liuppgit Goto Github PK

deep-face-vsr

Visual speech recognition with face inputs: code and models for F&G 2020 paper "Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition"

face_detection

flowers5_train

搭建tensorflow卷积网络训练flowers5分类模型，其中数据集是自己制作的tfrecords数据集，由于机器实在不给力只能搭建简单的卷积网络（2conv+2fullconnect）进行训练，整个网络搭建流程自己学习到的知识有：tfrecords数据集制作， 数据预处理，数据增广，训练模型数据的保存，tensorboard的使用， tfdbg的使用。数据增广方面除了使用tensorflow提供的函数，自己用tf.py_func定义了一个图片旋转的op， 可以随机旋转-20到20度。

hands-on-computer-vision-with-tensorflow-2

Hands-On Computer Vision with TensorFlow 2, published by Packt

lipreading-densenet3d

DenseNet3D Model In "LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild", https://arxiv.org/abs/1810.06990

lipreading_using_temporal_convolutional_networks

ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks

pydatapreprocessing

《Python数据预处理技术与实践》源码下载

siamesenetwork-tensorflow

Using siamese network to do dimensionality reduction and similar image retrieval

test

第一个repository呢

visual_speech_recognition_for_multiple_languages

Visual Speech Recognition for Multiple Languages