对神经网络的权值进行量化,使模型大小变小,运行速度变快,且准确率与原来相近。
Continue reading对神经网络(主要是CNN)进行剪枝,使模型运行速度变快,大小变小,且准确率与原来相近。
Continue reading介绍神经网络(主要是CNN)模型压缩与加速的常见方法
Continue reading代码仓库:https://github.com/lijiancheng0614/tensorflow_object_detection
修改TensorFlow Object Detection API,添加一些方便使用或新的功能。
Continue reading使用TensorFlow Android Inference Interface在Android上进行图像物体检测
不支持Camera2 API的手机也可以物体检测:https://github.com/lijiancheng0614/android-TFDetect
Continue reading参考 https://github.com/tensorflow/models/tree/master/research/object_detection
使用TensorFlow Object Detection API进行物体检测
Continue reading参考 https://github.com/tensorflow/models/tree/master/research/slim
使用TensorFlow-Slim进行图像分类
Continue readingRethinking Atrous Convolution for Semantic Image Segmentation
Paper: https://arxiv.org/abs/1706.05587
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
Paper: https://arxiv.org/abs/1606.02147
Code: https://github.com/e-lab/ENet-training