ethereon/caffe-tensorflow

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2786 stars · 1012 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python tool that converts Caffe-trained neural network models into TensorFlow format, producing a NumPy parameter file and a Python class that builds the model graph. It includes verified conversion examples for popular ImageNet models like ResNet, VGG, GoogLeNet, and AlexNet.

Use cases

• convert a caffe model to tensorflow
• port pretrained imagenet weights from caffe to tensorflow
• load caffe .caffemodel parameters in tensorflow
• rebuild a vgg16 or resnet graph in tensorflow
• verify converted model accuracy on ilsvrc2012
• migrate legacy deep learning models between frameworks

When to choose

• you have pretrained Caffe models (new format) and want to use them in TensorFlow
• you need verified conversions of standard architectures like ResNet or VGG
• you want weights extracted as NumPy data plus a graph-building class

When to avoid

• your Caffe model uses old format or unsupported layers/padding
• you need a maintained tool - the project has seen little activity since 2019
• you need runtime interop between Caffe and TensorFlow in one process (CUDA conflicts prevent it)

Facets

library · maturity maintenance

machine-learning deep-learning parser serialization deep-learning machine-learning developer-tools python caffe tensorflow model-conversion neural-networks model-porting gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ethereon/caffe-tensorflow")