Beibei

I have the similar needs. Could someone kindly share this file with us? Many thanks! Also, I'm trying to reproduce the work and get the training code to work. If...

I am having the same issue. I'm using Windows 10, Visual Studio Code, Powershell to run the code. I already installed all those requirements successfully. I can also load deca_model.tar...

NEW UPDATE: I tried `CUDA_VISIBLE_DEVICES=0 make runtest` instead of `make runtest` And I got more test cases past but still got the same issue with CUDA device number = 0....

Followup: In the code there are many more datasets than in the paper: ```python def build_train(config, is_train=True): data_list = [] if 'vox2' in config.training_data: data_list.append(VoxelDataset(dataname='vox2', K=config.K, image_size=config.image_size, scale=[config.scale_min, config.scale_max], trans_scale=config.trans_scale,...

In the validation step, all the code does is visualizing the results. How do we know quantitatively that the model is improving? ```python def validation_step(self): self.deca.eval() try: batch = next(self.val_iter)...