wqz960

I train the model on val2017 dataset and my own dataset, but the valid result is about 21db, have you tested them ?Thank you!

how to use the landmarks to process the gt parsing maps, i saw the previous issue, the method is called GFC, I can not find the paper , can u...

some other networks do not converge in the second stage.

3

Hi! Thank you for your excellent work, I just replaced the network which is vgg in your original network with Resnet or some others for my interest. during the first-stage...

Too difficult to reimplement your project !

5

Hi! I am very interesting in your project! But it seems that there are some difference between the Traindataset process script and the actual script in your paper. And can...

some questions about GeneratePerturbations function

2

HI ! Thanks for your codes! But i am confused in the GeneratePerturbation function. I am poor in math , can you provide me some information or paper to let...

you codes seem just for 300W-LP, if I want to train on 300W dataset, how can I change the codes, or just change the the load to image file?

Hi! some errors during the training!

3

[face_alignment_300w_hrnet_w18_2019-07-18-21-22_train.log](https://github.com/HRNet/HRNet-Facial-Landmark-Detection/files/3409038/face_alignment_300w_hrnet_w18_2019-07-18-21-22_train.log) Hi!, I am very interesting in your codes, and I want to retrain the network by your configure file, but it seems that it has a big difference between...

how to calculate the scale, can you provide me the script to write csv?

4

Thank you for your code! Could you please provide the script to write csv? Thank you!