efficient CNN model zoo / PyTorch image classification backbones
A PyTorch library providing implementations and pretrained weights for efficient CNN architectures (EfficientNet, MobileNet, etc.).
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it as the actively maintained superset that the seed's readme recommends replacing it with.
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
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it if you need EfficientNet in TensorFlow.js for browser or Node.js deployment instead of PyTorch.
tensorflowJS implementation of EfficientNet 🚀
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose it for a TensorFlow 1.x model zoo if you cannot use PyTorch and need older pretrained classification models.
High level network definitions with pre-trained weights in TensorFlow
Choose it for a notebook-based collection of basic PyTorch classification models if you don't need pretrained weights or a unified API.
用于pytorch的图像分类，包含多种模型方法，比如AlexNet，VGG，GoogleNet，ResNet，DenseNet等等，包含可完整运行的代码。除此之外，也有colab的在线运行代码，可以直接在colab在线运行查看结果。也可以迁移到自己的数据集进行迁移学习。
These projects were analysed and named gen-efficientnet-pytorch among their alternatives. The relationship is not symmetric — how gen-efficientnet-pytorch rates them is a separate judgement, made when gen-efficientnet-pytorch is analysed in its own right.
calls gen-efficientnet-pytorch “EfficientNet-family-only predecessor of timm; choose for a minimal dependency on just those architectures.”
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