Skip to content
#

tensorflowjs

Here are 794 public repositories matching this topic...

pt-br
pt-br commented Aug 24, 2019

I've ran into this issue for a couple hours and I ended up editing the dist library adding two new functions called fetchVideo and bufferToVideo that works pretty much like the fetchImage and bufferToImage functions.

I'll leave it here to help somebody else with the same issue and in case someone wants to include it on future releases.

face-api.js

...
exports.fetchVideo = fetc
nsfwjs

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

  • Updated Jul 22, 2021
  • Python
human

Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

  • Updated Jul 30, 2021
  • TypeScript

This script converts the OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC) -> TFLite (NHWC). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflite and saved_model to .tflite and saved_model to onnx. 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.

  • Updated Jul 30, 2021
  • Python

Improve this page

Add a description, image, and links to the tensorflowjs topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the tensorflowjs topic, visit your repo's landing page and select "manage topics."

Learn more