)D nets, MultiView CNNs, Temporal Relation Networks, BigGANs StyleGANs, etc.

332
Python
MIT
dormant4.7y ago
rwightman/pytorch-dpn-pretrainedGitHub

Narrower DPN-only pretrained weights; choose if you only need DPN and want the original MXNet port, but it's stale.

Dual Path Networks (DPN) supporting pretrained weights converted from original MXNet implementation

205
Python
Apache-2.0
dormant7.3y ago
yeephycho/nasnet-tensorflowGitHub

Single NASNet model in TensorFlow; choose only if you need NASNet in TF and don't mind old code.

A nasnet in tensorflow

135
Python
Apache-2.0
dormant5.2y ago
titu1994/Keras-NASNetGitHub

Keras NASNet with weights; narrower alternative if you specifically need NASNet in Keras.

"NASNet" models in Keras 2.0+ with weights

196
Python
MIT
dormant8.4y ago
kentsommer/keras-inceptionV4GitHub

Keras InceptionV4 with pretrained weights; narrow alternative for that one model.

Keras Implementation of Google's Inception-V4 Architecture (includes Keras compatible pre-trained weights)

467
Python
Apache-2.0
dormant9.1y ago

Listed as an alternative to

These projects were analysed and named pretrained-models.pytorch among their alternatives. The relationship is not symmetric — how pretrained-models.pytorch rates them is a separate judgement, made when pretrained-models.pytorch is analysed in its own right.

huggingface/pytorch-image-modelsGitHub

calls pretrained-models.pytorch “Older pretrained ConvNet zoo; choose if you need its original weight APIs, but it is unmaintained.”

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

37.2kPythonactive