search

mks0601 / I2L-MeshNet_RELEASE

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
MIT License
710 stars 130 forks source link

Regarding the calculation of the three indicators The PA MPVPE, PA MPJPE, and F-scores when test on the Freihand dataset #60

Open booker-max opened 3 years ago

booker-max commented 3 years ago

Hello, when I tested the network on the Freihand dataset, the annotation in the testset did not provide joint_cam, and mano parameters, your code uses dummy data, and uses the np.ones() function to generate joint_cam and mano parameters.

微信图片_20210408084437 I would like to ask whether the final calculation of PA MPVPE, PA MPJPE, and F-scores also uses dummy data? Do you have a specific code?

mks0601 commented 3 years ago

You should submit the saved json file to the evalation server. See here.

booker-max commented 3 years ago

Great! Thank you.