Xiong Lin

How to finetune with new dataset ?

1

Do you plan to release finetune code ? or If I want to finetune model with new dataset (different classes), how can I remove the weights in arcface_loss after load...

How to convert the cuda-based npz model to npz used in web demo ?

2

I trained nerf-sh model with chair dataset. After extraction and optimization, I got the tree_opt.npz. However, I loaded this npz with webgl viewer, I got an incorrect viewing result as...

training speed

1

I run training code, but the speed is quite slow. only 20 images/sec even I set batch_image =32 on 1 GPU or 4 GPU even larger. Could you give some...

Segmentation fault

4

is there any good solution to solve the segmentation fault occured randomly when training pretrain model?

I can't find the pretrained model, could you update your link of pretrained model ?

How to recover the global rotation of root for amass?

1

The preprocess of data in amass data_loader, the global rotation of root is removed. How to recover the global rotation of root in order to prepare data for training and...

How can I use this Resnet to fine-tune on other application ? such as face data

2

@tornadomeet Thank you for your Resnet implementation with MxNet. At present, I have completed train imagenet'12 dataset with Resnet 50 and Resnet 101. I can get the similar performance, although,...

Can not convert to mesh from ply

3

 I try to convert .ply to textured mesh with convert.py. But I got this error as showed above. How can I fix it ?