Tensorflow Models Python Packages

onnx2keras

Convert ONNX model graph to Keras model format.

tflite2tensorflow

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite, ONNX, OpenVINO, Myriad Inference Engine blob and .pb from .tflite. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support. Supports inverse quantization of INT8 quantization model.

face-detection-tflite

Face and iris detection for Python based on MediaPipe

automatic-speech-recognition

🎧 Automatic Speech Recognition: DeepSpeech & Seq2Seq (TensorFlow)

spflow

Sum Product Flow: An Easy and Extensible Library for Sum-Product Networks

openmodelzoo-modelapi

Pre-trained Deep Learning models and demos (high quality and extremely fast)

tf-object-detection

A Thin Wrapper around Tensorflow Object Detection API for Easy Installation and Use

pytorch2keras

PyTorch to Keras model convertor

nondefaced-detector

Identify non-defaced datasets before publication

simple-tensorflow-serving

The simpler and easy-to-use serving service for TensorFlow models

seq2annotation

seq2annotation

nn-meter

A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.

steppy-toolkit

Curated set of transformers that make your work with steppy faster and more effective :telescope:

tfserve

Serve TF models simple and easy as an HTTP API

kelner

Serve your models

s2a-nightly

基于 TensorFlow & PaddlePaddle 的通用序列标注算法库（目前包含 BiLSTM+CRF, Stacked-BiLSTM+CRF 和 IDCNN+CRF，更多算法正在持续添加中）实现中文分词（Tokenizer / segmentation）、词性标注（Part Of Speech, POS）和命名实体识别（Named Entity Recognition, NER）等序列标注任务。

tf-sdp

Deep nonparametric estimation of discrete conditional distributions via smoothed dyadic partitioning