| lutzroeder/netron |
25,287 |
|
4 |
70 |
about 2 years ago |
610 |
December 09, 2023 |
27 |
mit |
JavaScript |
| Visualizer for neural network, deep learning and machine learning models |
| Tencent/ncnn |
18,693 |
|
0 |
1 |
about 2 years ago |
26 |
October 27, 2023 |
1,010 |
other |
C++ |
| ncnn is a high-performance neural network inference framework optimized for the mobile platform |
| onnx/onnx |
16,275 |
|
148 |
493 |
about 2 years ago |
31 |
October 26, 2023 |
296 |
apache-2.0 |
Python |
| Open standard for machine learning interoperability |
| ufoym/deepo |
6,312 |
|
0 |
0 |
about 3 years ago |
0 |
|
1 |
mit |
Python |
| Setup and customize deep learning environment in seconds. |
| microsoft/MMdnn |
5,767 |
|
3 |
0 |
over 2 years ago |
10 |
July 24, 2020 |
333 |
mit |
Python |
| 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. |
| ysh329/deep-learning-model-convertor |
3,197 |
|
0 |
0 |
almost 3 years ago |
0 |
|
2 |
|
|
| The convertor/conversion of deep learning models for different deep learning frameworks/softwares. |
| PINTO0309/PINTO_model_zoo |
3,121 |
|
0 |
0 |
about 2 years ago |
0 |
|
11 |
mit |
Python |
| A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML. |
| onnx/tensorflow-onnx |
2,133 |
|
3 |
64 |
about 2 years ago |
32 |
August 25, 2023 |
163 |
apache-2.0 |
Jupyter Notebook |
| Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX |
| fastmachinelearning/hls4ml |
1,913 |
|
0 |
0 |
21 days ago |
10 |
November 16, 2023 |
164 |
apache-2.0 |
Python |
| Machine learning on FPGAs using HLS |
| neuralmagic/sparseml |
1,910 |
|
0 |
5 |
about 2 years ago |
37 |
December 04, 2023 |
60 |
apache-2.0 |
Python |
| Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models |
