GoogleNet weights trained on the Places dataset for Keras.

This file (googlenet_weights.h5) contains the initial weights of GoogleNet (aka v1) trained on the Places dataset, and is used for fine-tuning task related to pose regression networks. The file was downloaded from https://github.com/kentsommer/keras-posenet. Adding to the repository is only for the purpose of eliminating dependency on external URLs.Other files contain the weights of the final trained model from our experiments of the paper Recurrent BIM-PoseNet: SynCar - Weights of model fine-tuned on Synthetic Cartoonish images.SynPhoReal - Weights of model fine-tuned on Synthetic photo-realistic images.SynPhoRealTex - Weights of model fine-tuned on Synthetic photo-realistic textured images.GradmagSynCar - Weights of model fine-tuned on synthetic gradmag of SynCar images.EdgeRender - Weights of model fine-tuned on Synthetic edge render images.Other details in the name of the weight files describes the parameters, such as window length, learning rate, batch, ...., etc. This is a support file for the code available at https://github.com/debaditya-unimelb/RecurrentBIM-PoseNet.

此文件（googlenet_weights.h5）包含基于 Places 数据集训练的 GoogleNet（亦称 v1 版本）的初始权重，并用于与姿态回归网络相关的微调任务。该文件从 https://github.com/kentsommer/keras-posenet 网址下载。将文件添加至仓库的目的是为了消除对外部 URL 的依赖。其他文件包含了我方实验中论文《Recurrent BIM-PoseNet: SynCar - 基于合成卡通化图像微调的模型权重》、《SynPhoReal - 基于合成真实照片图像微调的模型权重》、《SynPhoRealTex - 基于合成真实纹理图像微调的模型权重》以及《GradmagSynCar - 基于合成 gradmag SynCar 图像微调的模型权重》。EdgeRender 文件包含基于合成边缘渲染图像微调的模型权重。权重文件名称中的其他细节描述了参数，例如窗口长度、学习率、批量等。此文件是位于 https://github.com/debaditya-unimelb/RecurrentBIM-PoseNet 的代码的支持文件。