Sealbook / Open source / Machine learning & data science

microsoft/MMdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

caffecntkcoremldarknetkerasmodel-convertermxnetonnxpytorchtensorflow

GitHub ↗

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 14 months ago.

Similar projects

	Repository	Stars	Language	License	Activity
1	Tencent/ncnnncnn is a high-performance neural network inference framework optimized for the mobile platform	★ 24k	C++	Other	Active
2	microsoft/onnxruntimeONNX Runtime: cross-platform, high performance ML inferencing and training accelerator	★ 22.1k	C++	MIT	Active
3	horovod/horovodDistributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.	★ 14.7k	Python	Other	Archived
4	keras-team/kerasDeep Learning for humans	★ 64.4k	Python	Apache-2.0	Active
5	CorentinJ/Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-time	★ 60.2k	Python	Other	Slowing
6	ultralytics/yolov5Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.	★ 58.2k	Python	AGPL-3.0	Active
7	lutzroeder/netronVisualizer for neural network, deep learning and machine learning models	★ 33.6k	JavaScript	MIT	Active
8	deepinsight/insightfaceState-of-the-art 2D and 3D Face Analysis Project	★ 30k	Python	—	Active