res-loglikelihood-regression
res-loglikelihood-regression copied to clipboard
Jeff-sjtu
Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral
你好，大佬我是一名本科生对你的工作十分感兴趣。但是在尝试替换loss时遇到了问题。 1.无法直接在其他项目内替换loss（如HRNet的官方代码），我尝试替换数据集定义文件也失败 2.大佬你提供的项目内好像没有可视化以及AP,AR详细精度的结果输出 3.请问如果要更换backbone网络如更改为HourglassNet需要更改为分类网络后在跟nvp适配么，不添加分类头的话会如何呢 谢谢大佬
Hello, could you tell me why the third dimension must ensure is 2? " out_coord = self.fc_coord(x).reshape(BATCH_SIZE, self.num_joints, 2) assert out_coord.shape[2] == 2"
Thank you for this grate work! I noticed that the Google Drive link provided for the Human3.6M parsed data is no longer accessible. Could you please check and update the...
