John Feng's Projects
TensorFlow code and pre-trained models for BERT
The complete project of Self-Driving Car Engineer Nanodegree Program. I done the assignment at winter, 2018. I just upload this in to github.
The complete project of Self-Driving Car Engineer Nanodegree Program. I done the assignment at Jan, 2019. I just upload this in to github.
The complete project of Self-Driving Car Engineer Nanodegree Program. I done the assignment at spring, 2019. I just upload this in to github.
The complete project of Self-Driving Car Engineer Nanodegree Program. I done the assignment at winter, 2018. I just upload this in to github.
The complete project of Self-Driving Car Engineer Nanodegree Program. I done the assignment at winter, 2018. I just upload this in to github.
This repository shows the question and answering demo with distilled Chinese BERT model.
An ordering system that based on the speech recognition, BERT and voice synthesize for Chinese users.
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
The complete assignment of cs231n course, it include some small project such as NN, BN, Dropout, CNN, etc. I done the assignment at spring, 2017. I just upload this in to github.
The complete assignment of cs231n course, it include some small project such as Image Captioning with Vanilla RNNs, LSTM, etc. I done the assignment at spring, 2017. I just upload this in to github.
The assignment of cs231n course, it include some small project such as knn, softmax, svm, etc. I done the assignment at spring, 2017. I just upload this in to github.
The Data Augmentation functions in python base on numpy and opencv.
Deep Learning Book Chinese Translation
PyTorch re-implementation of DeepMask
A TensorFlow implementation of Baidu's DeepSpeech architecture
This is the demo application for Deep Speech algorithm, which make speech to text that are being performed on input speech audio.
Deep Learning Deployment Toolkit
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
starter from "How to Train a GAN?" at NIPS2016
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Using OpenVINO to run the image captioning on C++ and python.
C Programming Lab: Assessing Your C Programming Skills
Mandarin text-to-speech 中文语音合成(TTS), based on Fastspeech2
MelGAN vocoder (compatible with NVIDIA/tacotron2)
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2020"
machine learning algorithms and implementations