GoogleNet weights trained on the Places dataset for Keras.
收藏DataCite Commons2025-05-01 更新2025-04-17 收录
下载链接：
https://melbourne.figshare.com/articles/GoogleNet_weights_trained_on_the_Places_dataset_for_Keras_/10959350
下载链接
链接失效反馈官方服务：
资源简介：
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 <i>https://github.com/kentsommer/keras-posenet.</i> Adding to the repository is only for the purpose of eliminating dependency on external URLs.<br>Other files contain the weights of the final trained model from our experiments of the paper Recurrent BIM-PoseNet: <br><b>SynCar</b> - Weights of model fine-tuned on Synthetic Cartoonish images.<b>SynPhoReal</b> - Weights of model fine-tuned on Synthetic photo-realistic images.<b>SynPhoRealTex </b>- Weights of model fine-tuned on Synthetic photo-realistic textured images.<b>GradmagSynCar</b> - Weights of model fine-tuned on synthetic gradmag of SynCar images.<b>EdgeRender </b>- Weights of model fine-tuned on Synthetic edge render images.<br>Other details in the name of the weight files describes the parameters, such as window length, learning rate, batch, ...., etc. <br><br>This is a support file for the code available at <i>https://github.com/debaditya-unimelb/RecurrentBIM-PoseNet.</i>
提供机构：
University of Melbourne
创建时间：
2019-11-23
